Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones

TL;DR

This paper presents two approaches to improve multi-object detection, tracking, and re-identification for disaster response drones, achieving higher accuracy and lower error rates through multi-camera systems and advanced detectors.

Contribution

Introduces two simple yet effective methods combining multi-camera systems and high-performance detectors to enhance object detection and tracking in drone-based disaster response.

Findings

First approach achieved 85.71% accuracy, slightly better than baseline.

Error reduction of 27.4% in L2-norm error with proposed model.

Second approach with DeepSORT outperformed FairMOT in recall, despite processing fewer frames.

Abstract

We aim to detect and identify multiple objects using multiple cameras and computer vision for disaster response drones. The major challenges are taming detection errors, resolving ID switching and fragmentation, adapting to multi-scale features and multiple views with global camera motion. Two simple approaches are proposed to solve these issues. One is a fast multi-camera system that added a tracklet association, and the other is incorporating a high-performance detector and tracker to resolve restrictions. (...) The accuracy of our first approach (85.71%) is slightly improved compared to our baseline, FairMOT (85.44%) in the validation dataset. In the final results calculated based on L2-norm error, the baseline was 48.1, while the proposed model combination was 34.9, which is a great reduction of error by a margin of 27.4%. In the second approach, although DeepSORT only processes a quarter of all frames due to hardware and time limitations, our model with DeepSORT (42.9%) outperforms FairMOT (71.4%) in terms of recall. Both of our models ranked second and third place in the `AI Grand Challenge' organized by the Korean Ministry of Science and ICT in 2020 and 2021, respectively. The source codes are publicly available at these URLs (github.com/mlvlab/drone_ai_challenge, github.com/mlvlab/Drone_Task1, github.com/mlvlab/Rony2_task3, github.com/mlvlab/Drone_task4).