Search

Abstract Traffic sign detection is critical for autonomous driving technology. However, accurately detecting traffic signs in complex traffic environments remains challenge despite the widespread use of one‐stage detection algorithms known for their real‐time processing capabilities. In this paper, the authors propose a traffic sign detection method based on YOLO v8. Specifically, this study introduces the Space‐to‐Depth (SPD) module to address missed detections caused by multi‐scale variations of traffic signs in traffic scenes. The SPD module compresses spatial information into depth channels, expanding the receptive field and enhancing the detection capabilities for objects of varying sizes. Furthermore, to address missed detections caused by complex backgrounds such as trees, this paper employs the Select Kernel attention mechanism. This mechanism enables the model to dynamically adjust its focus and more effectively concentrate on key features. Additionally, considering the uneven distribution of training data, the authors adopted the WIoUv3 loss function, which optimizes loss calculation through a weighted approach, thereby improving the model's detection performance across various sizes and frequencies of instances. The proposed methods were validated on the CCTSDB and TT100K datasets. Experimental results demonstrate that the authors’ method achieves substantial improvements of 3.2% and 5.1% on the mAP50 metric compared to YOLOv8s, while maintaining high detection speed, significantly enhancing the overall performance of the detection system. The code for this paper is located at https://github.com/dusongjie/TSD‐YOLO‐Small‐Traffic‐Sign‐Detection‐Based‐on‐Improved‐YOLO‐v8

Abstract The limited of texture details information in low‐resolution facial or eye images presents a challenge for gaze estimation. To address this, FSKT‐GE (feature maps similarity knowledge transfer for low‐resolution gaze estimation) is proposed, a gaze estimation framework consisting of both a high resolution (HR) network and low resolution (LR) network with the identical structure. Rather than mere feature imitation, this issue is addressed by assessing the cosine similarity of feature layers, emphasizing the distribution similarity between the HR and LR networks. This enables the LR network to acquire richer knowledge. This framework utilizes a combination loss function, incorporating cosine similarity measurement, soft loss based on probability distribution difference and gaze direction output, along with a hard loss from the LR network output layer. This approach on low‐resolution datasets derived from Gaze360 and RT‐Gene datasets is validated, demonstrating excellent performance in low‐resolution gaze estimation. Evaluations on low‐resolution images obtained through 2×, 4×, and 8× down‐sampling are conducted on two datasets. On the Gaze360 dataset, the lowest mean angular errors of 10.97°, 11.22°, and 13.61° were achieved, while on the RT‐Gene dataset, the lowest mean angular errors of 6.73°, 6.83°, and 7.75° were obtained.

Objective The data of various monitoring points regarding rail potential as monitoring object is correlated in time and space, and the direct manifestation of changes in rail-to-rebar structural resistance is reflected in rail potential variation. It is aimed to explore a method for monitoring the rail-to-ground insulation state and diagnosing defects based on rail potential spatiotemporal correlation. Method The stray current monitoring system with rail potential as the monitoring object is elaborated. The characteristics of rail potential data under insulation defects are analyzed and a feature matrix for the data is established. Based on the anomaly detection principle of Minkowski distance, the detection steps for abnormal sections of rail-to-ground insulation and for insulation defect locationing are explained. A project in Qingdao Rail Transit is taken as study case for modeling and simulation to evaluate the effectiveness and accuracy of the proposed method. Result & Conclusion The proposed method can effectively monitor the rail insulation state and accurately locate insulation defects.

With the promotion of China’s ”peak carbon and carbon neutrality” target, PV power generation is gradually entering the era of price parity, and cost will no longer be the main obstacle to its scale development, but grid consumption will become the main factor to restrict its further development. In order to further promote the consumption of PV and realize the low-carbon transformation of microgrid, this paper establishes a game pricing model led by Photovoltaic Cluster (PVC) based on the response of power demand, carries out the research on the optimal scheduling of PV in microgrid by establishing the game relationship among grid, PVC and users. Firstly, a new IEEE 33-node arithmetic simulation model is built, and secondly, three PVCs are divided among the nodes, and the feasibility of the model is verified by solving the optimal tariff strategy through genetic algorithm. The final results show that the optimal scheduling method is effective in meeting the demand response of users in PVCs while reducing the cost of electricity consumption and promoting the local consumption of PV; in addition, after increasing the proportion of PV access, PV will become the main supplier of electricity and the operation mode of PVCs will be free from dependence on the grid.

Adding hydrogen to the fuel can change the combustion characteristics and greatly improve the pollutants emission for the gas turbine. The numerical method was adopted to study the combustion process in a counter-flow combustor of a 100 kW micro gas turbine using methane doped by hydrogen and various distribution schemes of air flow. The combustion characteristics and pollutant emissions were explored to ascertain the influence of air distribution based on solving the validated models. It was shown that as the amount of premixed air increased in the swirling gas, the range of the recirculation region became larger and the range of the high-temperature zone in the combustion chamber gradually enlarged. When the amount of premixed air was 30%, the outlet temperature distribution of the combustor was excellent and the average temperature was 1172 K. Moreover, the concentration of NOXgradually increased and reached a maximum value of 23.46 ppm (@15% O2) as the premixed air increased in the range of the ratio less than 40%. It was reduced to 0.717 ppm (@15% O2) when the amount of premixed air increased to 50%. These findings may support the running of the micro gas turbine using the hybrid fuel of hydrogen and methane.

Vision-based object detection is an essential component of autonomous driving. Because vehicles typically have limited on-board computing resources, a small-sized detection model is required. Simultaneously, high object detection accuracy and real-time inference detection speeds are required to ensure safety while driving. In this paper, an anchor-free lightweight object detector for autonomous driving called ALODAD is proposed. ALODAD incorporates an attention scheme into the lightweight neural network GhostNet and builds an anchor-free detection framework to achieve lower computational costs and provide parameters with high detection accuracy. Specifically, the lightweight backbone neural network integrates a convolutional block attention model that analyzes the valuable features from traffic scene images to generate an accurate bounding box, and then constructs feature pyramids for multi-scale object detection. The proposed method adds an intersection over union (IoU) branch to the decoupled detector to rank the vast number of candidate detections accurately. To increase the data diversity, data augmentation was used during training. Extensive experiments based on benchmarks demonstrate that the proposed method offers improved performance compared to the baseline. The proposed method can achieve an increased detection accuracy while meeting the real-time requirements of autonomous driving. The proposed method was compared with the YOLOv5 and RetinaNet models and 98.7% and 94.5% were obtained for the average precision metrics AP50 and AP75, respectively, on the BCTSDB dataset.

Image dehazing is one of the problems that need to be solved urgently in the field of computer vision. In recent years, more and more algorithms have been applied to image dehazing and achieved good results. However, the image after dehazing still has color distortion, contrast and saturation disorder, and other challenges; in order to solve these problems, in this paper, an effective image dehazing method is proposed, which is based on improved color channel transfer and multiexposure image fusion to achieve image dehazing. First, the image is preprocessed using a color channel transfer method based on k-means. Second, gamma correction is introduced on the basis of guided filtering to obtain a series of multiexposure images, and the obtained multiexposure images are fused into a dehazed image through a Laplacian pyramid fusion scheme based on local similarity of adaptive weights. Finally, contrast and saturation corrections are performed on the dehazed image. Experimental verification is carried out on synthetic dehazed images and natural dehazed images, and it is verified that the method proposed is superior to existing dehazed algorithms from both subjective and objective aspects.

Deep learning techniques for gaze estimation usually determine gaze direction directly from images of the face. These algorithms achieve good performance because face images contain more feature information than eye images. However, these image classes contain a substantial amount of redundant information that may interfere with gaze prediction and may represent a bottleneck for performance improvement. To address these issues, we model long-distance dependencies between the eyes via Strip Pooling and Multi-Criss-Cross Attention Networks (SPMCCA-Net), which consist of two newly designed network modules. One module is represented by a feature enhancement bottleneck block based on fringe pooling. By incorporating strip pooling, this residual module not only enlarges its receptive fields to capture long-distance dependence between the eyes but also increases weights on important features and reduces the interference of redundant information unrelated to gaze. The other module is a multi-criss-cross attention network. This module exploits a cross-attention mechanism to further enhance long-range dependence between the eyes by incorporating the distribution of eye-gaze features and providing more gaze cues for improving estimation accuracy. Network training relies on the multi-loss function, combined with smooth L1 loss and cross entropy loss. This approach speeds up training convergence while increasing gaze estimation precision. Extensive experiments demonstrate that SPMCCA-Net outperforms several state-of-the-art methods, achieving mean angular error values of 10.13° on the Gaze360 dataset and 6.61° on the RT-gene dataset.

Heatmap-based traditional approaches for estimating human pose usually suffer from drawbacks such as high network complexity or suboptimal accuracy. Focusing on the issue of multi-person pose estimation without heatmaps, this paper proposes an end-to-end, lightweight human pose estimation network using a multi-scale coordinate attention mechanism based on the Yolo-Pose network to improve the overall network performance while ensuring the network is lightweight. Specifically, the lightweight network GhostNet was first integrated into the backbone to alleviate the problem of model redundancy and produce a significant number of effective feature maps. Then, by combining the coordinate attention mechanism, the sensitivity of our proposed network to direction and location perception was enhanced. Finally, the BiFPN module was fused to balance the feature information of different scales and further improve the expression ability of convolutional features. Experiments on the COCO 2017 dataset showed that, compared with the baseline method YOLO-Pose, the average accuracy of the proposed network on the COCO 2017 validation dataset was improved by 4.8% while minimizing the amount of network parameters and calculations. The experimental results demonstrated that our proposed method can improve the detection accuracy of human pose estimation while ensuring that the model is lightweight.

Abstract Conventional maintenance mode for the traction power supply system (TPSS) is to perform scheduled regular maintenance activities for power supply equipment, while such maintenance mode may result in undue maintenance tasks and low efficiency due to different degradation processes of different sorts of equipment. To address this problem, this paper introduces a preventive opportunistic maintenance (POM) method for TPSS based on equipment reliability. Firstly, a POM model is established by considering the equipment reliability degradation process based on Weibull distribution. Then, by considering the total power outage time in the planned operation cycle of TPSS as the optimization objective, the optimal maintenance scheme of TPSS is formulated by iterative method of maintenance strategies. The proposed method is verified by introducing practical maintenance strategies and fault record data of the traction transformer, circuit breaker and disconnector in an actual TPSS of a railway administration. Results show that the presented method can make full use of the existing fault data to develop a POM scheme for TPSS. It can improve maintenance efficiency and reduce power outage time, providing guidance to formulate scientific maintenance strategies for TPSS.

Traffic sign detection is an important component of autonomous vehicles. There is still a mismatch problem between the existing detection algorithm and its practical application in real traffic scenes, which is mainly due to the detection accuracy and data acquisition. To tackle this problem, this study proposed an improved sparse R-CNN that integrates coordinate attention block with ResNeSt and builds a feature pyramid to modify the backbone, which enables the extracted features to focus on important information, and improves the detection accuracy. In order to obtain more diverse data, the augmentation method used is specifically designed for complex traffic scenarios, and we also present a traffic sign dataset in this study. For on-road autonomous vehicles, we designed two modules, self-adaption augmentation (SAA) and detection time augmentation (DTA), to improve the robustness of the detection algorithm. The evaluations on traffic sign datasets and on-road testing demonstrate the accuracy and effectiveness of the proposed method.

In the field of computer vision, training a well-performing model on a dataset with a long-tail distribution is a challenging task. To address this challenge, image resampling is usually introduced as a simple and effective solution. However, when performing instance segmentation tasks, there may be multiple classes in one image. Hence, image resampling alone is not enough to obtain a sufficiently balanced distribution at the level of target data volume. In this paper, we propose an improved instance segmentation method for long-tail datasets based on Mask R-CNN. Specifically, an object-centric memory bank is used to establish an object-centric storage strategy that can solve the imbalance problem with respect to categories. In the testing phase, a post-processing calibration is used to adjust each class logit to change the confidence score, which improves the prediction score of tail classes. A discrete cosine transform-based mask is used to obtain high-quality masks, which improves segmentation accuracy. The evaluation of the proposed method on the LVIS dataset demonstrates its effectiveness. The proposed method improves the AP performance of EQL by 2.2%.

The anchor-free-based object detection method is a crucial part in an autonomous driving system because of its low computing cost. However, the under-fitting of positive samples and over-fitting of negative samples affect the detection performance. An aspect-aware anchor-free detector is proposed in this paper to address this problem. Specifically, it adds an aspect prediction head at the end of the detector, which can learn different distributions of aspect ratios between other objects. The sample definition method is improved to alleviate the problem of positive and negative sample imbalance. A loss function is designed to strengthen the learning weight of the center point of the network. The validation results show that the AP50 and AP75 of the proposed method are 97.3% and 93.4% on BCTSDB, and the average accuracies of the car, pedestrian, and cyclist are 92.7%, 77.4%, and 78.2% on KITTI, respectively. The comparison results demonstrate that the proposed algorithm is better than existing anchor-free methods.

Object detection plays a vital role in autonomous driving systems, and the accurate detection of surrounding objects can ensure the safe driving of vehicles. This paper proposes a category-assisted transformer object detector called DetectFormer for autonomous driving. The proposed object detector can achieve better accuracy compared with the baseline. Specifically, ClassDecoder is assisted by proposal categories and global information from the Global Extract Encoder (GEE) to improve the category sensitivity and detection performance. This fits the distribution of object categories in specific scene backgrounds and the connection between objects and the image context. Data augmentation is used to improve robustness and attention mechanism added in backbone network to extract channel-wise spatial features and direction information. The results obtained by benchmark experiment reveal that the proposed method can achieve higher real-time detection performance in traffic scenes compared with RetinaNet and FCOS. The proposed method achieved a detection performance of 97.6% and 91.4% in AP50 and AP75 on the BCTSDB dataset, respectively.

As the core equipment of a traction power supply system, the traction transformer is very important to ensure the safe and reliable operation of the system. At present, the three-ratio method is mainly used to distinguish transformer faults, whereas such a method has some defects, such as insufficient coding and over-general fault classification. At the same time, on-site maintenance personnel make an empirical judgment based on various test data, which is subjective and uncertain to a certain extent. For cases with multiple abnormal data and relatively complex conditions, on-site personnel often need to discuss and even dismantle the transformer to identify the fault, which is time-consuming and costly. In order to improve the effect of fault diagnosis for traction transformer, this paper uses Bayesian network to correlate the cause and effect of various tests and faults. By combining the results of field tests, the fault is diagnosed by the causal probability of the Bayesian network, rather than relying on the exception that occurred in a single experiment to judge its fault. The diagnosis results are more accurate and objective by using the Bayesian network. In this paper, the frequent test anomalies of the traction transformer are taken into account in the network, so that the network can more comprehensively analyze the operation situation of the traction transformer and judge the type of fault. According to field situations, based on the existing set of symptoms of the Bayesian network fault diagnosis, this paper further considers the insulation resistance, dielectric loss tangent value, oil and gas, power frequency voltage, and leakage current. By combining the association rules algorithm and the experience of the field operators, the cause–effect relationship of test data and the conditional probability parameters of the network are obtained. Then, the Bayesian network is constructed and used for traction transformer fault diagnosis. The case study shows that the four types of fault diagnosed using the Bayesian network model proposed in this paper are consistent with the fault types inspected by on-site operators, which shows promising engineering application prospects.

The initial simulation calculation of the ORC power generation system was carried out using the software Aspen Plus, and the simulation data matched with the design conditions were obtained. According to the specific structure of the evaporator and superheater in the ORC power generation system and the characteristics of the software Aspen EDR, a new simulation calculation method is proposed: structural simulation calculation method. The calculation method and the direct simulation calculation method are used to carry out simulation comparison to find out the regularity of the change of waste heat resources, and it is convenient to further analyze and control the ORC power generation system.

This survey reviews advances in 3D object detection approaches for autonomous driving. A brief introduction to 2D object detection is first discussed and drawbacks of the existing methodologies are identified for highly dynamic environments. Subsequently, this paper reviews the state-of-the-art 3D object detection techniques that utilizes monocular and stereo vision for reliable detection in urban settings. Based on depth inference basis, learning schemes, and internal representation, this work presents a method taxonomy of three classes: model-based and geometrically constrained approaches, end-to-end learning methodologies, and hybrid methods. There is highlighted segment for current trend of multi-view detectors as end-to-end methods due to their boosted robustness. Detectors from the last two kinds were specially selected to exploit the autonomous driving context in terms of geometry, scene content and instances distribution. To prove the effectiveness of each method, 3D object detection datasets for autonomous vehicles are described with their unique features, e. g., varying weather conditions, multi-modality, multi camera perspective and their respective metrics associated to different difficulty categories. In addition, we included multi-modal visual datasets, i. e., V2X that may tackle the problems of single-view occlusion. Finally, the current research trends in object detection are summarized, followed by a discussion on possible scope for future research in this domain. [ABSTRACT FROM AUTHOR]

When a brazed plate heat exchanger is used as an evaporator, the working mass in the channel may undergo solidification, thereby hindering the refrigeration cycle. In this study the liquid solidification process and its optimization in a brazed plate heat exchanger are investigated numerically for different inlet velocities; moreover, different levels of corrugation are considered. The results indicate that solidification first occurs around the contacts, followed by the area behind the contacts. It is also shown that dead flow zones exist in the sharp areas and such areas are prone to liquid solidification. After optimization, the solidification area attains its smallest value when a corrugation spacing λ = 4.2 mm is considered. [ABSTRACT FROM AUTHOR]

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof- the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation. [ABSTRACT FROM AUTHOR]