Kim Bongjun, Kim Sunkyu, Park Seokwon, Jeong Junho
Department of Computer Science and Engineering, Dongguk University, Seoul 04620, Republic of Korea.
Sensors (Basel). 2025 Mar 14;25(6):1819. doi: 10.3390/s25061819.
In aerial surveillance using drones, person re-identification (ReID) is crucial for public safety. However, low resolutions in drone footage often leads to a significant drop in ReID performance of subjects. To investigate this issue, rather than relying solely on real-world datasets, we employed a synthetic dataset that systematically captures variations in drone altitude and distance. We also utilized an eXplainable Artificial Intelligence (XAI) framework to analyze how low resolutions affect ReID. Based on our findings, we propose a method that improves ReID accuracy by filtering out attributes that are not robust in low-resolution environments and retaining only those features that remain reliable. Experiments on the Market1501 dataset show a 6.59% percentage point improvement in accuracy at a 16% resolution scale. We further discuss the effectiveness of our approach in drone-based aerial surveillance systems under Fog/Edge Computing paradigms.
在使用无人机进行空中监视时，行人重识别（ReID）对公共安全至关重要。然而，无人机拍摄的低分辨率图像往往会导致被拍摄对象的ReID性能大幅下降。为了研究这个问题，我们没有仅仅依赖真实世界的数据集，而是使用了一个合成数据集，该数据集系统地捕捉了无人机高度和距离的变化。我们还利用了可解释人工智能（XAI）框架来分析低分辨率如何影响ReID。基于我们的发现，我们提出了一种方法，通过过滤掉在低分辨率环境中不可靠的属性，只保留那些仍然可靠的特征，从而提高ReID的准确性。在Market1501数据集上的实验表明，在16%分辨率尺度下，准确率提高了6.59个百分点。我们进一步讨论了我们的方法在雾计算/边缘计算范式下基于无人机的空中监视系统中的有效性。
