Improved Pedestrian Detection Algorithm of Yolov4 Network Structure
Authors: 
Xiujun Zhu, Yujie Bai, Yijian PeiAuthors Info & Claims
Article No.: 13, Pages 1 - 6
Abstract
When the YOLOV4 network detects pedestrians alone, the small target pedestrians will be missed, resulting in the reduction of P (Precision) and AP (Average Precision) values. This paper improves the YOLOV4 network structure. In order to improve the feature extraction capability of the network for small targets, a shallower feature layer is added to the original three output feature layers of the YOLOV4 backbone network to build PANet (Path Aggregation Network) together. And two SPP (Spatial Pyramid Pooling) structures are added to expand the receptive field. The channel attention mechanism module is added and some convolutional layers of the original network are deleted. Finally, transfer learning is used to make the detection effect better. The P value of the pedestrian on the PASCAL VOC data set increased from 84.43% to 91.37%, and the AP value increased from 74.78% to 87.39%, and the P value on the commonly used pedestrian detection data set INRIA (INRIA Person Dataset) increased from 93.20% increased to 98.02%, AP value increased from 91.08% to 94.02%. Experimental results show that the network has a better effect on pedestrian detection, and the accuracy and average precision are improved.
References
[1]
N. Dalal, (2005). Histograms of oriented gradients for human detection. Proc of Cvpr.
[2]
M. Nan, C. Li, Jiancheng, H., Qiuna, S and Guoping, Z. . (2019). Pedestrian Detection Based on HOG Features and SVM Realizes Vehicle-Human-Environment Interaction. 2019 15th International Conference on Computational Intelligence and Security (CIS).
[3]
Wu, B. and Nevatia, R. (2005). Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors. Tenth IEEE International Conference on Computer Vision. IEEE.
[4]
Ojala, T., Matti Pietikäinen and Topi Mäenpää. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Classification with Local Binary Patterns.
[5]
Girshick, R., Donahue, J., Darrell, T., & Malik, J. . (2013). Rich feature hierarchies for accurate object detection and semantic segmentation.
[6]
Luo, H. W., Zhang, C. S., Pan, F. C., & Ju, X. M. . (2020). Contextual-YOLOV3: Implement Better Small Object Detection Based Deep Learning. 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI). IEEE.
[7]
Lai, Y., Sun, F., & Liu, H. . (2020). Small Object Detection Base on YOLOv3 For Pedestrian Recognition. 2020 5th International Conference on Control and Robotics Engineering (ICCRE). IEEE.
[8]
Nguyen, N. D., Do, T., Ngo, T. D., & Le, D. D. . (2020). An evaluation of deep learning methods for small object detection. Journal of Electrical and Computer Engineering, 2020, 1-18.
[9]
Girshick, R. . (2015). Fast r-cnn. Computer ence.
[10]
Ren, S., He, K., Girshick, R., & Sun, J. . (2017). Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 39(6), 1137-1149.
[11]
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. . (2016). You Only Look Once: Unified, Real-Time Object Detection. Computer Vision & Pattern Recognition. IEEE.
[12]
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., & Berg, A. C. . (2016). SSD: Single Shot MultiBox Detector. European Conference on Computer Vision. Springer International Publishing
[13]
Bochkovskiy, Alexey & Wang, Chien-Yao & Liao, Hong-yuan. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. Proc of Cvpr.
[14]
Zhu, Y., Yang, J., Deng, X., Xiao, C., & An, W. . (2020). Infrared pedestrian detection based on attention mechanism. Journal of Physics: Conference Series, 1634(1), 012032 (6pp).
[15]
Yang, X., Wang, Y., & Laganiere, R. . (2020). A scale-aware YOLO model for pedestrian detection. International Symposium on Visual Computing (ISVC) 2020.
[16]
Huang, Z., Wang, J., Fu, X., Yu, T., & Wang, R. . (2020). Dc-spp-yolo: dense connection and spatial pyramid pooling based yolo for object detection. Information Sciences, 522.
[17]
Li, J., Liao, S., Jiang, H., & Shao, L. . (2020). Box Guided Convolution for Pedestrian Detection. MM '20: The 28th ACM International Conference on Multimedia. ACM.
[18]
Guo, Wei; Li, Weihong; Gong, Weiguo; Cui, Jinkai (2020). Extended Feature Pyramid Network with Adaptive Scale Training Strategy and Anchors for Object Detection in Aerial Images. Remote Sensing, 12(5), 784–.
[19]
Deng, C., Wang, M., Liu, L., & Liu, Y. J. a. e.-p. (2020). Extended Feature Pyramid Network for Small Object Detection. arXiv:2003.07021.
[20]
LIU L, ZHENG Y, FU D M.(2020). Occluded Pedestrian Detection Algorithm Based on Improved YOLOv3.Pattern Recognition and Artificial Intelligence, 2020, 33( 6) : 568−574.
[21]
YANG Yaru, DENG Hongxia, WANG Zhe, (2020). Deep network pedestrian detection guided by shallow feature fusion.Computer Engineering and Applications, 2020, 56(2): 196-200.
Recommendations
Real-time pedestrian detection via hierarchical convolutional feature
With the development of pedestrian detection technologies, existing methods can not simultaneously satisfy high quality detection and fast calculation for practical applications. Therefore, the goal of our research is to balance of pedestrian detection ...
A Channel-Cascading Pedestrian Detection Network for Small-Size Pedestrians
Intelligence Science and Big Data EngineeringAbstractAt present, there are several new challenges for multi-scale pedestrian detection in wide-angle field of view, especially small-size pedestrians. So the problem is how we can detect pedestrians efficiently and accurately with limited resources in ...
Multi-scale Pedestrian Detection Based on Receptive Field Matching
ICGSP '21: Proceedings of the 5th International Conference on Graphics and Signal ProcessingPedestrian detection is a hot topic in both academia and industry. However, the pedestrian in the image presents different scales due to the different distance from the fixed cameras. Thus, how to detect pedestrians of different scales has become an ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2021
660 pages
Copyright © 2021 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 07 December 2021
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CSAE 2021
CSAE 2021: The 5th International Conference on Computer Science and Application Engineering
October 19 - 21, 2021
Sanya, China
Acceptance Rates
Overall Acceptance Rate 368 of 770 submissions, 48%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 78Total Downloads
- Downloads (Last 12 months)3
- Downloads (Last 6 weeks)0
Reflects downloads up to 28 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format