Research on Fast Recognition of Vulnerable Traffic Participants in Intelligent Connected Vehicles on Edge Computing

Gu, Musong1,2; Lyu, Jingjing1; Li, Zhongwen1; Yan, Zihan3; Fan, Wenjie1

2022-09-01

10.1142/S0218126623500469

JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS   影响因子和分区

0218-1266

1793-6454

Real-time and fast recognition of all kinds of traffic participants in intelligent driving has always been a major difficulty in the research of internet of vehicles. With the advent of edge computing, we try to deploy an image recognition algorithm directly to the intelligent vehicles. However, the original image recognition algorithm is difficult to be directly deployed on the vehicles due to limited edge device resources. Based on this, a fast recognition model of vulnerable traffic participants based on depthwise separable convolutional neural network (DSCYOLO) is proposed in this paper. The algorithm can significantly reduce the convolutional parameter quantity and computing load, making it suitable for deployment on the vehicle-mounted edge embedded devices. In order to validate the effectiveness of the proposed method, its simulation results are compared with the main target detection models Faster R-CNN, SSD and YOLOv3. The results show that the recognition time of the proposed model is reduced by 80.28%, 66.80% and 86.74%, respectively, on the basis of a relatively high recognition precision. The model can realize real-time detection and fast recognition of vulnerable traffic participants, so as to avoid a large number of traffic accidents. It has significant social and economic benefits.

Intelligent connected vehicle YOLOv3 edge computing real-time traffic warning

SCI ; EI

英语

其他

Open Project Program of the State Key Lab of CAD&CG Zhejiang University[A2117] ; Key Laboratory of Pattern Recognition and Intelligent Information Processing, Institutions of Higher Education of Sichuan Province[MSSB-2021-06] ; Science & Technology Bureau of Chengdu[2020-YF09-00005-SN] ; Talent Cultivation Quality and Teaching Reform Project of Chengdu University in 2021-2023[cdjgb2022051] ; Second Batch of Industry-University Cooperation, Project of Sichuan Research Center for Application and Development of Educational Informatization in 2021[JYXX21-004] ; Project of Urban and Rural Education Development Research Center in 2021[TCCXJY-2021-E46]

Computer Science ; Engineering

Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic

WOS:000852447300004

WORLD SCIENTIFIC PUBL CO PTE LTD

20230713583178

Convolution ; Edge computing ; Edge detection ; Image recognition ; Neural networks

Information Theory and Signal Processing:716.1 ; Digital Computers and Systems:722.4

ENGINEERING

Web of Science

1.Chengdu Univ, Coll Comp Sci, Chengdu, Peoples R China
2.Chengdu Univ, Inst Higher Educ Sichuan Prov, Key Lab Pattern Recognit & Intelligent Informat P, Chengdu, Peoples R China
3.Southern Univ Sci & Technol, Dept Math, Shenzhen, Peoples R China

Gu, Musong,Lyu, Jingjing,Li, Zhongwen,et al. Research on Fast Recognition of Vulnerable Traffic Participants in Intelligent Connected Vehicles on Edge Computing[J]. JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS,2022,32(03).

Gu, Musong,Lyu, Jingjing,Li, Zhongwen,Yan, Zihan,&Fan, Wenjie.(2022).Research on Fast Recognition of Vulnerable Traffic Participants in Intelligent Connected Vehicles on Edge Computing.JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS,32(03).

Gu, Musong,et al."Research on Fast Recognition of Vulnerable Traffic Participants in Intelligent Connected Vehicles on Edge Computing".JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS 32.03(2022).