Natural language (NL) based vehicle retrieval is a task aiming to retrieve a vehicle that is most consistent with a given NL query from among all candidate vehicles. Because NL query can be easily obtained, such a task has a promising prospect in building an interactive intelligent traffic system (ITS). Current solutions mainly focus on extracting both text and image features and mapping them to the same latent space to compare the similarity. However, existing methods usually use dependency analysis or semantic role-labelling techniques to find keywords related to vehicle attributes. These techniques may require a lot of pre-processing and post-processing work, and also suffer from extracting the wrong keyword when the NL query is complex. To tackle these problems and simplify, we borrow the idea from named entity recognition (NER) and construct FindVehicle, a NER dataset in the traffic domain. It has 42.3k labelled NL descriptions of vehicle tracks, containing information such as the location, orientation, type and colour of the vehicle. FindVehicle also adopts both overlapping entities and fine-grained entities to meet further requirements. To verify its effectiveness, we propose a baseline NL-based vehicle retrieval model called VehicleFinder. Our experiment shows that by using text encoders pre-trained by FindVehicle, VehicleFinder achieves 87.7\% precision and 89.4\% recall when retrieving a target vehicle by text command on our homemade dataset based on UA-DETRAC. The time cost of VehicleFinder is 279.35 ms on one ARM v8.2 CPU and 93.72 ms on one RTX A4000 GPU, which is much faster than the Transformer-based system. The dataset is open-source via the link https://github.com/GuanRunwei/FindVehicle, and the implementation can be found via the link https://github.com/GuanRunwei/VehicleFinder-CTIM.

翻译：基于自然语言（NL）的车辆检索任务旨在从所有候选车辆中检索出与给定NL查询最一致的车辆。由于NL查询易于获取，该任务在构建交互式智能交通系统（ITS）方面具有广阔前景。现有解决方案主要聚焦于提取文本和图像特征，并将其映射到同一隐空间以比较相似性。然而，现有方法通常依赖依存分析或语义角色标注技术来定位与车辆属性相关的关键词。这些技术需要大量预处理和后处理工作，且在NL查询复杂时容易提取错误关键词。为解决上述问题并简化流程，我们借鉴命名实体识别（NER）的思想，构建了交通领域的NER数据集FindVehicle。该数据集包含42.3k条带标注的车辆轨迹NL描述，涵盖车辆位置、朝向、类型和颜色等信息。FindVehicle还采用重叠实体和细粒度实体以满足更高要求。为验证其有效性，我们提出了名为VehicleFinder的基准NL车辆检索模型。实验表明，使用FindVehicle预训练的文本编码器后，VehicleFinder在基于UA-DETRAC自建数据集上通过文本指令检索目标车辆时，实现了87.7%的精确率和89.4%的召回率。该模型在单个ARM v8.2 CPU上耗时279.35毫秒，在单个RTX A4000 GPU上耗时93.72毫秒，显著快于基于Transformer的系统。数据集通过链接https://github.com/GuanRunwei/FindVehicle开源，实现代码可通过链接https://github.com/GuanRunwei/VehicleFinder-CTIM获取。