DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objects
Peng Wang, Yongcai Wang, Deying Li

TL;DR
DroneMOT introduces novel attention and motion-based methods to improve multi-object tracking from drones, effectively handling small, blurred, and occluded objects amidst drone and object movements.
Contribution
The paper presents a dual-domain attention module and motion-driven association scheme specifically designed for drone-based multi-object tracking, addressing unique challenges of dynamic aerial environments.
Findings
Significant performance improvements on VisDrone2019-MOT and UAVDT datasets.
Enhanced detection and feature embedding for small, blurred, and occluded objects.
Robust object association considering simultaneous drone and object movements.
Abstract
Multi-object tracking (MOT) on static platforms, such as by surveillance cameras, has achieved significant progress, with various paradigms providing attractive performances. However, the effectiveness of traditional MOT methods is significantly reduced when it comes to dynamic platforms like drones. This decrease is attributed to the distinctive challenges in the MOT-on-drone scenario: (1) objects are generally small in the image plane, blurred, and frequently occluded, making them challenging to detect and recognize; (2) drones move and see objects from different angles, causing the unreliability of the predicted positions and feature embeddings of the objects. This paper proposes DroneMOT, which firstly proposes a Dual-domain Integrated Attention (DIA) module that considers the fast movements of drones to enhance the drone-based object detection and feature embedding for small-sized,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsUAV Applications and Optimization · Video Surveillance and Tracking Methods · Distributed Control Multi-Agent Systems
MethodsSoftmax · Attention Is All You Need
