Skip to main navigation Skip to search Skip to main content

Multi-target vehicle detection and tracking based on video

  • Northeastern University China

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In order to realize the vehicle tracking on the traffic road, a multi-target vehicle detecting and tracking method K-YOLOv3 based on video tracking is proposed in combination with experiments. The algorithm is composed of vehicle detection, tracking, trajectory generation part. The focus of this paper is vehicle detection and tracking. K-YOLOv3 is an improvement on YOLOv3, which is combined with KCF to detect and track the target vehicle at the same time, and then the vehicle trajectory set is established to form the vehicle trajectory. Experimental results show that the detection accuracy of k-yolov3 algorithm is slightly higher than YOLOv3, while the detection speed is much faster than YOLOv3.

Original languageEnglish
Title of host publicationProceedings of the 32nd Chinese Control and Decision Conference, CCDC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3317-3322
Number of pages6
ISBN (Electronic)9781728158549
DOIs
StatePublished - Aug 2020
Externally publishedYes
Event32nd Chinese Control and Decision Conference, CCDC 2020 - Hefei, China
Duration: 22 Aug 202024 Aug 2020

Publication series

NameProceedings of the 32nd Chinese Control and Decision Conference, CCDC 2020

Conference

Conference32nd Chinese Control and Decision Conference, CCDC 2020
Country/TerritoryChina
CityHefei
Period22/08/2024/08/20

Keywords

  • KCF
  • Object detection
  • Object recognition
  • YOLOv3

Fingerprint

Dive into the research topics of 'Multi-target vehicle detection and tracking based on video'. Together they form a unique fingerprint.

Cite this