Search

Image classification tasks often compress the neural network model to reduce the number of parameters, which leads to a decrease in classification accuracy. herefore, we propose a novel ResNet50-based attention mechanism for image classification. ResNet50 network is used to extract image features and input the features into the graph neural network as node features. Then, packet convolution and depth-separable convolution are used to compress the residual network. The attention mechanism is introduced into the network backbone to make it focus on the important part of the neighborhood and help the branch network to extract key information. The accuracy of 5-way 1-shot task classification on three publicly available datasets reaches 86.32%, 92.21% and 92.19%, respectively. The proposed method has achieved remarkable results in image classification tasks.

Background Lung metastasis is the primary cause of breast cancer-related mortality. Neutrophil extracellular traps (NETs) are involved in the progression of breast cancer. However, the mechanism of NET formation is not fully understood. This study posits that tumor cell-released autophagosomes (TRAPs) play a crucial role in this process.Methods TRAPs were isolated from breast cancer cell lines to analyze their impact on NET formation in both human and mouse neutrophils. The study used both in vitro and in vivo models, including Toll-like receptor 4 (TLR4−/−) mice and engineered breast cancer cell lines. Immunofluorescence, ELISA, Western blotting, RNA sequencing, and flow cytometry were employed to dissect the signaling pathways leading to NET production and to explore their immunosuppressive effects, particularly focusing on the impact of NETs on T-cell function. The therapeutic potential of targeting TRAP-induced NETs and their immunosuppressive functions was evaluated using DNase I and αPD-L1 antibodies. Clinical relevance was assessed by correlating circulating levels of TRAPs and NETs with lung metastasis in patients with breast cancer.Results This study showed that TRAPs induced the formation of NETs in both human and mouse neutrophils by using the high mobility group box 1 and activating the TLR4-Myd88-ERK/p38 signaling axis. More importantly, PD-L1 carried by TRAP-induced NETs inhibited T-cell function in vitro and in vivo, thereby contributing to the formation of lung premetastatic niche (PMN) immunosuppression. In contrast, Becn1 KD-4T1 breast tumors with decreased circulating TRAPs in vivo reduced the formation of NETs, which in turn attenuated the immunosuppressive effects in PMN and resulted in a reduction of breast cancer pulmonary metastasis in murine models. Moreover, treatment with αPD-L1 in combination with DNase I that degraded NETs restored T-cell function and significantly reduced tumor metastasis. TRAP levels in the peripheral blood positively correlated with NET levels and lung metastasis in patients with breast cancer.Conclusions Our results demonstrate a novel role of TRAPs in the formation of PD-L1-decorated NETs, which may provide a new strategy for early detection and treatment of pulmonary metastasis in patients with breast cancer.

Vibration problems have become one of the most important factors affecting robot performance. To this end, a terminal residual vibration suppression method based on joint trajectory optimization is proposed to improve the accuracy and stability of robot motion. Firstly, based on the characteristics of the friction nonlinearity due to joint coupling and physical feasibility of dynamic parameters, a semidefinite programming method is used to identify dynamic parameters with actual physical meaning, thereby obtaining an accurate dynamic model. Then, based on the result of the residual vibration time domain analysis, a joint trajectory optimization model with the goal of minimizing joint tracking error is established. The Chebyshev collocation method is used to discretize the optimization model. The dynamic model is used as the optimization constraint, and barycentric interpolation is used to obtain the optimized joint motion trajectory. Finally, industrial robot experiments prove that the vibration suppression method proposed in this article can reduce the maximum acceleration amplitude of residual vibration by 62% and the vibration duration by 71%. Compared with the input shaping method, the method proposed in this paper can reduce the terminal residual vibration more effectively and ensure the consistency of running time and trajectory.

This paper analyzes traditional vibration suppression methods in order to solve the vibration problem caused by the stiffness of flexible industrial robots. The principle of closed-loop control dynamic feedforward vibration suppression is described as the main method for solving robot vibration suppression. This paper proposes a method for time-lag filtering based on T-trajectory interpolation, which combines the T-planning curve and the time-lag filtering method. The method’s basic principle is to dynamically adjust the trajectory output through the algorithm, which effectively suppresses the amplitude of the harmonic components of a specific frequency band to improve the vibration response of industrial robot systems. This experiment compared traditional vibration suppression methods with the time-lag filtering method based on T-trajectory interpolation. A straight-line method was proposed to measure the degree of vibration. The results demonstrate that the time-lag filtering method based on T-trajectory interpolation is highly effective in reducing the vibration of industrial robots. This makes it an excellent option for scenarios that demand real-time response and high-precision control, ultimately enhancing the efficiency and stability of robots in performing their tasks.

The current semantic segmentation algorithms suffer from encoding feature distortion and small object feature loss. Context information exchange can effectively address the feature distortion problem, but it has the issue of fixed spatial range. Maintaining the input feature resolution can reduce the loss of small object information but would slow down the network’s operation speed. To tackle these problems, we propose a lightweight semantic segmentation network with configurable context and small object attention (CCSONet). CCSONet includes a long-short distance configurable context feature enhancement module (LSCFEM) and a small object attention decoding module (SOADM). The LSCFEM differs from the regular context exchange module by configuring long and short-range relevant features for the current feature, providing a broader and more flexible spatial range. The SOADM enhances the features of small objects by establishing correlations among objects of the same category, avoiding the introduction of redundancy issues caused by high-resolution features. On the Cityscapes and Camvid datasets, our network achieves the accuracy of 76.9 mIoU and 73.1 mIoU, respectively, while maintaining speeds of 87 FPS and 138 FPS. It outperforms other lightweight semantic segmentation algorithms in terms of accuracy.

This study introduces a parallel YOLO–GG deep learning network for collaborative robot target recognition and grasping to enhance the efficiency and precision of visual classification and grasping for collaborative robots. First, the paper outlines the target classification and detection task, the grasping system of the robotic arm, and the dataset preprocessing method. The real-time recognition and grasping network can identify a diverse spectrum of unidentified objects and determine the target type and appropriate capture box. Secondly, we propose a parallel YOLO–GG deep vision network based on YOLO and GG-CNN. Thirdly, the YOLOv3 network, pre-trained with the COCO dataset, identifies the object category and position, while the GG-CNN network, trained using the Cornell Grasping dataset, predicts the grasping pose and scale. This study presents the processes for generating a target’s grasping frame and recognition type using GG-CNN and YOLO networks, respectively. This completes the investigation of parallel networks for target recognition and grasping in collaborative robots. Finally, the experimental results are evaluated on the self-constructed NEU-COCO dataset for target recognition and positional grasping. The speed of detection has improved by 14.1%, with an accuracy of 94%. This accuracy is 4.0% greater than that of YOLOv3. Experimental proof was obtained through a robot grasping actual objects.

Lightweight semantic segmentation promotes the application of semantic segmentation in tiny devices. The existing lightweight semantic segmentation network (LSNet) has the problems of low precision and a large number of parameters. In response to the above problems, we designed a full 1D convolutional LSNet. The tremendous success of this network is attributed to the following three modules: 1D multi-layer space module (1D-MS), 1D multi-layer channel module (1D-MC), and flow alignment module (FA). The 1D-MS and the 1D-MC add global feature extraction operations based on the multi-layer perceptron (MLP) idea. This module uses 1D convolutional coding, which is more flexible than MLP. It increases the global information operation, improving features’ coding ability. The FA module fuses high-level and low-level semantic information, which solves the problem of precision loss caused by the misalignment of features. We designed a 1D-mixer encoder based on the transformer structure. It performed fusion encoding of the feature space information extracted by the 1D-MS module and the channel information extracted by the 1D-MC module. 1D-mixer obtains high-quality encoded features with very few parameters, which is the key to the network’s success. The attention pyramid with FA (AP-FA) uses an AP to decode features and adds a FA module to solve the problem of feature misalignment. Our network requires no pre-training and only needs a 1080Ti GPU for training. It achieved 72.6 mIoU and 95.6 FPS on the Cityscapes dataset and 70.5 mIoU and 122 FPS on the CamVid dataset. We ported the network trained on the ADE2K dataset to mobile devices, and the latency of 224 ms proves the application value of the network on mobile devices. The results on the three datasets prove that the network generalization ability we designed is powerful. Compared to state-of-the-art lightweight semantic segmentation algorithms, our designed network achieves the best balance between segmentation accuracy and parameters. The parameters of LSNet are only 0.62 M, which is currently the network with the highest segmentation accuracy within 1 M parameters.

Semantic segmentation can address the perceived needs of autonomous driving and micro-robots and is one of the challenging tasks in computer vision. From the application point of view, the difficulty faced by semantic segmentation is how to satisfy inference speed, network parameters, and segmentation accuracy at the same time. This paper proposes a lightweight multi-dimensional dynamic convolutional network (LMDCNet) for real-time semantic segmentation to address this problem. At the core of our architecture is Multidimensional Dynamic Convolution (MDy-Conv), which uses an attention mechanism and factorial convolution to remain efficient while maintaining remarkable accuracy. Specifically, LMDCNet belongs to an asymmetric network architecture. Therefore, we design an encoder module containing MDy-Conv convolution: MS-DAB. The success of this module is attributed to the use of MDy-Conv convolution, which increases the utilization of local and contextual information of features. Furthermore, we design a decoder module containing a feature pyramid and attention: SC-FP, which performs a multi-scale fusion of features accompanied by feature selection. On the Cityscapes and CamVid datasets, LMDCNet achieves accuracies of 73.8 mIoU and 69.6 mIoU at 71.2 FPS and 92.4 FPS, respectively, without pre-training or post-processing. Our designed LMDCNet is trained and inferred only on one 1080Ti GPU. Our experiments show that LMDCNet achieves a good balance between segmentation accuracy and network parameters with only 1.05 M.

Image classification indicates that it classifies the images into a certain category according to the information in the image. Therefore, extracting image feature information is an important research content in image classification. Traditional image classification mainly uses machine learning methods to extract features. With the continuous development of deep learning, various deep learning algorithms are gradually applied to image classification. However, traditional deep learning-based image classification methods have low classification efficiency and long convergence time. The training networks are prone to over-fitting. In this paper, we present a novel CapsNet neural network based on the MobileNetV2 structure for robot image classification. Aiming at the problem that the lightweight network will sacrifice classification accuracy, the MobileNetV2 is taken as the base network architecture. CapsNet is improved by optimizing the dynamic routing algorithm to generate the feature graph. The attention module is introduced to increase the weight of the saliency feature graph learned by the convolutional layer to improve its classification accuracy. The parallel input of spatial information and channel information reduces the computation and complexity of network. Finally, the experiments are carried out in CIFAR-100 dataset. The results show that the proposed model is superior to other robot image classification models in terms of classification accuracy and robustness.

This article proposes a CBAM-ASPP-SqueezeNet model based on the attention mechanism and atrous spatial pyramid pooling (CBAM-ASPP) to solve the problem of robot multi-target grasping detection. Firstly, the paper establishes and expends a multi-target grasping dataset, as well as introduces and uses transfer learning to conduct network pre-training on the single-target dataset and slightly modify the model parameters using the multi-target dataset. Secondly, the SqueezeNet model is optimized and improved using the attention mechanism and atrous spatial pyramid pooling module. The paper introduces the attention mechanism network to weight the transmitted feature map in the channel and spatial dimensions. It uses a variety of parallel operations of atrous convolution with different atrous rates to increase the size of the receptive field and preserve features from different ranges. Finally, the CBAM-ASPP-SqueezeNet algorithm is verified using the self-constructed, multi-target capture dataset. When the paper introduces transfer learning, the various indicators converge after training 20 epochs. In the physical grabbing experiment conducted by Kinova and SIASUN Arm, a network grabbing success rate of 93% was achieved.

Abstract Although recently a series of deep‐learning based methods have promoted the performance of face super resolution (FSR), most of these methods cannot recover essential face attributes accurately, especially to super‐resolve a very low‐resolution (LR) face image (16×16 pixels) to its (8×) high‐resolution (HR) version. To address this issue, a novel alternating optimisation algorithm to estimate facial attributes and restore facial images in a single network is presented . Specifically, two convolutional neural modules (denoted as Restorer and Corrector) are constructed and these two modules are alternated repeatedly to form an end‐to‐end trainable network. The Restorer module reconstructs face images based on estimated facial attributes, while the Corrector module corrects the estimated attributes with the help of restored face image. Since Corrector can utilise information from previous estimated attributes and the FSR image, the estimated attributes are iteratively corrected and gradually approach the ground truth. Moreover, a new attribute transformation scheme is designed to introduce attribution information into Restorer, in which the facial attribute vectors as the control conditions can guide the face image restoration explicitly. By conducting extensive experiments on the well‐known CelebA dataset, it is demonstrated that the proposed method can provide superior FSR performance in both quantitative and qualitative measurements.

Blind face restoration (BFR) from severely degraded face images is important in face image processing and has attracted increasing attention due to its wide applications. However, due to the complex unknown degradations in real-world scenarios, existing priors-based methods tend to restore faces with unstable quality. In this article, we propose a multi-prior collaboration network (MPCNet) to seamlessly integrate the advantages of generative priors and face-specific geometry priors. Specifically, we pretrain a high-quality (HQ) face synthesis generative adversarial network (GAN) and a parsing mask prediction network, and then embed them into a U-shaped deep neural network (DNN) as decoder priors to guide face restoration, during which the generative priors can provide adequate details and the parsing map priors provide geometry and semantic information. Furthermore, we design adaptive priors feature fusion (APFF) blocks to incorporate the prior features from pretrained face synthesis GAN and face parsing network in an adaptive and progressive manner, making our MPCNet exhibits good generalization in a real-world application. Experiments demonstrate the superiority of our MPCNet in comparison to state-of-the-arts and also show its potential in handling real-world low-quality (LQ) images from several practical applications.

For visual tracking, key factors that affect the performance of trackers are related to whether it can effectively extract the appearance information and spatial information of a target. And most of state-of-the-art trackers either do not model the appearance information and spatial information separately or do not design special strategies to deal with the strong geometric deformation of the target. In this paper, we design an appearance information model and a spatial information model separately, and then combine them to obtain complementary benefits. Firstly, because the features from deeper layers of a convolutional neural network (CNN) can better describe the semantic information of a target while the spatial information becomes less, we adopt the features from the deepest layer as the appearance information model. Secondly, we focus on tracking the target with drastic geometric deformation through utilizing a projection transformation group (SL(3) group) to model the geometric transformation of the target, where SL(3) group can describe the geometric deformation more accurately. Furthermore, a standard discriminative correlation filter is used to develop the effect of convolutional features and is more efficient than other methods used for CNN. Extensive experiments results show that our tracker outperforms all the compared trackers.

Machine learning based bottom-up saliency detection (MLBU) methods are very popular recently. These MLBU methods firstly use prior knowledge to select some regions from the given image as training samples and label them. Based on training set, a saliency classifier is learned to classify salient object and background by applying machine learning algorithms in the given image. Nevertheless, training labels obtained by prior knowledge are not always accurate in some complex scenes, inaccurate training set is hard to make subsequent learning process succeed. To solve this problem, we propose an inaccurate supervised learning (ISL) based saliency detection framework, which assumes that training labels obtained by prior knowledge might be inaccurate and constructs three checking rules to remove mislabeled samples for more accurate training set construction. The refined training set is used to learn a saliency classifier which can better predict each image region. To obtain more accurate saliency inference, the proposed ISL process is introduced into a novel iterative feedback (IF) framework to generate better saliency result. Finally, we use smoothness operator to further smooth saliency result for performance improvement. Experimental results on three benchmark datasets demonstrate adequately the superiority of the proposed method.

For current learning-based single image deraining methods, deraining networks are usually designed based on a simplified linear additive rain model, which may not only cause unreal synthetic rainy images for both training and testing datasets, but also adversely affect the applicability and generality of corresponding networks. In this paper, we use the screen blend model of Photoshop as the nonlinear rainy image decomposition model. Based on this model, we design a novel channel attention U-DenseNet for rain detection and a residual dense block for rain removal. The detection sub-network not only adjusts channel-wise feature responses by our novel channel attention block to pay more attention to learn the rain map, but also combines the context information with the precise localization by the U-DenseNet to promote pixel-wise estimation accuracy. After rain detection, we use the nonlinear model to get a coarse rain-free image, and then introduce a deraining refinement subnetwork consisted of the residual dense block to obtain a fine rain-free image. For training our network, we apply the nonlinear rain model to synthesize a benchmark dataset called as RITD. It contains 3200 triplets of rainy images, rain maps, and clean background images. Our extensive quantitative and qualitative experimental results show that our method outperforms several state-of-the-art methods on both synthetic and real images.

The state-of-the-art trackers using deep learning technology have little special strategy to gain the bounding box well when the target suffers drastic geometric deformation. In this paper, we take full use of the convolutional neural network (CNN) features of the deepest layer to represent the semantic feature model, and affine transformation to be as the space information model. A tracking method based on geometrical transformation region CNN is proposed. Firstly, affine transformation is applied to predict possible locations of a target, and the candidate bounding boxes obtained by affine transformation sampling can locate the possible geometric regions of the target more effectively before extracting features from CNN. Furthermore, RoI pooling with different sizes and shapes are designed to describe the geometric deformation region of the target. Then, multi-tasks loss function including the affine transformation regression is designed to refine the affine bounding box. Finally, the affine transformation NMS (Non-maximum suppression) is used to ensure the tracking bounding box having the largest IoU value. Extensive experimental results show that the proposed algorithm performs favorably against the compared methods in the public benchmarks.

With the rapid development of the Internet of Things (IoT) and smart cities, more and more types of applications have been emerging. In fact, different applications have different features and different requirements on services. In order to satisfy users' Quality of Service (QoS) requirements, the application-awareness technique should be leveraged to distinguish different applications for providing the differentiated services. However, the traditional Internet only can obtain the local network view, which belongs to the offline awareness mode and cannot adapt to the dynamical network environment. At the right time, Software-Defined Networking (SDN) has been accepted as a new networking paradigm thanks to its network awareness on the global status information, which can greatly facilitate the online application-awareness. At present, three ways, i.e., port number, depth packet inspection and deep learning can be used for the application-awareness. To the best of our knowledge, the deep learning based application-awareness method is the most cutting-edge technique. In spite of this, the previous related schemes fail to effectively guarantee the correctness and stability. To this end, this paper proposes a Convolutional Neural Network (CNN) based deep learning mechanism to do the application-awareness, including three phases, i.e., traffic collection, data pre-processing and application-awareness. The SDN environment is implemented based on the MiniNet and the simulation experiments are made based on the TensorFlow. The experimental results show that the proposed application-awareness mechanism outperforms three benchmarks on recall ratio, precision ratio, F value and stability.

Image clustering is a complex procedure that is significantly affected by the choice of the image representation. Generally speaking, image representations are generated by using handcraft features or trained neural networks. When dealing with high dimension data, these two representation methods cause two problems: i) the representation ability of the manually designed features is limited; ii) the non-representative and meaningless feature of a trained deep network may hurt the clustering performance. To overcome these problems, we propose a new clustering method which efficiently builds an image representation and precisely discovers the cluster assignments. Our main tools are an unsupervised representation learning method based on Deep Mutual Information Maximization (DMIM) system, and a clustering method based on self-training algorithm. Specifically speaking, to extract the informative representation of image data, we derive the maximum mutual information theory and propose a system to learn the maximum mutual information between the input images and the latent representations. To discover the clusters and assign each image a clustering label, a self-training mechanism is applied to cluster the learned representations. The superiority and validity of our algorithm are verified in a series of real-world image clustering experiments.

Recently, single image super-resolution (SISR) has been widely applied in the field of remote sensing image processing and obtained remarkable performance. However, existing CNN-based remote sensing image super-resolution methods are unable to exploit shallow visual characteristics at global receptive fields, which results in the limited perceptual capability of these models. Furthermore, the low-resolution inputs and features contain abundant low-frequency information, which are weighed in channels and space equally, hence limiting the representational ability of CNNs. To solve these problems, we propose a non-locally up-down convolutional attention network (NLASR) for remote sensing image super-resolution. First, a non-local features enhancement module (NLEB) is constructed to obtain the spatial context information of high-dimensional feature maps, which allows our network to utilize global information to enhance low-level similar structured texture information with effect, overcoming the defects of deficiency perceptual ability of shallow convolutional layers. Second, an enhanced up-sampling channel-wise attention (EUCA) module and enhanced down-sampling spatial-wise attention (EDSA) module are proposed to weight the features at multiple scales. By integrating the channel-wise and multi-scale spatial information, the attention modules are able to compute the response values from the multi-scale regions of each neuron and then establish the accurate mapping from low to high resolution space. Extensive experiments on NWPU-RESISC45 and UCMerced-LandUse datasets show that the proposed method can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.

Low-dose CT (LDCT) images have been widely applied in the medical imaging field due to the potential risk of exposing patients to X-ray radiations. Given the fact that reducing the radiation dose may result in increased noise and artifacts, methods that can eliminate the noise and artifacts in the LDCT image have drawn increasing attentions and produced impressive results over the past decades. However, recent proposed methods mostly suffer from noise remaining, over-smoothing structures or false lesions derived from noise. In this paper, we propose a generative adversarial network (GAN) with novel architecture and loss function for restoring the LDCT image. Firstly, the inception-residual block and residual mapping are incorporated in the U-Net structure. The modified U-Net is applied as the generator of the GAN network so that the noise feature can be eliminated during the forward propagation. Secondly, a novel multi-level joint discriminator is designed by concatenating multiple convolutional neural networks (CNNs) where the output of each deconvolutional layer in the generator is compared with the corresponding down-sampled ground truth image. The adversarial training can be sensitive to noise and artifacts in different scales with this discriminator. Thirdly, we novely define a loss function consisting of the least square adversarial loss, VGG based perceptual loss, MSE based pixel loss and the noise loss, so that the differences in pixel, visual perception and noise distribution are comprehensively considered to optimize the network. Experimental results on both simulated and official simulated clinical images have demonstrated that the proposed method can provide superior performance to the state-of-the-art methods in noise removal, structure preservation and false lesions elimination.

For aquaculture resource evaluation and ecological environment monitoring, the automatic detection and identification of marine organisms is critical; however, due to the low quality of underwater images and the characteristics of underwater biological detection, the lack of abundant features can impede traditional hand-designed feature extraction approaches or CNN-based object detection algorithms, particularly in complex underwater environments. Therefore, the goal of this study was to perform object detection in underwater environments. This study developed a novel method for capturing feature information by adding the convolutional block attention module (CBAM) to the YOLOv5 backbone network. The interference of underwater organism characteristics in object characteristics decreased and the output object information of the backbone network was enhanced. In addition, a self-adaptive global histogram stretching algorithm (SAGHS) was designed to eliminate degradation problems, such as low contrast and color loss, that are caused by underwater environmental features in order to restore image quality. Extensive experiments and comprehensive evaluations using the URPC2021 benchmark dataset demonstrated the effectiveness and adaptivity of the proposed methods. Additionally, this study conducted an exhaustive analysis of the impacts of training data on performance.

With the development of computer vision, high quality images with rich information have great research potential in both daily life and scientific research. However, due to different lighting conditions, surrounding noise and other reasons, the image quality is different, which seriously affects people's discrimination of the information in the image, thus causing unnecessary conflicts and results. Especially in the dark, the images captured by the camera are difficult to identify, and the smart system relies heavily on high-quality input images. The image collected in low-light environment has the characteristic with high noise and color distortion, which makes it difficult to utilize the image and can not fully explore the rich value information of the image. In order to improve the quality of low-light image, this paper proposes a Heterogenous low-light image enhancement method based on DenseNet generative adversarial network. Firstly, the generative network of generative adversarial network is realized by using DenseNet framework. Secondly, the feature map from low light image to normal light image is learned by using the generative adversarial network. Thirdly, the enhancement of low-light image is realized. The experimental results show that, in terms of PSNR, SSIM, NIQE, UQI, NQE and PIQE indexes, compared with the state-of-the-art enhancement algorithms, the values are ideal, the proposed method can improve the image brightness more effectively and reduce the noise of enhanced image.

Sunshine-based trajectory analysis plays a significant impact on comprehensive scenarios, including driving safety and routing planning for mobile solar collection. To the best of our knowledge, however, a little work analyzes the impact of sunshine on mobile objects on different trajectories. This paper investigates the relationship between sunshine and the trajectories of mobile objects. We introduce a sunshine orientation model to integrate sunshine information with trajectories. A sunshine-based trajectory simplification model is proposed to remove redundant points in trajectories, which carry a little sunshine-related information. The sunshine-based trajectory simplification model is indeed versatile. We apply this model to help users efficiently query the sunshine information of their trips. Our design is evaluated with extensive simulations based on three-month general transit feed specification data from August to October in 2017 in five USA cities, including Washington, DC, USA, and Minneapolis. Furthermore, we develop a sunshine query system for mobile scenarios by embedding our sunshine-based trajectory simplification model and conduct a field study to show the validity and efficiency of this model. The evaluation results show that our design reduces 87.4% position points in trajectories while only sacrificing 9.6% of sunshine information in the field tests.

Trajectory analysis based on sunshine information shows that sunshine has a crucial effect on many conditions involving driving comfort and route planning. However, based on our best understanding, a little, if any, work takes into consideration the influence of sunshine on large numbers of trajectories of mobile objects such as vehicles. In this paper, we analyze, for the first time, the correlation between sunshine and large numbers of trajectories of mobile objects while presenting compression of the sunshine-based trajectories on a national scale. Within the research, a sunshine-oriented model is introduced to combine sunshine with real trajectories through the extraction of information centering around sunshine on arbitrary trajectories. Our trajectory analysis based on sunshine is versatile, and the model mentioned above is implemented to enhance the riding comfort of passengers. Our model is evaluated with an extensive simulation using general transit feed specification data over three months from August to October 2017 in five U.S. cities. We also conduct a field study in Minneapolis to show the validity and efficiency of our model. The evaluation results show that our design: 1) decreases trajectory computation by 88.7% with the trajectory compression and 2) achieves more than 90% accuracy for the trip sunshine information prediction in both the simulation and real-world tests.

Glaucoma is an eye disease which is one of the most common causes of blindness. Accurate optic disc (OD) and optic cup (OC) segmentation play a critical role for detecting glaucoma. Considering that the existing approaches can't effectively integrate the multi-view information deriving from shape and appearance to sufficiently describe OD and OC for segmentation, Locally Statistical Active Contour Model with the Information of Appearance and Shape (LSACM-AS) and Modified Locally Statistical Active Contour Model with the Information of Appearance and Shape (MLSACM-AS) are proposed in this paper. The main contributions are as below: (1) we introduce the Locally Statistical Active Contour Model (LSACM) to address the commonly occurred intensity inhomogeneity phenomenon caused by imperfection of image devices or illumination variations. (2) In order to overcome the common effects caused by pathological changes (i.e., peripapillary atrophy (PPA)) and vessel occlusion in OD and OC segmentation, we integrate the local image probability information around the point of interest from a multi-dimensional feature space into our model to preserve the integrity of the OD and OC structures. (3) Since the segmentation objects have the similar ellipse shape structure, we incorporate the shape priori constraint information into our model to further improve the robustness of the variations found in and around objects regions. To evaluate the effectiveness of the proposed models, an available publicly DRISHTI-GS database is employed in this paper. Seen from the abundant experiments, the proposed models outperform the state-of-the-art approaches in terms of the obtained qualitative and quantitative results.

Convolutional autoencoders are making a significant impact on computer vision and signal processing communities. In this work, a convolutional autoencoder denoising method is proposed to restore the corrupted laser stripe images of the depth sensor, which directly reduces the external noise of the depth sensor so as to increase its accuracy. To reduce the amount of training data and avoid overfitting, a patch size of the laser stripe image is determined, on the basis of which a small-scale dataset called Laser Stripe Image Patch (LSIP) is created. Also, a 14-layers convolutional autoencoder is constructed to reduce the noise of the image patches, which can learn the most salient features on the LSIP dataset. Moreover, the trained convolutional autoencoder is applied to an omnidirectional structured light system. Experimental results demonstrate that the proposed method obtains useful features and superior performance both visually and quantitatively on denoising tasks, and significantly improves the accuracy of the structured light system. Keywords: Convolutional autoencoder, Deep learning, Depth perception, Image denoising, Laser stripe, Structured light

Abstract Background Optimized dithering fringe pattern is a promising method for high-speed, high-accuracy three-dimensional shape measurement. The recently proposed dithering optimization technology optimizes the fringe quality in either phase domain or intensity domain according to their objective functions. Phase-based optimization is direct and effective, but it is sensitive to projector defocusing levels. Intensity-based optimization is robust to projector defocusing levels, but it does not fully improve the phase quality. In practice, it is difficult to control defocusing levels so it is still a challenge to get high quality fringe patterns which affects the measurement quality under different defocusing levels. Methods In order to get high-quality binary dithered patterns which are robust to defocusing levels, this paper proposes a weight object function. This function combines two parts: a global intensity part and a local structure part. The global intensity measurement is based on the normalized mean squared error. The local structure measurement is based on residual error of intensity. To generate high quality fringe patterns, the weight object function is applied to the best patch framework. Results and discussion Both simulation and experimental results demonstrate that the phase-based optimization method and the proposed method perform better than the intensity-based optimization method under nearly focused. However the quality of measurement results from phase-based optimization will decrease with the defoucsing levels increasing. The proposed method is robust to the defocusing levels and it can still reduce the phase error when the projector is strongly defocused. Conclusions The proposed method can get high-quality binary dithered patterns under different defocusing levels by combining global similarity and local residual error of intensity. It inherits the merits of binary fringe pattern so that gamma calibration of projector is not required. In practice, the proposed method can be used to generate high quality fringe patterns. The experiment results verify that the proposed method can get better measurement results without considering the projector defocusing levels.

Summary: Activin A levels are elevated during multiple severe infections and associated with an increased risk of death. However, the role of activin A in bacterial infection is still unclear. Here, we found that activin A levels were increased during S. aureus skin infection in mice. Administration of activin A increased the bacterial burden and promoted the spread of bacteria in vivo. Moreover, activin A inhibited neutrophil chemotaxis to N-formylmethionine-leucyl-phenylalanine via the type IIA activin receptor (ActRIIA) in vitro and impaired ActRIIA+ neutrophil recruitment to infection foci in vivo. Additionally, we identified a novel subpopulation of neutrophils, ActRIIA+ neutrophils, which exhibit superior phagocytic capacity compared to ActRIIA− neutrophils and possess an N2-like immunoregulatory activity via secreting IL-10 and TGF-β. Taken together, these findings indicate that activin A inhibits the recruitment of ActRIIA+ neutrophils to infected foci, leading to the impairment of bacterial clearance, and thus may hamper early infection control.

As the key technology for Internet of things, wireless sensor networks have received more attentions in recent years. Mobile localization is one of the significant topics in wireless sensor networks. In wireless sensor network, non-line-of-sight propagation is a common phenomenon leading to the growing non-line-of-sight error. It is a fatal impact for the localization accuracy of the mobile target. In this article, a novel method based on the nearest neighbor variable estimation is proposed to mitigate the non-line-of-sight error. First, the linear regression model of the extended Kalman filter is used to obtain the residual of the distance measurement value. After that, the residual analysis is used to complete the identification of the measurement value state. Then, by analyzing the statistical characteristics of the non-line-of-sight residual, the nearest neighbor variable estimation is proposed to estimate the probability density function of residual. Finally, the improved M-estimation is proposed to locate the mobile robot. Experiment results prove that the accuracy and robustness of the proposed algorithm are better than other methods in the mixed line-of-sight/non-line-of-sight environment. The proposed algorithm effectively inhibits the non-line-of-sight error.

Abstract Background In the fast 3D shape measurement, it is an important factor to use the least number of fringe patterns to get the wrapped phase and the wrapped phase is always required to be retrieved to absolute phase. But the process of phase unwrapping may affect the quality of absolute phase. Besides absolute phase retrieval is time-costing especially for high-speed 3D shape measurement. Methods This paper proposes a fast measurement method based on Fourier transform profilometry and stereo vision. Because of the property of stereo vision, every point can find its corresponding point in the wrapped phase. This method can reconstruct 3D surface without phase unwrapping. In order to further increase the measurement speed and overcome the gamma effect of projector, the dithering fringe pattern is used. To resist false matching, the original image matching constraint gives a rough parallax. Phase matching and sub-pixel parallax optimization are used to reduce the matching errors. In order to confirm the phase value of points which are at the edge of wrapped phase, average phase value is calculated. Results A white mask is measured based on the proposed method. The results from every step show the effect of different functions. To better show the effect of the proposed method, a white house is measured and the measurement is compared with LSSM and MFH. In order to further to show the advantage of the proposed method, discontinuous blocks and continuous blocks are measured. The average height, RMS, average error, maximum error are compared with the method which uses absolute phase to match the corresponding points. Experiment results verify the feasibility of the proposed method and it can measure complex objects with high speed and accuracy. Conclusion This paper uses Fourier transform and stereo vision to get wrapped phase and reconstruct 3D shape without phase unwrapping. The proposed method contains three part: phase matching, edge points detection and sub-pixel parallax optimization. By comparing matching precision, the proposed method can get high quality surface. Because the process of measurement only need one frame of deformed fringe pattern to get the wrapped phase and the matching process does not need phase unwrapping, the proposed method has the potential to be used in fast measurement.

Abstract Feature selection, which aims to select an optimal feature subset to avoid the “curse of dimensionality,” is an important research topic in many real-world applications. To select informative features from a high-dimensional dataset, we propose a novel unsupervised feature selection algorithm called Double Regularized Matrix Factorization Feature Selection (DRMFFS) in this paper. DRMFFS is based on the feature selection framework of matrix factorization, but extends this framework by introducing double regularizations (i.e., graph regularization and inner product regularization). There are three major contributions to our approach. First, for the sake of preserving the useful underlying geometric structure information of the feature space of the data, we introduce the graph regularization to guide the learning of the feature selection matrix, making it more effective. Second, in order to take into account the correlations among features, an inner product regularization term is imposed on the objective function of matrix factorization. Therefore, the selected features by DRMFFS cannot only represent the original high-dimensional data well but also contain low redundancy. Third, we design an efficient iteratively update algorithm to solve our approach and also prove its convergence. Experiments on six benchmark databases demonstrate that the proposed approach outperforms the state-of-the-art approaches in terms of both the classification and clustering performance.

Abstract Background The recently proposed optimized dithering techniques can improve measurement quality. However, the objective function in these optimization methods just qualifies the global similarity of the pattern while the global optimization methods ignore the influences of local structure. Method In order to get high quality binary dithered patterns, this paper presents an algorithm which combines optimization on global and local similarity and implements it in the whole-fringe optimization. Results Both the simulation and experimental results demonstrate that the proposed algorithm can achieve binary fringe patterns with higher phase quality and less intensity difference. The fringe patterns based on the proposed method can get high quality measurement results. Conclusion The proposed method can get high quality binary dithered patterns under different defocusing levels by combining global similarity and local structure similarity. The proposed method can improve the robustness to the amounts of defocusing.

With the increase of complexity of monitoring tasks in wireless sensor networks, using a single kind of sensor can no longer fit the strict monitoring requirements. Nowadays, event coverage is widely applied to detect events accurately by utilizing diverse kinds of sensors. The traditional 2-D event model cannot meet the actual monitoring requirements, and there will be many kinds of complicated constraints in the environment. Therefore, a compound event model with multiple constraints is put forward to 3-D sensor networks. Simultaneously, a compound event barrier coverage algorithm on the basis of non-preference bi-objective evolution (NPBO) strategy is presented in multiple constraints sensor networks. The proposed algorithm introduces a non-preference α-dominance mechanism to solve the low efficiency problem of multi-objective evolutionary under multiple constraints. A large number of experimental results indicate that the NPBO mechanism is more high-efficient than the latest algorithm in allocating sensor resources.

Following the development of autonomous underwater vehicles (AUVs), multiple trajectory-based submarine target information collection constitutes one of the key technologies that significantly influence underwater information collection ability and deployment efficiency. In this paper, we propose an underwater information collection AUV, O-AUV, that can perceive the omnidirectional area and could detect a larger area than the traditional AUV. A 3D sensing model for the O-AUV is proposed to describe the complex underwater information collection spaces. Thereafter, a cube-based environment model involving candidate observation point calculation methods are suggested to adapt the O-AUV model. A voyage cost map is also built according to the multi-AUV path planning for a common submarine mission that must traverse numerous mission targets in complex environments through the R-Dijkstra algorithm. Specifically, the voyage planning problem is solved through a critical algorithm called ANSGA (accelerated NSGA-II algorithm), which in turn, is developed by modifying the non-dominated sorting genetic algorithm (NSGA-II) to accelerate the optimization rate for the Pareto solution. Experiments are carried out in MATLAB, and the results verify the validity of the proposed O-AUV+ANSGA algorithm framework.

Abstract Background The accuracy of three-dimensional measurement of object surface is always affected by the nonlinear gamma of the projector. The defocusing binary projection can overcome the nonlinear gamma distortion of the projector and reduce the effect of high harmonics without gamma calibration. Although researches have already reduced the errors to get a clear sinusoidal curve, there still leave room for improvement, especially when wide stripes are applied during the measurement. Methods This paper presents a kind of ellipse binary pattern. By analyzing the property and spectrum, the binary pattern can produce high quality sinusoidal curve and produce smaller errors. It has a better effect to use an ellipse pattern to overcome the nonlinear gamma distortion of the projector and it is suit to be used as wide stripes. Results Simulation and comparison experiments plus three-step phase shifted method are conducted to verify feasibility and accuracy of this binary pattern. The experimental results have indicated that this binary pattern can increase the accuracy of 3D measurement and reduce phase errors caused by the nonlinear gamma of the projector. The defocusing ellipse pattern is superior to traditional methods. In addition, the defocusing binary stripe is robust and suit to measure object with large period. Conclusions In this paper, an binary ellipse pattern is proposed for high-accuracy 3D measurement profilometry. It is easy to generate high-quality sinusoidal fringe pattern. Experiment results have demonstrated the feasibility and accuracy of the improved binary pattern besides it proved that the period of fringe pattern has little impact on the accuracy of measurement.

Since microaneurysms (MAs) can be seen as the earliest lesions in diabetic retinopathy, its detection plays a critical role in the diabetic retinopathy diagnosis. In recent years, many machine-learning methods have been developed for MA detection. Generally, MA candidates are first identified and then a set of features for these candidates are extracted. Finally, machine-learning methods are applied for candidate classification. In this paper, we present a novel unsupervised classification method based on sparse posterior cerebral artery (PCA) for MA detection. Since it does not have to consider a non-MA training set, the class imbalance problem can be avoided. Furthermore, effective features can be selected due to the characteristic of sparse PCA, which combines the elastic net penalty with the PCA. Meanwhile, a single T2 statistic is introduced, and the control limit can be determined for distinguishing true MAs from spurious candidates automatically. Experiment results on the retinopathy online challenge competition database show the effectiveness of our proposed method.

Exudates can be regarded as one of the most prevalent clinical signs of diabetic retinopathy, and the detection of exudates has important clinical significance in diabetic retinopathy diagnosis. In this paper, a novel approach named superpixel multi-feature classification for the automatic detection of exudates is developed. First, an entire image is segmented into a series of superpixels considered as candidates. Then, a total of 20 features, including 19 multi-channel intensity features and a novel contextual feature, are proposed for characterizing each candidate. A supervised multi-variable classification algorithm is also introduced to distinguish the true exudates from the spurious candidates. Finally, a novel optic disc detection technique is designed to further improve the performance of classification accuracy. Extensive experiments are carried out on two publicly available online databases, DiaretDB1, and e-ophtha EX. Compared with other state-of-the-art approaches, the experimental results show the advantages and effectiveness of the proposed approach.

Inspired by the importance of self-representation and structure-preserving ability of features, in this paper, we propose a novel unsupervised feature selection algorithm named structure-preserving non-negative feature self-representation (SPNFSR). In this algorithm, each feature in high-dimensional data can be represented by the linear combination of other features. Then, to exploit the structure-preserving ability of features, we construct a low-rank representation graph, which takes the local and global structures into consideration to maintain the intrinsic structure of the data space. Finally, an l2,1-norm regularization and the non-negative constraint are imposed on the representation coefficient matrix with the goal of achieving feature selection in the batch mode. Moreover, we provide a simple yet efficient iterative update algorithm to solve SPNFSR, as well as the convergence analysis of the proposed algorithm. The performance of the proposed approach is illustrated by six publicly available databases. In comparison with the state-of-the-art approaches, the extensive experimental results show the advantages and effectiveness of our approach.

There are a variety of complex constraints in the wide application of wireless sensor networks. Traditional coverage models and algorithms have been unable to meet the needs of multi-constrained sensor networks. At the same time, in a complex monitoring environment, a single type of sensor information cannot meet the requirements of reliable monitoring. Hence, in this paper, aiming at the multi-constraints in sensor networks, a compound event barrier coverage algorithm is proposed based on environment Pareto-dominated selection strategy, which can distribute the sensor resources reasonably and find out the coverage ratio efficiently in multi-constraints sensor networks. The proposed algorithm takes advantage of Pareto domination relationship, constraint violation degree, constraint boundary distance, and crowding degree to preserve the outstanding infeasible individuals in the evolutionary process and participate in the mutation operation; we also adopt the adaptive scaling factor and crossover probability strategy to avoid the algorithm into local optimal. The proposed algorithm is proved to be more highly efficient than the latest algorithm in the distribution of sensor resources by experimental results.

In this paper, a novel depth acquisition algorithm aiming to obtain high resolution of dense depth maps based on lasers is proposed. Which expands the projection range and improves the robustness. In addition, dithering projection and defocusing techniques are used by lasers with the improvement of the Diffraction Optical Elements (DOE) technology. Four patterns are projected onto the projects by the lasers and captured by camera, where three for three-step phase-shifting (TS-PS) patterns and the other one is for space stripe pattern. More important, the calibrated by the traditional methods are unavailable in the proposed devices. We propose an algorithm for obtaining intrinsic and extrinsic parameters of the system. A substantially different spatial stripe coding scheme is designed, which is utilized to assist in time coding (TS-PS) solving depth information. We proposed a novel phase unwrapping method to obtain accurate absolute phase map. In addition, to further boost the performance, we utilized Weighted Least Squares (WLS) strategy to optimize the detail of the depth map based on color image. Thereby high resolution, detail and dense depth map obtained. Compared with the current methods, the robustness of our method is improved which will be extended to more scenes. The quantitative and qualitative evaluation experiments demonstrate that the proposed algorithm consistently produces better quality dense and higher resolution depth maps, superior to the current depth sensor. Keywords: Dithering defocusing techniques, Phase-shifting, Space stripe, WLS

Structured light (SL) has been extensively researched and developed due to reconstruction the fast and highly accurate depth sensing. In order to achieve this goal, many approaches have been taken. In this article, we have taken some innovative work in the field for building a new type of fast, high-precision depth perception based on structured light. In addition, the basic ideas we propose are as follows: our model for slow motion dynamic scenes, the sparse depth maps are obtained based on the pair of unstructured rigid pattern with different color, and the high-quality depth images are optimized by the ridge line extraction. Finally, the calculated two depth maps based on the different color pattern merged, which to acquire the optimization depth. We further propose a model for the high-speed motion dynamic scene which apply a pair of projectors structure light. We show that, we actively use motion blur to estimate depth which is different from the previous approaches. The patterns are illuminated from two projectors and the motion blur of each line is accurately measured. The scene depth information is estimated by analyzing the length of the blur. As a result, we describe two experiments that we conducted on two different experimental equipment (ball and planner board). The first experiment was conducted with the planer board, measuring the slow moving object. In addition, the second experiment scene was conducted with the ball, which obtained the depth of the ultra-fast object. Our experimental results demonstrate that our approach achieves effective real-time measurement, can successfully obtain accurate depth information of moving objects. Keywords: Structured light, Dynamic scene, Ridge detection, Light flow, Unstructured grid

In this research, the authors have addressed the collaboration calibration and real-time three-dimensional (3D) localization problem in the multi-view system. The 3D localization method is proposed to fuse the two-dimensional image coordinates from multi-views and provide the 3D space location in real time. It is a fundamental solution to obtain the 3D location of the moving object in the research field of computer vision. Improved common perpendicular centroid algorithm is presented to reduce the side effect of the shadow detection and improve localization accuracy. The collaboration calibration is used to generate the intrinsic and extrinsic parameters of multi-view cameras synchronously. The experimental results show that the algorithm can complete accurate positioning in indoor multi-view monitoring and reduce the complexity.

Lung cancer has one of the highest cancer mortality rates in the world and threatens people’s health. Timely and accurate diagnosis can greatly reduce the number of deaths. Therefore, an accurate diagnosis system is extremely important. The existing methods have achieved significant performances on lung cancer diagnosis, but they are insufficient in fine-grained representations. In this paper, we propose a novel attentive method to differentiate malignant and benign pulmonary nodules. Firstly, the residual attention network (RAN) and squeeze-and-excitation network (SEN) were utilized to extract spatial and contextual features. Secondly, a novel multi-scale attention network (MSAN) was proposed to capture multi-scale attention features automatically, and the MSAN integrated the advantages of the spatial attention mechanism and contextual attention mechanism, which are very important for capturing the salient features of nodules. Finally, the gradient boosting machine (GBM) algorithm was used to differentiate malignant and benign nodules. We conducted a series of experiments on the Lung Image Database Consortium image collection (LIDC-IDRI) database, achieving an accuracy of 91.9%, a sensitivity of 91.3%, a false positive rate of 8.0%, and an F1-score of 91.0%. The experimental results demonstrate that our proposed method outperforms the state-of-the-art methods with respect to accuracy, false positive rate, and F1-Score.

It is important for underwater wireless sensor networks (UWSNs) to satisfy the diverse monitoring demands in harsh and perilous three-dimensional underwater environments. After the monitoring missions and demands transform, a large number of underwater event coverage holes will appear. Traditional network repair strategies cannot be applied to the ever-changing underwater monitoring missions and the harsh multi-constrained three-dimensional underwater environments. Multiple autonomous underwater vehicles (multi-AUVs) have strong adaptability and flexibility in perilous and harsh three-dimensional underwater environments. First, an underwater event coverage hole (UECH) repair model under various constraints is proposed. Next, a multi-agent event coverage hole repair algorithm (MECHR), which combines multi-agent strategy with diversity archive strategy, is proposed to repair UECHs in UWSNs. The presented algorithm symmetrically completes subtasks through information exchange and interactive operations with other agents. Unlike existing repair strategies, the MECHR algorithm can effectively repair a large number of UECHs resulted by the transformations in underwater monitoring scenes and demands. The MECHR algorithm can adapt to a wide range of harsh scenes and multi-constrained three-dimensional underwater environments. Eventually, the effect of the MECHR algorithm is verified through underwater repair simulation experiments, which can adapt to the constantly changing three-dimensional underwater monitoring environments.

Region covariance descriptor that fuses multiple features compactly has proven to be very effective for visual tracking. While working effectively, the exhaustive global search strategy of covariance tracking is still inefficient, and there is much room for improvement. It may cause inconsecutive tracking trajectory and distraction. A suitable region similarity metric for covariance matching between the candidate object region and a given appearance template is of much importance. However, the computational burden of the metric, especially for large matrices under Riemannian space, may hinder its application in gradient‐based algorithms. In this study, the authors propose an algorithm which, by minimising the metric function, exploits an efficient conjugate gradient method to iteratively search the best matched candidate, and determines the search step size by non‐monotonic liner strategy. Then, an inferential reasoning in view of new efficient metric is derived for the gradient‐based algorithm. The authors test the proposed tracking method on test baseline dataset. Both quantitative and qualitative results demonstrate the effectiveness of the proposed algorithm compared with other state‐of‐the‐art methods.

Indoor localization is a significant research area in wireless sensor networks (WSNs). Generally, the nodes of WSNs are deployed in the same plane, i.e., the floor, as the target to be positioned, which causes the sensing signal to be influenced or even blocked by unpredictable obstacles, like furniture. However, a 3D system, like Cricket, can reduce the negative impact of obstacles to the maximum extent and guarantee the sensing signal transmission by using the line of sight (LOS). However, most of the traditional localization methods are not available for the new deployment mode. In this paper, we propose the self-localization of beacons method based on the Cayley–Menger determinant, which can determine the positions of beacons stuck in the ceiling; and differential sensitivity analysis (DSA) is also applied to eliminate measurement errors in measurement data fusion. Then, the calibration of beacons scheme is proposed to further refine the locations of beacons by the mobile robot. According to the robot’s motion model based on dead reckoning, which is the process of determining one’s current position, we employ the H ∞ filter and the strong tracking filter (STF) to calibrate the rough locations, respectively. Lastly, the optimal node selection scheme based on geometric dilution precision (GDOP) is presented here, which is able to pick the group of beacons with the minimum GDOP from all of the beacons. Then, we propose the GDOP-based weighting estimation method (GWEM) to associate redundant information with the position of the target. To verify the proposed methods in the paper, we design and conduct a simulation and an experiment in an indoor setting. Compared to EKF and the H ∞ filter, the adopted STF method can more effectively calibrate the locations of beacons; GWEM can provide centimeter-level precision in 3D environments by using the combination of beacons that minimizes GDOP.

The traffic block port monitors and manages the road traffic by shooting and recording the motor vehicles. However, due to the complex factors such as shooting angle, light condition, environmental background, etc., the recognition rate of license plate is not high enough. High light and low light under complex lighting conditions are symmetry problems. This paper analyzes and solves the low light problem in detail, an image adaptive enhancement algorithm under low light conditions is proposed in the paper. The algorithm mainly includes four modules, among which, the fast image classification module uses the deep and separable convolutional neural network to classify low-light images into low-light images by day and low-light images by night, greatly reducing the computation burden on the basis of ensuring the classification accuracy. The image enhancement module inputs the classified images into two different image enhancement algorithms and adopts the idea of dividing and ruling; the image quality evaluation module adopts a weighted comprehensive evaluation index. The final experiment shows that the comprehensive evaluation indexes are all greater than 0.83, which can improve the subsequent recognition of vehicle face and license plate.

Pulmonary nodule detection in chest computed tomography (CT) is of great significance for the early diagnosis of lung cancer. Therefore, it has attracted more and more researchers to propose various computer-assisted pulmonary nodule detection methods. However, these methods still could not provide convincing results because the nodules are easily confused with calcifications, vessels, or other benign lumps. In this paper, we propose a novel deep convolutional neural network (DCNN) framework for detecting pulmonary nodules in the chest CT image. The framework consists of three cascaded networks: First, a U-net network integrating inception structure and dense skip connection is proposed to segment the region of lung parenchyma from the chest CT image. The inception structure is used to replace the first convolution layer for better feature extraction with respect to multiple receptive fields, while the dense skip connection could reuse these features and transfer them through the network. Secondly, a modified U-net network where all the convolution layers are replaced by dilated convolution is proposed to detect the “suspicious nodules” in the image. The dilated convolution can increase the receptive fields to improve the ability of the network in learning global information of the image. Thirdly, a modified U-net adapting multi-scale pooling and multi-resolution convolution connection is proposed to find the true pulmonary nodule in the image with multiple candidate regions. During the detection, the result of the former step is used as the input of the latter step to follow the “coarse-to-fine” detection process. Moreover, the focal loss, perceptual loss and dice loss were used together to replace the cross-entropy loss to solve the problem of imbalance distribution of positive and negative samples. We apply our method on two public datasets to evaluate its ability in pulmonary nodule detection. Experimental results illustrate that the proposed method outperform the state-of-the-art methods with respect to accuracy, sensitivity and specificity.

Wireless sensor and robot networks (WSRNs) often work in complex and dangerous environments that are subject to many constraints. For obtaining a better monitoring performance, it is necessary to deploy different types of sensors for various complex environments and constraints. The traditional event-driven deployment algorithm is only applicable to a single type of monitoring scenario, so cannot effectively adapt to different types of monitoring scenarios at the same time. In this paper, a multi-constrained event-driven deployment model is proposed based on the maximum entropy function, which transforms the complex event-driven deployment problem into two continuously differentiable single-objective sub-problems. Then, a collaborative neural network (CONN) event-driven deployment algorithm is proposed based on neural network methods. The CONN event-driven deployment algorithm effectively solves the problem that it is difficult to obtain a large amount of sensor data and environmental information in a complex and dangerous monitoring environment. Unlike traditional deployment methods, the CONN algorithm can adaptively provide an optimal deployment solution for a variety of complex monitoring environments. This greatly reduces the time and cost involved in adapting to different monitoring environments. Finally, a large number of experiments verify the performance of the CONN algorithm, which can be adapted to a variety of complex application scenarios.

In the application of the wireless sensor and robot networks (WSRNs), there is an urgent need to accommodate flexible surveillance tasks in intricate surveillance scenarios. On the condition of flexible surveillance missions and demands, event coverage holes occur in the networks. The conventional network repair methods based on the geometric graph theory such as Voronoi diagram method are unable to meet the conditions of flexible surveillance tasks and severe multi-restraint scenarios. Mobile robots show obvious advantages in terms of adaptation capacity and mobility in hazardous and severe scenarios. First, we propose an event coverage hole healing model for multi-constrained scenarios. Then, we propose a joint event coverage hole repair algorithm (JECHR) on the basis of global repair and local repair to apply mobile robots to heal event coverage holes in WSRNs. Different from conventional healing methods, the proposed algorithm can heal event coverage holes efficaciously which are resulted from changing surveillance demands and scenarios. The JECHR algorithm can provide an optimal repair method, which is able to adapt different kinds of severe multi-constrained circumstances. Finally, a large number of repair simulation experiments verify the performance of the JECHR algorithm which can be adapted to a variety of intricate surveillance tasks and application scenarios.