Recognition Method for Complex Environment of Autopilot Vehicle Based on Monocular Vision

One of the major application scenarios of military and police unmanned vehicles is to support and carry equipment to reduce the load of personnel. Therefore, personnel identification technology in a complex off-road environment is one of the key technologies of military unmanned vehicles. The effect of laser radar identification is relatively good, but the method of monocular vision can greatly reduce the system cost and facilitate the popularization and application of equipment. In order to solve the problem of personnel identification under monocular vision perception, especially the problem of background interference in complex environment, this paper designs an improved YOLOV3 deep learning network architecture based on monocular vision information, and proposes a YOLOv3 deep learning network architecture with an improved residual module. Based on the original YOLOv3 network RB output, a global pooling layer, two full connection layers, Sigmoid activation function layer, and multiplication layer are added. Through the verification of real vehicles in an off-road environment, the results show that the designed personnel recognition algorithm based on monocular vision can accurately recognize personnel targets in a complex environment, and the recognition rate in a complex environment exceeds 95%.

• Record URL:
  • https://doi.org/10.1061/9780784483053.053
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784483053
• Supplemental Notes:
  • © 2020 American Society of Civil Engineers.
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Chen, Wanru
  • Fan, Jingjing
  • Liu, Yingzhe
  • Guo, Jianying
• Conference:
  • 20th COTA International Conference of Transportation Professionals
  • Location: Xi’an , China
  • Date: 2020-8-14 to 2020-8-16
• Publication Date: 2020

Language

• English

Media Info

• Media Type: Web
• Pagination: pp 620-626
• Monograph Title: CICTP 2020: Transportation Evolution Impacting Future Mobility

Subject/Index Terms

• TRT Terms: All terrain vehicles; Autonomous vehicles; Computer vision; Identification systems; Machine learning; Military vehicles; Police vehicles
• Identifier Terms: YOLO
• Subject Areas: Data and Information Technology; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01767352
• Record Type: Publication
• ISBN: 9780784483053
• Files: TRIS, ASCE
• Created Date: Mar 22 2021 10:34AM