SP-YOLO-Lite: A Lightweight Violation Detection Algorithm Based on SP Attention Mechanism

被引:4
作者
Huang, Zhihao [1 ]
Wu, Jiajun [1 ]
Su, Lumei [1 ,2 ]
Xie, Yitao [1 ]
Li, Tianyou [1 ]
Huang, Xinyu [3 ]
机构
[1] Xiamen Univ Technol, Sch Elect Engn & Automat, Xiamen 361024, Peoples R China
[2] Xiamen Key Lab Frontier Elect Power Equipment & In, Xiamen 361024, Peoples R China
[3] Xiamen Ocean Vocat Coll, Sch Informat Engn, Xiamen 361100, Peoples R China
基金
中国国家自然科学基金;
关键词
violation detection; deep learning; lightweight object detection algorithm; attention mechanism;
D O I
10.3390/electronics12143176
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In the operation site of power grid construction, it is crucial to comprehensively and efficiently detect violations of regulations for the personal safety of the workers with a safety monitoring system based on object detection technology. However, common general-purpose object detection algorithms are difficult to deploy on low-computational-power embedded platforms situated at the edge due to their high model complexity. These algorithms suffer from drawbacks such as low operational efficiency, slow detection speed, and high energy consumption. To address this issue, a lightweight violation detection algorithm based on the SP (Segmentation-and-Product) attention mechanism, named SP-YOLO-Lite, is proposed to improve the YOLOv5s detection algorithm and achieve low-cost deployment and efficient operation of object detection algorithms on low-computational-power monitoring platforms. First, to address the issue of excessive complexity in backbone networks built with conventional convolutional modules, a Lightweight Convolutional Block was employed to construct the backbone network, significantly reducing computational and parameter costs while maintaining high detection model accuracy. Second, in response to the problem of existing attention mechanisms overlooking spatial local information, we introduced an image segmentation operation and proposed a novel attention mechanism called Segmentation-and-Product (SP) attention. It enables the model to effectively capture local informative features of the image, thereby enhancing model accuracy. Furthermore, a Neck network that is both lightweight and feature-rich is proposed by introducing Depthwise Separable Convolution and Segmentation-and-Product attention module to Path Aggregation Network, thus addressing the issue of high computation and parameter volume in the Neck network of YOLOv5s. Experimental results show that compared with the baseline network YOLOv5s, the proposed SP-YOLO-Lite model reduces the computation and parameter volume by approximately 70%, achieving similar detection accuracy on both the VOC dataset and our self-built SMPC dataset.
引用
收藏
页数:21
相关论文
共 31 条
[21]   You Only Look Once: Unified, Real-Time Object Detection [J].
Redmon, Joseph ;
Divvala, Santosh ;
Girshick, Ross ;
Farhadi, Ali .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :779-788
[22]   Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization [J].
Selvaraju, Ramprasaath R. ;
Cogswell, Michael ;
Das, Abhishek ;
Vedantam, Ramakrishna ;
Parikh, Devi ;
Batra, Dhruv .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :618-626
[23]   Traffic Sign Instances Segmentation Using Aliased Residual Structure and Adaptive Focus Localizer [J].
Shi, Wenjun ;
Shi, Yingjun ;
Zhu, Dongchen ;
Zhang, Xiaolin ;
Li, Jiamao .
2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, :3676-3685
[24]   A Deep Learning Framework Performance Evaluation to Use YOLO in Nvidia Jetson Platform [J].
Shin, Dong-Jin ;
Kim, Jeong-Joon .
APPLIED SCIENCES-BASEL, 2022, 12 (08)
[25]   Safety Helmet Wearing Detection Model Based on Improved YOLO-M [J].
Wang, Lili ;
Zhang, Xinjie ;
Yang, Hailu .
IEEE ACCESS, 2023, 11 :26247-26257
[26]  
Wang lingmin, 2022, Computer Engineering and Applications, P303, DOI 10.3778/j.issn.1002-8331.2112-0242
[27]   ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks [J].
Wang, Qilong ;
Wu, Banggu ;
Zhu, Pengfei ;
Li, Peihua ;
Zuo, Wangmeng ;
Hu, Qinghua .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :11531-11539
[28]   CBAM: Convolutional Block Attention Module [J].
Woo, Sanghyun ;
Park, Jongchan ;
Lee, Joon-Young ;
Kweon, In So .
COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :3-19
[29]   Efficient Video Fire Detection Exploiting Motion-Flicker-Based Dynamic Features and Deep Static Features [J].
Xie, Yakun ;
Zhu, Jun ;
Cao, Yungang ;
Zhang, Yunhao ;
Feng, Dejun ;
Zhang, Yuchun ;
Chen, Min .
IEEE ACCESS, 2020, 8 :81904-81917
[30]   Workshop Safety Helmet Wearing Detection Model Based on SCM-YOLO [J].
Zhang, Bin ;
Sun, Chuan-Feng ;
Fang, Shu-Qi ;
Zhao, Ye-Hai ;
Su, Song .
SENSORS, 2022, 22 (17)