Benchmark:

MOT20 | MOT17 | MOT16 |

Short name:

FastTracker

Detector:

Public

Description:

Conventional multi-object tracking (MOT) systems
are predominantly designed for pedestrian tracking and often
exhibit limited generalization to other object categories. This
paper presents a generalized tracking framework capable of
handling multiple object types, with a particular emphasis on
vehicle tracking in complex traffic scenes. The proposed method
incorporates two key components: (1) an occlusion-aware re-
identification mechanism that enhances identity preservation for
heavily occluded objects, and (2) a road-structure-aware tracklet
refinement strategy that utilizes semantic scene priors—such as
lane directions, crosswalks, and road boundaries—to improve
trajectory continuity and accuracy. In addition, we introduce
a new benchmark dataset comprising diverse vehicle classes
with frame-level tracking annotations, specifically curated to
support evaluation of vehicle-focused tracking methods. Extensive
experimental results demonstrate that the proposed approach
achieves robust performance on both the newly introduced dataset
and several public benchmarks, highlighting its effectiveness in
general-purpose object tracking beyond the pedestrian domain.

Reference:

H. Hashempoor, Y. Hwang. Pintel: FastTracker-- Real Time and Accurate Visual Tracking. In , 2025.

Last submitted:

August 14, 2025 (5 months ago)

Published:

August 14, 2025 at 06:53:52 CET

Submissions:

3

Project page / code:

https://github.com/Hamidreza-Hashempoor/FastTracker

Open source:

Yes

Hardware:

2.1 GHZ, 8 Core

Runtime:

89.6 Hz

Benchmark performance:

Detailed performance:

Raw data:

download