Search

Abstract Human pose estimation is an important task in computer vision, which can provide key point detection of human body and obtain bone information. At present, human pose estimation is mainly utilized for detection of large targets, and there is no solution for detection of small targets. This paper proposes a multi-channel spatial information feature based human pose (MCSF-Pose) estimation algorithm to address the issue of medium and small targets inaccurate detection of human key points in scenarios involving occlusion and multiple poses. The MCSF-Pose network is a bottom-up regression network. Firstly, an UP-Focus module is designed to expand the feature information while reducing parameter computation during the up-sampling process. Then, the channel segmentation strategy is adopted to cut the features, and the feature information of multiple dimensions is retained through different convolutional groups, which reduces the parameter lightweight network model and makes up for the loss of the feature information associated with the depth of the network. Finally, the three-layer PANet structure is designed to reduce the complexity of the model. With the aid of the structure, it also to improve the detection accuracy and anti-interference ability of human key points. The experimental results indicate that the proposed algorithm outperforms YOLO-Pose and other human pose estimation algorithms on COCO2017 and MPII human pose datasets.

Human pose estimation is an important task in computer vision, which can provide key point detection of human body and obtain bone information. At present, human pose estimation is mainly utilized for detection of large targets, and there is no solution for detection of small targets. This paper proposes a multi-channel spatial information feature based human pose (MCSF-Pose) estimation algorithm to address the issue of medium and small targets inaccurate detection of human key points in scenarios involving occlusion and multiple poses. The MCSF-Pose network is a bottom-up regression network. Firstly, an UP-Focus module is designed to expand the feature information while reducing parameter computation during the up-sampling process. Then, the channel segmentation strategy is adopted to cut the features, and the feature information of multiple dimensions is retained through different convolutional groups, which reduces the parameter lightweight network model and makes up for the loss of the feature information associated with the depth of the network. Finally, the three-layer PANet structure is designed to reduce the complexity of the model. With the aid of the structure, it also to improve the detection accuracy and anti-interference ability of human key points. The experimental results indicate that the proposed algorithm outperforms YOLO-Pose and other human pose estimation algorithms on COCO2017 and MPII human pose datasets. [ABSTRACT FROM AUTHOR]

This article presents research conducted on the backplane high‐speed Peripheral Component Interconnect Express version 4 (PCIe gen4) link between central processor root complex and the end‐point device in order to confirm its compliance. Signal integrity analysis was performed using a method that included channel segmentation, development of corner models for channel segments, full‐wave electromagnetic simulation utilizing the finite element method (FEM) and the creation of cascaded channel models, as well as determination of the worst‐case models for the channel. The results of this analysis were then used to modify the channel design in order to decrease insertion loss. Changes in the design included utilizing a very low loss dielectric for the backplane board, correcting the sizes of differential pairs and decreasing the via stubs. Frequency domain simulation of the modified channel design has shown a 25% decrease in insertion loss. The calculation of eye diagrams for the modified design has confirmed that the channel parameters meet the requirements for the PCIe gen4 standard. [ABSTRACT FROM AUTHOR]

Abstract This article presents research conducted on the backplane high‐speed Peripheral Component Interconnect Express version 4 (PCIe gen4) link between central processor root complex and the end‐point device in order to confirm its compliance. Signal integrity analysis was performed using a method that included channel segmentation, development of corner models for channel segments, full‐wave electromagnetic simulation utilizing the finite element method (FEM) and the creation of cascaded channel models, as well as determination of the worst‐case models for the channel. The results of this analysis were then used to modify the channel design in order to decrease insertion loss. Changes in the design included utilizing a very low loss dielectric for the backplane board, correcting the sizes of differential pairs and decreasing the via stubs. Frequency domain simulation of the modified channel design has shown a 25% decrease in insertion loss. The calculation of eye diagrams for the modified design has confirmed that the channel parameters meet the requirements for the PCIe gen4 standard.

As a challenging computer vision task, video-based person Re-IDentification (Re-ID) has been intensively studied, and recent works have achieved a series of satisfactory results by capturing spatial temporal relationships. However, extensive observations have found that the same feature vector generated by a convolutional neural network contains considerable redundant information in the channel dimension. This issue is seldom investigated. A Spatial Temporal and Channel Aware Network (STCAN) for video-based ReID is studied in this paper. It jointly considers spatial temporal and channel information. Firstly, the Spatial Attention Enhanced (SAE) convolutional network is developed as the backbone network to learn spatial enhanced features from video frames. Secondly, a Channel Segmentation and Group Shuffle (CSGS) convolution module is designed to jointly address temporal and channel relations. Finally, a Two Branch Weighted Fusion (TBWF) mechanism is introduced to enhance the robustness of the Re-ID network by fusing the output of the SAE backbone network and CSGS. Comprehensive experiments are conducted on three large-scale datasets MARS, LSVID, and P-DESTRE. The experimental results imply that the STCAN can effectively improve the performance of video-based Re-ID and outperform several state-of-the-art methods. • A feature aggregation module, CSGS, is proposed to capture temporal and channel relations. • An attention mechanism, SAE, is introduced to enhance spatial dependencies. • A Fusion mechanism is proposed to combine the output of SAE and CSGS [ABSTRACT FROM AUTHOR]