V2I-CARLA: A Novel Dataset and a Method for Vehicle Reidentification-Based V2I Environment
Hai Wang, Y. L. Xin, Yingfeng Cai, Long Chen, Yicheng Li
Abstract
Vehicle to infrastructure (V2I) is the current development trend for modern-day intelligent transportation systems and corresponds to an emerging topic in the field of automatic driving. In the perceptual task of road vehicle collaboration, vehicle cross-camera matching plays a key role in achieving automatic driving vehicles overview blind zone perception. Existing reidentification (REID) methods for vehicles cross-camera matching ignore the vehicle detailed characteristics. Considering the shortage of vision distance and a single perspective overlapping problem from the existing datasets, this article builds a vehicle REID dataset V2I-CARLA based on an automatic driving simulator, thereby matching the same vehicle successfully when the common feature is few at different perspectives. For the REID task, this article proposes a method for vehicle REID by introducing a pyramid method, which tends to obtain multiscale features of the vehicle under different cameras, capturing subtle features difference between the vehicles with a similar appearance. Simultaneously, circle loss is used in this work for network optimization, and the network is more distinguished. We evaluated our method on the V2I-CARLA and VeRi776 datasets. The experimental results show the superiority of our method, which renders significant improvement over the baseline on different datasets. The dataset V2I-CARLA is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Yx1322441675/V2I-CARLA</uri> .