论文标题
改善对象检测，多对象跟踪和重新识别灾害响应无人机
Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones
论文作者
论文摘要
我们旨在使用多个摄像头和计算机视觉来检测和识别多个对象，以造成灾难响应无人机。主要的挑战是驯服检测错误，解决ID切换和碎片化，适应多尺度功能以及具有全球摄像机运动的多个视图。提出了两种简单的方法来解决这些问题。一个是一个快速的多摄像机系统，添加了轨迹关联，另一个正在融合高性能检测器和跟踪器以解决限制。 （...）与我们的基线相比，我们的第一种方法的准确性（85.71％）在验证数据集中的Fairmot（85.44％）略有提高。在基于L2-Norm误差计算的最终结果中，基线为48.1，而所提出的模型组合为34.9，这是误差的大幅减少27.4％。在第二种方法中，尽管由于硬件和时间限制，DeepSort仅处理所有帧的四分之一，但我们的DeepSort（42.9％）的模型在召回方面的表现（71.4％）都优于Fairmot（71.4％）。我们的两个模型分别在2020年和2021年分别由韩国科学和ICT组织的“ AI大挑战”中排名第二和第三。源代码可在这些URL上公开获得（github.com/mlvlab/drone_ai_ai_challenge，github.com/mlvlab/drone_task1，github.com/mlvlab/rony2_task3，github.com/mlvlab/drone_task4）。
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).
