Search

Zhang neural network (ZNN), a special recurrent neural network, has recently been established as an effective alternative for time-varying linear equations with inequality constraints (TLEIC) solving. Still, the convergent time produced by the ZNN model always tends to infinity. In contrast to ZNN, a finite-time convergent neural network (FCNN) is proposed for the TLEIC problem. By introducing a non-negative slack variable, the initial form of the TLEIC has been transformed into a system of time-varying linear equation. Afterwards, the stability and finite-time performance of the FCNN model is substantiated by the theoretical analysis. Then, simulation results further verify the effectiveness and superiority of the proposed FCNN model as compared with the ZNN model for solving TLEIC problem. Finally, the proposed FCNN model is successfully applied to the trajectory planning of redundant manipulators with joint limitations, thereby illustrating the applicability of the new neural network model.

This article proposes a three-stream self-attention network (TSNet) for indoor semantic segmentation comprising two asymmetric input streams (asymmetric encoder structure) and a cross-modal distillation stream with a self-attention module. The two asymmetric input streams are ResNet34 for the red-green-blue (RGB) stream and VGGNet16 for the depth stream. Accompanying the RGB and depth streams, a cross-modal distillation stream with a self-attention module extracts new RGB plus depth features in each level in the bottom-up path. In addition, while using bilinear upsampling to recover the spatial resolution of the feature map, we incorporated the feature information of both the RGB flow and the depth flow through the self-attention module. We constructed the NYU Depth V2 dataset to evaluate the TSNet and achieved results comparable to those of current state-of-the-art methods.

Many RGB-D visual attention models have been proposed with diverse fusion models; thus, the main challenge lies in the differences in the results between the different models. To address this challenge, we propose a local-global fusion model for fixation prediction on an RGB-D image; this method combines global and local information through a content-aware fusion module (CAFM) structure. First, it comprises a channel-based upsampling block for exploiting global contextual information and scaling up this information to the same resolution as the input. Second, our Deconv block contains a contrast feature module to utilize multilevel local features stage-by-stage for superior local feature representation. The experimental results demonstrate that the proposed model exhibits competitive performance on two databases.

Exploiting RGB and depth information can boost the performance of semantic segmentation. However, owing to the differences between RGB images and the corresponding depth maps, such multimodal information should be effectively used and combined. Most existing methods use the same fusion strategy to explore multilevel complementary information at various levels, likely ignoring different feature contributions at various levels for segmentation. To address this problem, we propose a network using a two-stage cascaded decoder (TCD), embedding a detail polishing module, to effectively integrate high- and low-level features and suppress noise from low-level details. Additionally, we introduce a depth filter and fusion module to extract informative regions from depth cues with the guidance of RGB images. The proposed TCD network achieves comparable performance to state-of-the-art RGB-D semantic segmentation methods on the benchmark NYUDv2 and SUN RGB-D datasets.

The use of RGB-D information for salient object detection (SOD) is being increasingly explored. Traditional multilevel models handle both low- and high-level features similarly, as they use the same number of features for blending. Unlike these models, in this paper, we propose multilevel reverse-context interactive-fusion (MRI) network (MRINet) for RGB-D SOD. Specifically, first, we extract and reuse different numbers of features depending on their level; the deeper the information, the more times do we perform the extraction. Deeper information contains more semantic cues, which are important for locating salient regions. Thereafter, we use an RGB MRI block (MRIB) to merge RGB information at different levels; furthermore, we use depth features as auxiliary information and an RGB-D MRIB for full merging with RGB information. RGB and RGB-D MRIBs can reconstruct the high-level feature map in high resolution and integrate the low-level feature map to enhance boundary details. Extensive experiments demonstrate the effectiveness of the proposed MRINet and its state-of-the-art performance in RGB-D SOD.

In recent years, the detection of distinctive objects in stereoscopic 3D images has drawn increasing attention. Unlike 2D salient object detection, salient object detection in stereoscopic 3D images is highly challenging. Hence, we propose a novel Deep Convolutional Residual Autoencoder (DCRA) for end-to-end salient object detection in stereoscopic 3D images. The core trainable architecture of the salient object detection model employs raw stereoscopic 3D images as the inputs and their corresponding ground truth saliency masks as the labels. A convolutional residual module is applied to both the encoder and the decoder as a basic building block in the DCRA, and long-range skip connections are employed to bypass the equal-sized feature maps between the encoder and the decoder. To explore the complex relationships and exploit the complementarity between RGB (photometric) and depth (geometric) information, multiple feature map fusion modules are constructed. These modules integrate texture and structure information between the RGB and depth branches of the encoder and fuse their features over several multiscale layers. Finally, to efficiently optimize DCRA parameters, a supervision pyramid based on boundary loss and background prior loss is adopted, which employs supervised learning over the multiscale layers in the decoder to prevent vanishing gradients and accelerate the training at the fusion stage. We compare the proposed DCRA with state-of-the-art methods on two challenging benchmark datasets. The results of these experiments demonstrate that our proposed DCRA performs favorably against the comparison models.

Most RGB-D salient object detection (SOD) models use the same network to process RGB images and their corresponding depth maps. Subsequently, these models perform direct concatenation and summation at deep or shallow layers. However, these models ignore the complementarity of multi-level features extracted from RGB images and depth maps. This paper presents an asymmetric deeply fused network (ADFNet) for RGB-D SOD. Two different backbone networks, i.e., ResNet-50 and VGG-16, are utilized to process RGB images and related depth maps. We use an aggregation decoder and adaptive attention transformer module (AATM) to avoid information loss in the decoding process. Additionally, we use an attention early fusion module (AEFM) and deep fusion module (DFM) to deal with the deep features in various complex situations. Experiments validate the effectiveness of the proposed ADFNet, which outperforms thirteen recent RGB-D SOD models in the analysis of five public RGB-D SOD datasets.

Blind binocular visual quality prediction (BVQP) is more challenging than blind monocular visual quality prediction (MVQP). Recently, the application of convolutional neural networks (CNNs) to blind MVQP has resulted in significant progress in that area. In contrast, the adoption of deep learning for blind BVQP has received scant attention. In this study, we devised an end-to-end deep fusion network (DFNet) model trained in a unified framework for blind BVQP. This core prediction engine comprises monocular feature encoding networks and binocular feature fusion networks, followed by a quality prediction layer. The monocular feature encoding networks are first established to capture the low- and high-level monocular features of the left and right retinal views, respectively. Subsequently, these monocular features are integrated by the binocular feature fusion networks to obtain binocular deep features. Finally, the final binocular visual quality is predicted by quality prediction networks. Comparisons via experiments using two standard subject-rated BVQP datasets indicate that the proposed DFNet architecture achieves highly consistent alignment with human assessment and outperforms most relevant existing models.

Semantic segmentation is a fundamental task in computer vision, and it has various applications in fields such as robotic sensing, video surveillance, and autonomous driving. A major research topic in urban road semantic segmentation is the proper integration and use of cross-modal information for fusion. Here, we attempt to leverage inherent multimodal information and acquire graded features to develop a novel multilabel-learning network for RGB-thermal urban scene semantic segmentation. Specifically, we propose a strategy for graded-feature extraction to split multilevel features into junior, intermediate, and senior levels. Then, we integrate RGB and thermal modalities with two distinct fusion modules, namely a shallow feature fusion module and deep feature fusion module for junior and senior features. Finally, we use multilabel supervision to optimize the network in terms of semantic, binary, and boundary characteristics. Experimental results confirm that the proposed architecture, the graded-feature multilabel-learning network, outperforms state-of-the-art methods for urban scene semantic segmentation, and it can be generalized to depth data.

The current study investigates the association of board characteristics with firms’ environmental performance to provide further research and policy implications by carrying out systematic bibliometric analysis. The most potent contribution of the current study was to evaluate the performance of authors, geographical regions, journals and academic institutions to document their impact on the development of current literature. Moreover, the current study has used analytical statistics to examine how current research themes have evolved, and how impediments in existing literature can be overcome. Our analysis allows us to conclude that there is a lack of research collaboration between researchers and institutions in developing and developed countries. Finally, we summarize that the economic literature focuses more on BOD diversity, and there is less focus on theoretical development; non-listed firms, geographical proximity and mediating variables are research areas that need further academic attention. We conclude the current research investigation by identifying new research avenues.

A novel exponential varying-parameter neural network (EVPNN) is presented and investigated to solve the inverse redundancy scheme of the mobile manipulators via quadratic programming (QP). To suspend the phenomenon of drifting free joints and guarantee high convergent precision of the end effector, the EVPNN model is applied to trajectory planning of mobile manipulators. Firstly, the repetitive motion scheme for mobile manipulators is formulated into a QP index. Secondly, the QP index is transformed into a time-varying matrix equation. Finally, the proposed EVPNN method is used to solve the QP index via the matrix equation. Theoretical analysis and simulations illustrate that the EVPNN solver has an exponential convergent speed and strong robustness in mobile manipulator applications. Comparative simulation results demonstrate that the EVPNN possesses a superior convergent rate and accuracy than the traditional ZNN solver in repetitive trajectory planning with a mobile manipulator.

This paper tackles a recent challenge in patrol image processing on how to improve the identification accuracy for power component, especially for the scenarios including many interference objects. Our proposed method can fully use the patrol image information from live work, and it is thus different from traditional power component identification methods. Firstly, we use long short-term memory networks to synthesize the context information in a convolutional neural network. Then, we constructed the Mask LSTM-CNN model by combining the existing Mask R-CNN method and the context information. Further, by extracting the specific features belonging to the power components, we design an optimization algorithm to optimize the parameters of Mask LSTM-CNN model. Our solution is competitive in the sense that the power component is still identified accurately even if the patrol images contain much interference information. Extensive experiments show that the proposed scheme can improve the accuracy of component recognition and has an excellent anti-interference ability. Comparing with the existing R-FCN model and Faster R-CNN model, the proposed method demonstrates a significantly superior detection performance, and the average recognition accuracy is improved from 8 to 11%.

Human eye-fixation prediction in 3D images is important for many 3D applications, such as fine-grained 3D video object segmentation and intelligent bulletproof curtains. While the vast majority of existing 2D-based approaches cannot be applied, the main challenge lies in the inconsistency, or even conflict, between the RGB and depth saliency maps. In this paper, we propose a three-stream architecture to accurately predict human visual attention on 3D images end-to-end. First, a two-stream feature extraction network based on advanced convolutional neural networks is trained for RGB and depth, and hierarchical information is extracted from each ResNet-18. Then, these multi-level features are fed into the channel attention mechanism to suppress the feature space inconsistency and make the network focus on a significant target. The enhanced saliency map is fused step-by-step by VGG-16 to generate the final coarse saliency map. Finally, each coarse map is refined empirically through refinement blocks, and the network's own identification errors are corrected based on the acquired knowledge, thus converting the prediction saliency map from coarse to fine. The results of comparison of our model with six other state-of-the-art approaches on the NUS dataset (CC of 0.5579, KLDiv of 1.0903, AUC of 0.8339, and NSS of 2.3373) and the NCTU dataset (CC of 0.8614, KLDiv of 0.2681, AUC of 0.9143, and NSS of 2.3795) indicate that the proposed model consistently outperforms them by a considerable margin as it fully employs the channel attention mechanism.

Batch steganography refers to a steganography method where a user tries to hide confidential payload within a batch of images from social networks. It is significantly different from the traditional laboratory steganography where a user only considers an individual image. To apply batch steganography in social media networks, we are faced with two nontrivial problems: 1) how to assign payload to multiple images? and 2) how to recover the hidden payload if some images are lost during transmission? We tackle the problems by: 1) developing an optimal payload embedding strategy and 2) designing a special type of data decomposition. In the former, an optimal non-uniform payload distribution for multiple images is obtained by iterative feature back replacement. In the later, we employ special matrix operation to expand original data and split them into multiple shares. These shares are then embedded into different covers following the optimal non-uniform payload distribution. Our solution is robust in the sense that the recipient can recover the hidden data even if some images are intercepted or lost during delivery. Comprehensive experimental results show that our method outperforms the state-of-the-art in terms of anti-detectability and robustness.

Person re-identification is critical for human tracking in the video surveillance which has attracted more and more attention in recent years. Various recent approaches have made great progress in re-identification performance using metric learning techniques and among them, Keep It Simple and Straightforward (KISS) metric learning method has shown remarkably importance because of its simpleness and high-efficiency. The KISS method is based on an assumption that the differences between feature pairs obey the Gaussian distribution. However, for most existing features of person re-identification, the distributions of differences between feature pairs are irregular and undulant. Therefore, prior to the Guassian based metric learning step, it's important to augment the Guassian distribution of data without losing discernment. Moreover, most metric learning methods were greatly influenced by the small sample size (SSS) problem and the KISS method is no exception, which causing the inexistence of inverse of covariance matrices. To solve the above two problems, we present Kernelized Random KISS (KRKISS) metric learning method. By transforming the original features into kernelized features, the differences between feature pairs can better fit the Gaussian distribution and thus they can be more suitable for the Guassian assumption based models. To solve the inverse of covariance matrix estimation problem, we apply a random subspace ensemble method to obtain exact estimation of covariance matrix by randomly selecting and combining several different subspaces. In each subspace, the influence of SSS problem can be minimized. Experimental results on three challenging person re-identification datasets demonstrate that the KRKISS method significantly improves the KISS method and achieves better performance than most existing metric learning approaches.

This paper tackles a new challenge in power big data: how to improve the precision of short-term load forecasting with large-scale data set. The proposed load forecasting method is based on Spark platform and “clustering–regression” model, which is implemented by Apache Spark machine learning library (MLlib). Proposed scheme firstly clustering the users with different electrical attributes and then obtains the “load characteristic curve of each cluster”, which represents the features of various types of users and is considered as the properties of a regional total load. Furthermore, the “clustering–regression” model is used to forecast the power load of the certain region. Extensive experiments show that the proposed scheme can predict reasonably the short-term power load and has excellent robustness. Comparing with the single-alone model, the proposed method has a higher efficiency in dealing with large-scale data set and can be effectively applied to the power load forecasting.

This work proposes an improvement solution in identifying malicious user (or steganographer) who try to deliver hidden information in a batch of natural images. In this solution, a sampling construction strategy is proposed firstly. We design a probability calculation model by analying the principle of adaptive steganography, and then select DCT blocks with higher embedding probability to reconstruct a sample image, which is considered as the proof of extracting steganalysis features. Furthermore, inspired by the classical PEV-193 feature space, we reform a reduced PEV feature set including histogram features and intra-block co-occurrence features, which can capture more steganographic changes and match the sampling construction strategy well. Comprehensive experimental results show that comparing with the state-of-the-arts, the proposed scheme has a significant improvement in identifying potential steganographers in large-scale social media networks, and therefore is believed to be able to resist adaptive steganography with small payload.

This work proposes a new unsupervised steganalysis scheme which mainly tackles the challenge in identifying individual JPEG image as stego or cover. The proposed scheme does not need a large number of samples to train classification model, and thus it is significantly different from the existing supervised steganalysis schemes. The proposed scheme employs calibration technology to construct multiple reference images from one suspicious image. These reference images are considered as the imitation of cover. Furthermore, randomized sampling is performed to construct sub-image sets from suspicious image and reference images, respectively. By calculating the maximum mean discrepancy between any two sub-image sets, an efficient measure is provided to give the optimal decision on this suspicious image. Experimental results show that the proposed scheme is effective and efficient in identifying individual image, and outperforms the state-of-the-art steganalysis scheme.

In a typical smart grid, a large number of smart meters are deployed at energy consumers premises, which can report real-time usage data to the control center of the energy producer. Although such a communication model can help to improve the efficiency and reliability of electricity delivery, which is crucial to our society, it also leads to several security issues: (1) attackers may violate the privacy of energy consumers, and (2) attackers may tamper with the transmitted data for their own benefits or purposes. To deal with these security issues, many researchers have proposed different schemes for privacy preservation or abnormal data detection. However, existing studies usually address them separately. In this paper, we jointly resolve these two major security issues in the smart grid. Specifically, we propose a privacy-aware data dissemination scheme for smart grid with abnormal data traceability (PDDS), based on bilinear group theory and non-interactive zero-knowledge proof. In our scheme, we design a novel link function that can verify whether there are different signatures that are signed by the same consumer, which effectively reduces the time and communication overhead for tracing. To evaluate the correctness and performance of the proposed scheme, we first develop a solid security analysis, which shows that the proposed scheme can efficiently preserve identity confidentiality and data integrity. We then conduct extensive simulation experiments, which further demonstrate that our scheme can significantly reduce communication costs.

Recent developments in convolutional neural networks (CNNs) have significantly improved the results of salient object detection (SOD), particularly RGB-D SOD. This article proposes BPA-Net (Boundary-aware Pyramid Attention Network), a network that addresses two key issues in RGB-D SOD based on CNNs: 1) accurately locking the position of an object when it is unclear whether it is a multi-object or a single object, and 2) depicting fine edges and fill pixels while maintaining robustness with complex scenes and similarly-colored backgrounds. Accordingly, we model three network branches to solve these problems separately. To address the first problem, we devise the Multi-scale Attention Branch, a pyramid attention network that collects the positions of objects, thereby eliminating interference from non-objects. The second is addressed via a Boundary Refine Branch that uses a depth image to capture the edges of objects. This step refines the boundaries of objects and emphasizes the importance of salient edge information. Such branches are learned for obtaining precise salient boundaries and for position estimation and are subsequently combined with a coarse salient map generated by the Coarse Salient Detection Branch, an encode-decode SOD network, to improve salient object segmentation. Extensive experiments show that our BPA-Net outperforms state-of-the-art approaches on two popular benchmarks.

Stereoscopic 3D (S3D) visual quality prediction (VQP) is used to predict human perception of visual quality for S3D images accurately and automatically. Unlike that of 2D VQP, the quality prediction of S3D images is more difficult owing to complex binocular vision mechanisms. In this study, inspired by the binocular fusion and competition of the binocular visual system (BVS), we designed a blind deep visual quality predictor for S3D images. The proposed predictor is a multi-layer fusion network that fuses different levels of features. The left- and right-view sub-networks use the same structure and parameters. The weights and qualities for the left- and right-view patches of S3D images can be predicted. Furthermore, training patches with more saliency information can improve the accuracy of prediction results, which also make the predictor more robust. The LIVE 3D Phase I and II datasets were used to evaluate the proposed predictor. The results demonstrate that the performance of the proposed predictor surpasses most existing predictors on both asymmetrically and symmetrically distorted S3D images.

Saliency prediction on RGB-D images is an underexplored and challenging task in computer vision. We propose a channel-wise attention and contextual interaction asymmetric network for RGB-D saliency prediction. In the proposed network, a common feature extractor provides cross-modal complementarity between the RGB image and corresponding depth map. In addition, we introduce a four-stream feature-interaction module that fully leverages multiscale and cross-modal features for extracting contextual information. Moreover, we propose a channel-wise attention module to highlight the feature representation of salient regions. Finally, we refine coarse maps through a corresponding refinement block. Experimental results show that the proposed network achieves a performance comparable with state-of-the-art saliency prediction methods on two representative datasets.

RGB-D data are increasingly being used for myriad computer vision tasks. For such tasks, most methods simply concatenate or add feature vectors from RGB images and depth maps and allow the two modalities to complement each other mutually. However, such a fusion strategy results in inefficient and inadequate performance. In this study, we propose deep binocular fixation prediction based on a hierarchical multimodal fusion network that suitably combines RGB and depth maps. In the proposed method, a novel convolutional block attention module completely extracts image texture features and retains spatial information. In addition, a pyramid dilated-convolution module refines feature information, further improving the fusion of RGB and depth maps. Experimental results indicate that the proposed network achieves state-of-the-art performance on the NUS and NCTU datasets.

Red–green–blue and depth (RGB-D) saliency detection has recently attracted much research attention; however, the effective use of depth information remains challenging. This paper proposes a method that leverages depth information in clear shapes to detect the boundary of salient objects. As context plays an important role in saliency detection, the method incorporates a proposed end-to-end multiscale multilevel context and multimodal fusion network (MCMFNet) to aggregate multiscale multilevel context feature maps for accurate saliency detection from objects of varying sizes. Finally, a coarse-to-fine approach is applied to an attention module retrieving multilevel and multimodal feature maps to produce the final saliency map. A comprehensive loss function is also incorporated in MCMFNet to optimize the network parameters. Extensive experiments demonstrate the effectiveness of the proposed method and its substantial improvement over state-of-the-art methods for RGB-D salient object detection on four representative datasets.

Recently, deep-learning-based blind picture quality measurement (BPQM) metrics have gained significant attention. However, training a robust deep BPQM metric remains a difficult and challenging task because of the limited number of subject-rated training samples. State-of-the-art full-reference (FR) picture quality measurement (PQM) metrics are in good agreement with human subjective quality scores. Therefore, they can be employed to approximate human subjective quality scores to train BPQM metrics. Inspired by this, we propose a deep encoder–decoder architecture (DEDA) for opinion-unaware (OU) BPQM that does not require human-labeled distorted samples for training. In the training procedure, to avoid overfitting and to ensure the independency of the training and testing samples, we first construct 6,000 distorted pictures and use their objective quality/similarity maps obtained using a high-performance FR-PQM metric for distorted pictures as training labels. Subsequently, an end-to-end map between the distorted pictures and their objective quality/similarity maps (labels) is learned, represented as the DEDA that takes the distorted picture as the input and outputs its predicted quality/similarity map. In the DEDA, the pyramid supervision training strategy is used, which applies supervised learning over three scale layers to efficiently optimize the parameters. In the testing procedure, the quality/similarity maps of the testing samples that can help localize distortions can be predicted with the trained DEDA architecture. The predicted quality/similarity maps are then gradually pooled together to obtain the overall objective quality scores. Comparative experiments on three publicly available standard PQM datasets demonstrate that our proposed DEDA metric is in good agreement with subjective assessment compared to previous state-of-the-art OU-BPQM metrics.