Simple Online and Realtime Tracking

Code

• github.com/abewley/sort
  OfficialIn papertf★ 0
• github.com/open-mmlab/mmtracking
  pytorch★ 3,865
• github.com/chonyy/AI-basketball-analysis
  tf★ 1,229
• github.com/noahcao/OC_SORT
  pytorch★ 1,047
• github.com/chonyy/ML-auto-baseball-pitching-overlay
  none★ 306
• github.com/linghu8812/tensorrt_tracker
  pytorch★ 108
• github.com/LdDl/odam
  none★ 37
• github.com/Nanyangny/CenterTrack-IOU
  pytorch★ 36
• github.com/casys-kaist/cova
  tf★ 18
• github.com/BingfengYan/DS_OCSORT
  pytorch★ 13

Abstract

This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is identified as a key factor influencing tracking performance, where changing the detector can improve tracking by up to 18.9%. Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers. Furthermore, due to the simplicity of our tracking method, the tracker updates at a rate of 260 Hz which is over 20x faster than other state-of-the-art trackers.

Tasks

Benchmark Results

Reproductions