Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism

Zhang Xue; Chang Li

doi:doi:10.11648/j.ajece.20220601.16

| Peer-Reviewed

Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism

Zhang Xue, Chang Li

Published in American Journal of Electrical and Computer Engineering (Volume 6, Issue 1)

Received: 8 May 2022 Accepted: 13 June 2022 Published: 16 June 2022

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Pedestrian detection is widely used in daily life, but it is difficult to study in highway environment, such as occlusion overlap. In order to reduce error detection rate of highway pedestrian detection, an algorithm based on YOLOv5s was proposed. Since vehicle occlusion leads to the reduction of effective features of targets, CBAM attention and SE-NET mechanism module is introduced in the network of YOLOv5s to maximize the extraction of effective features. In order to prevent the spatial characteristic information in the trunk network from being damaged, CBAM module is added at the beginning and end of the structure, and SE-Net attention module is added in the neck network, that is, after the detection layer C3 module, the weight information obtained is connected with the subsequent Conv module, so that the model pays more attention to the pedestrian area. Due to low detection accuracy caused by pedestrian overlap. YOLOv5s was designed by combining DIOU_NMS candidate box screening mechanism. The results show that the mean average precision of YOLOv5s (IOU=0.5) increases by 0.48, and the value of Recall of the improved algorithm increases by 0.51 respectively. The improved pedestrian detection algorithm improves the accuracy of target box regression. Thus, the confidence of pedestrian detection is improved. Based on the improvement strategies mentioned above, the detection speed is 32fps, which meets the requirements of real-time detection.

Published in	American Journal of Electrical and Computer Engineering (Volume 6, Issue 1)
DOI	10.11648/j.ajece.20220601.16
Page(s)	47-53
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2022. Published by Science Publishing Group

Keywords

Pedestrian Detection, Overlapping Target Detection, YOLOv5s, Attention Mechanism, Non-maximum Suppression

References

[1]	Dalal N, Triggs B. Histograms of oriented gradients for human detection [C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE, 2005, 1: 886-893.
[2]	Nam W, P Dollár, Han J H. Local decorrelation for improved detection [J]. Advances in Neural Information Processing Systems, 2014, 1: 424-432.
[3]	Gavrila D M, Munder S. Multi-cue pedestrian detection and tracking from a moving vehicle [J]. International Journal of Computer Vision, 2007, 73 (1): 41-59.
[4]	Zhou C, Yang M, Yuan J. Discriminative feature transformation for occluded pedestrian detection [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 9557-9566.
[5]	Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 779-788.
[6]	Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector [C]//European Conference on Computer Vision. Springer, Cham, 2016: 21-37.
[7]	Deng J, Wan W G. Dense pedestrian detection based on improved YOLOv3 [J]. Electronic Measurement Technology, 2021, 44 (11): 90-95.
[8]	Ahmed Z, Iniyavan R. Enhanced vulnerable pedestrian detection using deep learning [C]//2019 International Conference on Communication and Signal Processing (ICCSP). IEEE, 2019: 0971-0974.
[9]	Zhuang C, Li Z, Zhu X, et al. SAD et: learning an efficient and accurate pedestrian detector [C]//2021 IEEE International Joint Conference on Biometrics (IJCB). IEEE, 2021: 1-8.
[10]	Woo S, Park J, Lee J Y, et al. CBAM: Convolutional block attention module [C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 3-19.
[11]	Hu J, Shen L, Sun G. Squeeze-and-excitation networks [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7132-7141.
[12]	Lin X Z, LIU J, Tian S, et al. Image Description Generation Method based on multi-space mixed attention [J]. Computer Applications, 2020, 40 (4): 985-989.
[13]	Cheng M Y, Gai S Y, DA F P. Research on stereo matching network based on attention mechanism [J]. Acta Optica Sinica, 2020, 40 (14): 138-146.
[14]	Selvaraju R R, Cogswell M, Das A, et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization [J]. International Journal of Computer Vision, 2020, 128 (2): 336-359.
[15]	Felzenszwalb P F, Girshick R B, McAllester D, et al. Object detection with discriminatively trained part-based models [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 32 (9): 1627-1645.
[16]	Yang H, Quan J C, LIANG X Y, et al. Progress in Object Detection Based on Weakly supervised Learning. Computer Engineering and Applications, 2021, 57 (16): 40-49.

Cite This Article

Plain Text BibTeX RIS

APA Style

Zhang Xue, Chang Li. (2022). Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism. American Journal of Electrical and Computer Engineering, 6(1), 47-53. https://doi.org/10.11648/j.ajece.20220601.16

Copy | Download

ACS Style

Zhang Xue; Chang Li. Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism. Am. J. Electr. Comput. Eng. 2022, 6(1), 47-53. doi: 10.11648/j.ajece.20220601.16

Copy | Download

AMA Style

Zhang Xue, Chang Li. Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism. Am J Electr Comput Eng. 2022;6(1):47-53. doi: 10.11648/j.ajece.20220601.16

Copy | Download

@article{10.11648/j.ajece.20220601.16,
  author = {Zhang Xue and Chang Li},
  title = {Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism},
  journal = {American Journal of Electrical and Computer Engineering},
  volume = {6},
  number = {1},
  pages = {47-53},
  doi = {10.11648/j.ajece.20220601.16},
  url = {https://doi.org/10.11648/j.ajece.20220601.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajece.20220601.16},
  abstract = {Pedestrian detection is widely used in daily life, but it is difficult to study in highway environment, such as occlusion overlap. In order to reduce error detection rate of highway pedestrian detection, an algorithm based on YOLOv5s was proposed. Since vehicle occlusion leads to the reduction of effective features of targets, CBAM attention and SE-NET mechanism module is introduced in the network of YOLOv5s to maximize the extraction of effective features. In order to prevent the spatial characteristic information in the trunk network from being damaged, CBAM module is added at the beginning and end of the structure, and SE-Net attention module is added in the neck network, that is, after the detection layer C3 module, the weight information obtained is connected with the subsequent Conv module, so that the model pays more attention to the pedestrian area. Due to low detection accuracy caused by pedestrian overlap. YOLOv5s was designed by combining DIOU_NMS candidate box screening mechanism. The results show that the mean average precision of YOLOv5s (IOU=0.5) increases by 0.48, and the value of Recall of the improved algorithm increases by 0.51 respectively. The improved pedestrian detection algorithm improves the accuracy of target box regression. Thus, the confidence of pedestrian detection is improved. Based on the improvement strategies mentioned above, the detection speed is 32fps, which meets the requirements of real-time detection.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism
AU  - Zhang Xue
AU  - Chang Li
Y1  - 2022/06/16
PY  - 2022
N1  - https://doi.org/10.11648/j.ajece.20220601.16
DO  - 10.11648/j.ajece.20220601.16
T2  - American Journal of Electrical and Computer Engineering
JF  - American Journal of Electrical and Computer Engineering
JO  - American Journal of Electrical and Computer Engineering
SP  - 47
EP  - 53
PB  - Science Publishing Group
SN  - 2640-0502
UR  - https://doi.org/10.11648/j.ajece.20220601.16
AB  - Pedestrian detection is widely used in daily life, but it is difficult to study in highway environment, such as occlusion overlap. In order to reduce error detection rate of highway pedestrian detection, an algorithm based on YOLOv5s was proposed. Since vehicle occlusion leads to the reduction of effective features of targets, CBAM attention and SE-NET mechanism module is introduced in the network of YOLOv5s to maximize the extraction of effective features. In order to prevent the spatial characteristic information in the trunk network from being damaged, CBAM module is added at the beginning and end of the structure, and SE-Net attention module is added in the neck network, that is, after the detection layer C3 module, the weight information obtained is connected with the subsequent Conv module, so that the model pays more attention to the pedestrian area. Due to low detection accuracy caused by pedestrian overlap. YOLOv5s was designed by combining DIOU_NMS candidate box screening mechanism. The results show that the mean average precision of YOLOv5s (IOU=0.5) increases by 0.48, and the value of Recall of the improved algorithm increases by 0.51 respectively. The improved pedestrian detection algorithm improves the accuracy of target box regression. Thus, the confidence of pedestrian detection is improved. Based on the improvement strategies mentioned above, the detection speed is 32fps, which meets the requirements of real-time detection.
VL  - 6
IS  - 1
ER  -

Copy | Download

Author Information

Zhang Xue

School of Information Science and Engineering, Shenyang University of Technology, Shenyang, China
Chang Li

School of Information Science and Engineering, Shenyang University of Technology, Shenyang, China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Zhang Xue, Chang Li. (2022). Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism. American Journal of Electrical and Computer Engineering, 6(1), 47-53. https://doi.org/10.11648/j.ajece.20220601.16

Copy | Download

ACS Style

Zhang Xue; Chang Li. Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism. Am. J. Electr. Comput. Eng. 2022, 6(1), 47-53. doi: 10.11648/j.ajece.20220601.16

Copy | Download

AMA Style

Zhang Xue, Chang Li. Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism. Am J Electr Comput Eng. 2022;6(1):47-53. doi: 10.11648/j.ajece.20220601.16

Copy | Download

@article{10.11648/j.ajece.20220601.16,
  author = {Zhang Xue and Chang Li},
  title = {Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism},
  journal = {American Journal of Electrical and Computer Engineering},
  volume = {6},
  number = {1},
  pages = {47-53},
  doi = {10.11648/j.ajece.20220601.16},
  url = {https://doi.org/10.11648/j.ajece.20220601.16},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajece.20220601.16},
  abstract = {Pedestrian detection is widely used in daily life, but it is difficult to study in highway environment, such as occlusion overlap. In order to reduce error detection rate of highway pedestrian detection, an algorithm based on YOLOv5s was proposed. Since vehicle occlusion leads to the reduction of effective features of targets, CBAM attention and SE-NET mechanism module is introduced in the network of YOLOv5s to maximize the extraction of effective features. In order to prevent the spatial characteristic information in the trunk network from being damaged, CBAM module is added at the beginning and end of the structure, and SE-Net attention module is added in the neck network, that is, after the detection layer C3 module, the weight information obtained is connected with the subsequent Conv module, so that the model pays more attention to the pedestrian area. Due to low detection accuracy caused by pedestrian overlap. YOLOv5s was designed by combining DIOU_NMS candidate box screening mechanism. The results show that the mean average precision of YOLOv5s (IOU=0.5) increases by 0.48, and the value of Recall of the improved algorithm increases by 0.51 respectively. The improved pedestrian detection algorithm improves the accuracy of target box regression. Thus, the confidence of pedestrian detection is improved. Based on the improvement strategies mentioned above, the detection speed is 32fps, which meets the requirements of real-time detection.},
 year = {2022}
}

Copy | Download

TY  - JOUR
T1  - Research on YOLOv5s Highway Pedestrian Detection Algorithm Integrating Attention Mechanism
AU  - Zhang Xue
AU  - Chang Li
Y1  - 2022/06/16
PY  - 2022
N1  - https://doi.org/10.11648/j.ajece.20220601.16
DO  - 10.11648/j.ajece.20220601.16
T2  - American Journal of Electrical and Computer Engineering
JF  - American Journal of Electrical and Computer Engineering
JO  - American Journal of Electrical and Computer Engineering
SP  - 47
EP  - 53
PB  - Science Publishing Group
SN  - 2640-0502
UR  - https://doi.org/10.11648/j.ajece.20220601.16
AB  - Pedestrian detection is widely used in daily life, but it is difficult to study in highway environment, such as occlusion overlap. In order to reduce error detection rate of highway pedestrian detection, an algorithm based on YOLOv5s was proposed. Since vehicle occlusion leads to the reduction of effective features of targets, CBAM attention and SE-NET mechanism module is introduced in the network of YOLOv5s to maximize the extraction of effective features. In order to prevent the spatial characteristic information in the trunk network from being damaged, CBAM module is added at the beginning and end of the structure, and SE-Net attention module is added in the neck network, that is, after the detection layer C3 module, the weight information obtained is connected with the subsequent Conv module, so that the model pays more attention to the pedestrian area. Due to low detection accuracy caused by pedestrian overlap. YOLOv5s was designed by combining DIOU_NMS candidate box screening mechanism. The results show that the mean average precision of YOLOv5s (IOU=0.5) increases by 0.48, and the value of Recall of the improved algorithm increases by 0.51 respectively. The improved pedestrian detection algorithm improves the accuracy of target box regression. Thus, the confidence of pedestrian detection is improved. Based on the improvement strategies mentioned above, the detection speed is 32fps, which meets the requirements of real-time detection.
VL  - 6
IS  - 1
ER  -

Copy | Download