跨域监控场景下车辆属性分类的基准测试集
A Benchmark for Vehicle Attribute Classification in Cross-Domain Surveillance Scenarios
- Federal University of Paraná（巴拉那联邦大学）
- Pontifical Catholic University of Paraná（巴拉那天主教大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出UVIB基准测试集，评估跨域监控场景下车辆属性分类的三项任务，测试四类模型后发现域偏移影响更大，凸显需开发评估操作鲁棒性的基准测试集。
AI中文摘要：
车辆属性分析是智能交通系统（ITS）的关键组成部分，可支撑车辆识别、交通监控和法医调查等应用。然而，在受控条件下训练的模型，会因视角变化、遮挡、光照和传感器特性等因素，在真实监控场景中性能下降。本文提出了无约束车辆识别基准测试集（UVIB），用于评估三项车辆分析任务：前后朝向、遮挡对车辆品牌型号识别（VMMR）的适用性，以及颜色清晰度。该基准测试集包含来自7个巴西公开数据集的84835张车辆图像，分为监控和通用采集域，且具有原始来源中未联合提供的统一二元标注。本文评估了四种代表性架构：EfficientNetV2-S、ResNet-50、ViT/B-16和YOLO11s-cls，采用混合域、跨域和跨数据集协议。结果表明，域偏移比架构选择的影响更大，在跨域设置中性能大幅下降，尤其在VMMR适用性和颜色清晰度任务上；朝向任务的泛化更可靠，而VMMR适用性仍受类别不平衡和模糊遮挡的影响，颜色清晰度则对光照和传感器模态高度敏感。这些发现凸显了开发基准测试集和评估协议的必要性，需明确测量超出标准域内准确率的操作鲁棒性。所提出的基准测试集可通过该URL公开获取。
英文摘要：
Vehicle attribute analysis is a key component of Intelligent Transportation Systems (ITS), supporting applications such as vehicle identification, traffic monitoring, and forensic investigation. However, models trained under controlled conditions often degrade in real surveillance scenarios due to changes in viewpoint, occlusion, illumination, and sensor characteristics. This paper introduces Unconstrained Vehicle Identification Benchmark (UVIB), a benchmark for evaluating three operational vehicle-analysis tasks: front/rear orientation, occlusion-related suitability for Vehicle Make and Model Recognition (VMMR), and color clarity. The benchmark contains 84,835 vehicle images from seven public Brazilian datasets, grouped into surveillance and general acquisition domains, with unified binary annotations that were not jointly available in the original sources. Four representative architectures, EfficientNetV2-S, ResNet-50, ViT/B-16, and YOLO11s-cls, are evaluated under mixed-domain, cross-domain, and cross-dataset protocols. The results show that domain shift has a stronger impact than architecture choice, with substantial degradation in cross-domain settings, especially for VMMR suitability and color clarity. While orientation generalizes more reliably, VMMR suitability remains affected by class imbalance and ambiguous occlusions, and color clarity is highly sensitive to illumination and sensor modality. These findings highlight the need for benchmarks and evaluation protocols that explicitly measure operational robustness beyond standard in-domain accuracy. The proposed benchmark is publicly available at https://github.com/UFPR-IPASP-PR/uvib-vehicle-attributes/.
