Object Detection and Danger Warning of Transmission Channel Based on Improved YOLO Network

被引：0

作者：

Ning, Wenbo ^{[1
]}

Mu, Xiaochen ^{[1
]}

Zhang, Chong ^{[1
]}

Dai, Taotao ^{[1
]}

Qian, Sheng ^{[1
]}

Sun, Xiaotong ^{[1
]}

机构：

[1] State Grid Shandong Dongying Power Supply Co, Dongying, Peoples R China

来源：

PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020) | 2020年

关键词：

Object detection; transmission channel; YOLOv3-MobileNet; danger warning; IoU-Kmeans;

D O I：

10.1109/itnec48623.2020.9085177

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 view of the wide monitoring area of the transmission channel, the proportion of object in the captured pictures is small, especially the problem of early warning of targets in inspection images under complex backgrounds such as mutual occlusion, forests, mountains and rivers and multiple interference factors. A YOLOv3-MobileNet algorithm for power transmission channel danger warning is proposed. According to the characteristics of the transmission channel image, the number of network layers is increased while maintaining a small amount of calculation, and the feature mapping module is enriched to provide more accurate semantic information for the prediction layer. An IoU-Kmeans algorithm is proposed, which improves the predicted position of the target. Experimental results show that the optimized algorithm's detection accuracy (mAP) is 90% Compared with SSD and YOLOv3 object detection algorithms, the detection accuracy of the algorithm is improved by 75% and 3.5%

引用

页码：1089 / 1093

页数：5

共 16 条

[1] CHEN Liangqin, 2018, POWER SYSTEMS BIG DA, V21, P1
[2] Deep Learning: Methods and Applications
Deng, Li
Yu, Dong
[J]. FOUNDATIONS AND TRENDS IN SIGNAL PROCESSING, 2013, 7 (3-4): : I - 387
[3] Di WANG, 2016, J N CHINA ELECT POWE, V43, P66
[4] End-to-End Training of Object Class Detectors for Mean Average Precision
Henderson, Paul
Ferrari, Vittorio
[J]. COMPUTER VISION - ACCV 2016, PT V, 2017, 10115 : 198 - 213
[5] Jiao S., 2016, SCI TECHNOLOGY ENG, V44, P1
[6] ImageNet Classification with Deep Convolutional Neural Networks
Krizhevsky, Alex
Sutskever, Ilya
Hinton, Geoffrey E.
[J]. COMMUNICATIONS OF THE ACM, 2017, 60 (06) : 84 - 90
[7] LI Peng, 2019, GUANGDONG ELECT POWE, V32, P49
[8] Ma S. Y., 2010, Electric Power Construction, V31, P14
[9] Redmon J, 2018, Arxiv, DOI [arXiv:1804.02767, DOI 10.1109/CVPR.2017.690]
[10] You Only Look Once: Unified, Real-Time Object Detection
Redmon, Joseph
Divvala, Santosh
Girshick, Ross
Farhadi, Ali
[J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 779 - 788

← 1 2 →