Efficient Real-Time Dense Pedestrian Detector Based on Improved YOLOv7-tiny
Pages 42 - 48
Abstract
The state-of-the-art YOLO framework strikes an excellent balance between speed and accuracy and has become one of the most effective object detection algorithms. However, when performing dense pedestrian detection tasks, the network is computationally intensive, real-time is insufficient, and it is difficult to be applied to edge devices with weak computational power in practical use. Therefore, we propose a detection algorithm based on YOLOv7-tiny improvement. Based on the GhostNetv2 network, we use the parameter-free attention mechanism SimAM to construct the GhostNet-tiny structure and propose the C3Ghost-tiny module to be combined with the YOLO network in order to reduce the network computational parameters. We propose a new neck network structure to extract richer information with a bi-directional weighted pyramid structure and weighted connectivity of features at different scales. We also use WIoU as a coordinate loss function to improve the network's attention to small targets. We tested the effectiveness of the proposed method on the public dataset CrowdHuman, and the results show that our method can effectively reduce the network parameters while improving the accuracy. Notably, compared to the YOLOv7-tiny model, our model improves the accuracy value by 2.13%, reduces the amount of network parameters by 5.9%, reduces the amount of floating-point calculations by 60.3%, reduces the size of the network model file by 27.7%, and improves the detection speed by up to 46.64%.
References
[1]
Algamdi A M, Alghamdi H M. Instant Counting & Vehicle Detection during Hajj Using Drones[J]. Journal of Image and Graphics, 2023, 11(2).https://doi.org/ 10.18178/joig.11.2.204-211
[2]
Utaminingrum F, Prasetya R P, Rizdania R. Combining multiple feature for robust traffic sign detection[J]. Journal of Image and Graphics, 2020, 8(2): 53-58.https://doi.org/10.18178/joig.8.2.53-58
[3]
Liu Y, Geng L, Zhang W, Survey of video based small target detection[J]. Journal of Image and Graphics, 2021, 9(4): 122-134.https://doi.org/10.18178/joig.9.4.122-134
[4]
Lo E. Target detection algorithms in hyperspectral imaging based on discriminant analysis[J]. Journal of Image and Graphics, 2019, 7(4): 140-144.https://doi.org/10.18178/joig.7.4.140-144
[5]
Howard A G, Zhu M, Chen B, Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017.
[6]
Han K, Wang Y, Tian Q, Ghostnet: More features from cheap operations[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 1580-1589.
[7]
Mehta S, Rastegari M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer[J]. arXiv preprint arXiv:2110.02178, 2021.
[8]
Zhang X, Zhou X, Lin M, Shufflenet: An extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6848-6856.
[9]
Sun J, Ge H, Zhang Z. AS-YOLO: An improved YOLOv4 based on attention mechanism and SqueezeNet for person detection[C]//2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). IEEE, 2021, 5: 1451-1456. https://doi.org/10.1109/IAEAC50856.2021.9390855
[10]
Spiess F, Reinhart L, Strobel N, People detection with depth silhouettes and convolutional neural networks on a mobile robot[J]. Journal of Image and Graphics, 2021, 9(4): 135-139.https://doi.org/10.18178/joig.9.4.135-139
[11]
Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 7464-7475.
[12]
Liu S, Qi L, Qin H, Path aggregation network for instance segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8759-8768.
[13]
Huang S, He Y, Chen X. M-YOLO: a nighttime vehicle detection method combining mobilenet v2 and YOLO v3[C]//Journal of Physics: Conference Series. IOP Publishing, 2021, 1883(1): 012094. https://doi.org/10.1088/1742-6596/1883/1/012094
[14]
Kong L, Wang J, Zhao P. YOLO-G: A lightweight network model for improving the performance of military targets detection[J]. IEEE Access, 2022, 10: 55546-55564.https://doi.org/10.1109/ACCESS.2022.3177628.
[15]
Li Y, Lv C. Ss-yolo: An object detection algorithm based on YOLOv3 and shufflenet[C]//2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC). IEEE, 2020, 1: 769-772. https://doi.org/ 10.1109/ITNEC48623.2020.9085091
[16]
Huang S, Wang Y, Su P. A New Synthetical Method of Feature Enhancement and Detection for SAR Image Targets[J]. Journal of Image and Graphics, 2016, 4(2): 73-77.https://doi.org/10.18178/joig.4.2.73-77
[17]
Wang Q, Cheng M, Huang S, A deep learning approach incorporating YOLO v5 and attention mechanisms for field real-time detection of the invasive weed Solanum rostratum Dunal seedlings[J]. Computers and Electronics in Agriculture, 2022, 199: 107194. https://doi.org/10.1109/ACCESS.2022.3195901
[18]
Zhang M, Yin L. Solar cell surface defect detection based on improved YOLO v5[J]. IEEE Access, 2022, 10: 80804-80815. https://doi.org/10.1016/j.compag.2022.107194
[19]
Xue Y, Ju Z, Li Y, MAF-YOLO: Multi-modal attention fusion based YOLO for pedestrian detection[J]. Infrared Physics & Technology, 2021, 118: 103906. https://doi.org/10.1016/j.infrared.2021.103906
[20]
Kim M, Jeong J, Kim S. ECAP-YOLO: Efficient channel attention pyramid YOLO for small object detection in aerial image[J]. Remote Sensing, 2021, 13(23): 4851. https://doi.org/10.3390/rs13234851
[21]
Khan R, Raisa T F, Debnath R. An Efficient Contour Based Fine-Grained Algorithm for Multi Category Object Detection[J]. Journal of Image and Graphics, 2018, 6(2).https://doi.org/10.18178/joig.6.2.127-136
[22]
Rezatofighi H, Tsoi N, Gwak J Y, Generalized intersection over union: A metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 658-666.
[23]
Yang L, Zhang R Y, Li L, Simam: A simple, parameter-free attention module for convolutional neural networks[C]//International conference on machine learning. PMLR, 2021: 11863-11874.
[24]
Woo S, Park J, Lee J Y, Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 3-19.
[25]
Wang Q, Wu B, Zhu P, ECA-Net: Efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 11534-11542.
[26]
Tang Y, Han K, Guo J, GhostNetV2: Enhance Cheap Operation with Long-Range Attention[J]. arXiv preprint arXiv:2211.12905, 2022.
[27]
Zhu X, Lyu S, Wang X, TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 2778-2788.
[28]
Tan M, Pang R, Le Q V. Efficientdet: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10781-10790.
[29]
Zheng Z, Wang P, Liu W, Distance-IoU loss: Faster and better learning for bounding box regression[C]//Proceedings of the AAAI conference on artificial intelligence. 2020, 34(07): 12993-13000. https://doi.org/10.1609/aaai.v34i07.6999
[30]
Tong Z, Chen Y, Xu Z, Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism[J]. arXiv preprint arXiv:2301.10051, 2023.
[31]
Shao S, Zhao Z, Li B, Crowdhuman: A benchmark for detecting human in a crowd[J]. arXiv preprint arXiv:1805.00123, 2018.
[32]
Ma N, Zhang X, Zheng H T, Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 116-131.
[33]
Koonce B, Koonce B. MobileNetV3[J]. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, 2021: 125-144. https://doi.org/10.1007/978-1-4842-6168-2_11
[34]
Zhou D, Hou Q, Chen Y, Rethinking bottleneck structure for efficient mobile network design[C]//Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16. Springer International Publishing, 2020: 680-697.
[35]
Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks[C]//International conference on machine learning. PMLR, 2019: 6105-6114.
[36]
Mehta S, Rastegari M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer[J]. arXiv preprint arXiv:2110.02178, 2021.
Index Terms
- Efficient Real-Time Dense Pedestrian Detector Based on Improved YOLOv7-tiny
Index terms have been assigned to the content through auto-classification.
Recommendations
A mask-wearing detection algorithm based on improved YOLOv7
SPML '23: Proceedings of the 2023 6th International Conference on Signal Processing and Machine LearningAiming at the problem that the accuracy of mask-wearing detection is poor and it is difficult to deploy in low-cost equipment, this paper has proposed a mask-wearing detection algorithm based on improved YOLOv7. By adding an attention mechanism to the ...
Helmet detection algorithm based on improved yolov7
CSAI '23: Proceedings of the 2023 7th International Conference on Computer Science and Artificial IntelligenceIn order to solve the problems of low detection accuracy, wrong detection and missed detection in the traditional target detection algorithm in the safety helmet detection task, a safety helmet detection algorithm based on improved YOLOv7 is proposed. ...
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 ...
Comments
Information & Contributors
Information
Published In
November 2023
90 pages
ISBN:9798400708275
DOI:10.1145/3635118
Copyright © 2023 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 the author(s) 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: 05 February 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICAIP 2023
ICAIP 2023: 2023 7th International Conference on Advances in Image Processing
November 17 - 19, 2023
Beijing, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 25Total Downloads
- Downloads (Last 12 months)25
- Downloads (Last 6 weeks)0
Reflects downloads up to 01 Nov 2024
Other Metrics
Citations
View Options
Get Access
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