DeepAI
Log In Sign Up

Multi-object Tracking with Tracked Object Bounding Box Association

05/17/2021
by   Nanyang Yang, et al.
0

The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint detection and tracking method still suffers from high identity switches due to the inferior association method. To reduce the high number of identity switches and improve the tracking accuracy, in this paper, we propose to incorporate a simple tracked object bounding box and overlapping prediction based on the current frame onto the CenterTrack algorithm. Specifically, we propose an Intersection over Union (IOU) distance cost matrix in the association step instead of simple point displacement distance. We evaluate our proposed tracker on the MOT17 test dataset, showing that our proposed method can reduce identity switches significantly by 22.6 improvement of 1.5 same tracklet lifetime. The source code is released at https://github.com/Nanyangny/CenterTrack-IOU.

READ FULL TEXT
11/02/2021

PolyTrack: Tracking with Bounding Polygons

In this paper, we present a novel method called PolyTrack for fast multi...
03/08/2022

SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking

Joint detection and embedding (JDE) based methods usually estimate bound...
09/27/2019

Towards Real-Time Multi-Object Tracking

Modern multiple object tracking (MOT) systems usually follow the trackin...
04/22/2022

Improving tracking with a tracklet associator

Multiple object tracking (MOT) is a task in computer vision that aims to...
10/13/2021

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Multi-object tracking (MOT) aims at estimating bounding boxes and identi...
11/26/2021

Immortal Tracker: Tracklet Never Dies

Previous online 3D Multi-Object Tracking(3DMOT) methods terminate a trac...