Cited time in webofscience Cited time in scopus

Integrated position and motion tracking method for online multi-vehicle tracking-by-detection

Title
Integrated position and motion tracking method for online multi-vehicle tracking-by-detection
Author(s)
Lim, Young-ChulLee, MinhoLee, Chung-HeeKwon, SoonLee, Jong-Hun
Issued Date
2011-07
Citation
Optical Engineering, v.50, no.7
Type
Article
Author Keywords
multi-vehicle trackingmotion trackingposition trackingtracking-by-detectiondata association
Keywords
Alarm SystemsAlgorithmsData AssociationData Association AlgorithmsDetection AlgorithmErrorsFalse DetectionsFalse NegativesFalse PositiveMotion TrackingMotion Tracking MethodsMulti-Vehicle TrackingMulti-VehiclesOn-Line ApplicationsPosition TrackingPROBABILISTIC DATA ASSOCIATIONReal Road EnvironmentsRoads and StreetsSignal DetectionTrack InitializationTracking-By-DetectionTracking (Position)Tracking MethodVehicle DetectionVehicles
ISSN
0091-3286
Abstract
In this paper, we present a multi-vehicle tracking method that uses integrated position and motion tracking methods to minimize missing and false detection. No existing state-of-the-art vehicle detection method can detect all the vehicles on the road and remove all false positive alarms. Therefore, a robust tracking-by-detection algorithm is necessary to minimize the number of false positive and false negative alarms. In multi-vehicle tracking, there are three types of errors such as false negative alarms, false positive alarms, and track identity switches. False negative and false positive alarms are caused by an imperfect detection algorithm, while track identity switches are caused by measurement-to-track pair confusion. Our tracking-by-detection method minimizes these errors while processing in real-time for online application. Sparse false positive alarms are reduced by a track initialization procedure. Motion tracking with selected features can minimize false negative alarms. A data association algorithm with complementary global and local distance prevents tracks from connecting measurements incorrectly. The proposed method was evaluated and verified in challenging, real road environments. The experimental results demonstrate that our multi-vehicle tracking method remarkably reduces false positive and false negative alarms and performs better than previous methods. © 2011 Society of Photo-Optical Instrumentation Engineers (SPIE).
URI
http://hdl.handle.net/20.500.11750/3444
DOI
10.1117/1.3595429
Publisher
SPIE
Related Researcher
  • 임영철 Lim, Young Chul
  • Research Interests Deep learning;딥러닝; object detection;객체검출; re-identification;재식별; multi-object tracking;다중객체추적; multi-camera video analysis;다중카메라영상분석
Files in This Item:

There are no files associated with this item.

Appears in Collections:
Division of AI, Big data and Block chain 1. Journal Articles
Division of Automotive Technology 1. Journal Articles

qrcode

  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE