Benchmarking UAV-based Vehicle Re-Identification under Simulated Weather Conditions
2026-07-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors looked at how well different computer programs can recognize the same vehicles in pictures taken from drones during bad weather like fog and rain. They created fake foggy and rainy versions of two vehicle image datasets to test these programs fairly. They found that rain makes it harder for the programs to correctly identify vehicles than fog does, and one method called AdaSP performed better in these tough conditions. Their work shows that current vehicle recognition methods struggle in bad weather and that future designs need to specifically handle weather effects.
UAVvehicle re-identificationadverse weatherfog simulationrain simulationdeep learningbenchmarkingmAPaerial imageryrobustness
Authors
Vu Minh Tran, Khang Nguyen
Abstract
UAV-based vehicle re-identification (ReID) has emerged as a promising technique for traffic surveillance, urban monitoring, and public-safety applications thanks to the flexible viewpoints and wide-area coverage provided by unmanned aerial vehicles. However, despite recent progress on UAV-based vehicle ReID benchmarks, the robustness of existing methods under adverse weather remains insufficiently studied. This is important because weather degradation can significantly affect the fine-grained appearance cues required for reliable vehicle matching in aerial imagery, especially under small object scale, viewpoint variation, and complex backgrounds. In this paper, we present a controlled comparative study of three representative recent vehicle ReID methods, namely CLIP-ReID, MSINet, and AdaSP, on two UAV-based benchmarks, VRU and UAV-VeID. To ensure consistent robustness evaluation, we generate synthetic foggy and rainy variants of both datasets using an analytical weather-effect pipeline while preserving the original identities and data splits. All methods are then trained and evaluated under matched clean, foggy, and rainy conditions. Experimental results show that adverse weather consistently degrades retrieval performance across both datasets, with rain causing larger drops than fog in nearly all settings. Among the evaluated methods, AdaSP demonstrates the strongest robustness, achieving 93.0% and 88.5% mAP on VRU-Large, and 88.7% and 76.2% mAP on UAV-VeID-Test under foggy and rainy conditions, respectively. Overall, our findings show that simulated adverse weather substantially increases the difficulty of UAV-based vehicle ReID, reveals clear robustness differences among recent methods, and highlights the need for weather-aware model design and evaluation protocols in future aerial ReID research. The code is released at https://github.com/tranminhvu945/Benchmarking-ReID.