Electronic Science and Technology ›› 2019, Vol. 32 ›› Issue (11): 23-27.doi: 10.16180/j.cnki.issn1007-7820.2019.11.005

Previous Articles     Next Articles

AGV Multi-target Tracking Under Smart Factory

YANG Biao,LIU Xiang,TANG Xian,CHEN Junting   

  1. School of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China
  • Received:2018-11-15 Online:2019-11-15 Published:2019-11-15
  • Supported by:
    National Key Research and Development Program of China(2016YFC0801304);Shanghai Science and Technology Commission Local Capacity Building Project(15590501300)

Abstract:

Aiming at identifying, occluding and losing similar objects in AGV tracking under logistics warehouse, the study proposed a multi-target tracking method which combined background modeling with Kalman filter. Because logistics AGV has the same color, the proposed method tracked a specific logistics car with the help of Camshift's color tracking feature. At the same time, Kalman filter was used to add motion information and make use of dynamic information of target. To solve the problems of AGV recognition, occlusion and loss under the same color, the influence of noise was removed. Experiment showed that this algorithm could distinguish similar AGV cars and track them in real time.

Key words: AGV, background modeling, object detection, target tracking, Camshift algorithm, Kalman filtering

CLC Number: 

  • TP751