• Home
  • Search
  • Trajectory Prediction Enhancement Method for Multiple Object Tracking in Complex Scenes
  • Cite Icon1
  • https://doi.org/10.3724/sp.j.1089.2024.19851Copy DOI Icon

Trajectory Prediction Enhancement Method for Multiple Object Tracking in Complex Scenes

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Taking the short-track speed skating match of the Winter Olympics as an example, a multiple object tracking dataset applicable to the short-track speed skating scene is designed based on the athletes’ motion characteristics, such as small distinctions in target appearance, fast motion changes, and frequent mutual occlusion between targets. A multiple object tracking method based on trajectory prediction enhancement was proposed. First, the intersection-over-union of bounding boxes and the cosine distance of appearance features are calculated to jointly judge the similarity between detection and trajectories, solving the problem of similar target appearances. Secondly, the tracking trajectory’s global features and motion clues are used to recover the lost information of occluded targets, improving the re-association ability of interrupted trajectories. Finally, the detection prior is used to control the initialization of new trajectories, reducing the impact of noisy detection on identity exchange during trajectory tracking. Experimental results show that compared with the DeepSORT method, this method can guarantee stable tracking in the short-track speed skating scene and effectively reduce trajectory interruptions, with an increase of 21 percentage points in IDF1 and 14.3 percentage points in multiple object tracking accuracy (MOTA). This method ensures long-term stable tracking in short-track speed skating scenes with small differences in targets and fast motion changes. It has inspirational significance for the application of multiple object tracking in complex scenes.

Similar Papers
  • Research Article
  • Citations5

Multiple Traffic Target Tracking with Spatial-Temporal Affinity Network.

  • May 23, 2022
  • Computational intelligence and neuroscience
  • Yamin Sun +2
  • Conference Article

A 3D Multi-Object Tracking Based on Bounding Box and Depth

  • Jun 02, 2021
  • Chun-Hao Feng +1
  • Research Article
  • Citations43

Dynamic center point learning for multiple object tracking under Severe occlusions

  • Jun 25, 2024
  • Knowledge-Based Systems
  • Yaoqi Hu +7
  • Research Article

Simple Online Multiple Human Tracking based on LK Feature Tracker and Detection for Embedded Surveillance

  • Jun 01, 2017
  • Journal of Korea Multimedia Society
  • Quang Dao Vu +2
  • Research Article
  • Citations29

Yolo-3DMM for Simultaneous Multiple Object Detection and Tracking in Traffic Scenarios

  • Aug 01, 2024
  • IEEE Transactions on Intelligent Transportation Systems
  • Lichen Liu +6
  • Research Article
  • Citations4

Visually guided computer-mouse clicking interferes with multiple-object tracking (MOT)

  • Jan 01, 2022
  • Current Research in Behavioral Sciences
  • Mallory E Terry +1
  • PDF
  • Research Article
  • Citations4

Multi-Feature Single Target Robust Tracking Fused with Particle Filter.

  • Feb 27, 2022
  • Sensors
  • Caihong Liu +2
  • Research Article
  • Citations1

Survey on Multiple Objects Tracking in Video Analytics

  • Jan 17, 2019
  • International Journal of Computer Applications
  • Anjali Parihar +3
  • Research Article
  • Citations2

Multiple object detection and tracking with pseudo-particle filter

  • Mar 06, 2009
  • Frontiers of Electrical and Electronic Engineering in China
  • Baolong Guo +1
  • Research Article
  • Citations7

Real-Time Detection and Localization of Weeds in Dictamnus dasycarpus Fields for Laser-Based Weeding Control

  • Oct 13, 2024
  • Agronomy
  • Yanlei Xu +5
  • Conference Article
  • Citations19

Anomalous Driving Detection for Traffic Surveillance Video Analysis

  • Aug 24, 2021
  • Hang Shi +2
  • Research Article
  • Citations93

Visual tracking in complex scenes: A location fusion mechanism based on the combination of multiple visual cognition flows

  • Feb 04, 2023
  • Information Fusion
  • Shuai Liu +5
  • Research Article
  • Citations3

EnhanceCenter for improving point based tracking and rich feature representation

  • Mar 03, 2025
  • Scientific Reports
  • Hyun-Sung Yang +3
  • Research Article

Study on the correlation between multiple object tracking ability and eye- tracking characteristics in sports decision making among basketball players

  • Sep 08, 2025
  • PeerJ
  • Qifeng Gou +1
  • Conference Article
  • Citations10

Multiple object tracking using improved GMM-based motion segmentation

  • May 01, 2009
  • Saeid Fazli +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.