Abstract

License plate detection serves as one of the most widely-used real-world applications in fields like toll control, traffic scene analysis, and suspected vehicle tracking. Along with license plate information, to obtain overall comprehension, the information of the owner vehicle also plays a great role, and contextual information is defined as the relationship between the license plate and the owner vehicle in our work. We proposed a one-stage anchor-free object detector for simultaneously detecting the region of license plates and vehicles’ poses. The detector, rather than bounding rectangles, gives bounding quadrilaterals, which gives a more precise indication for license plates. For single scale input, we reached license plate mAP/mAP50 of 35.4/82.3 on the benchmark dataset, already outperformed the existing commercial systems OpenALPR and Sighthound. For multi-scale input, we reached the best mAP/mAP50 of 40.8/90.1. For the car pose (front-rear), classification accuracy reached 98.8%, average IoU reached 71.3%, giving a promising result as an end-to-end license plate detector with contextual information.