End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining

NEUROCOMPUTING

卷:446

Article

Chen, Song-Lu^1,2  Tian, Shu^1,2  Ma, Jia-Wei^1,2  Liu, Qi^1,2  Yang, Chun^1,2  Chen, Feng^2,3  Yin, Xu-Cheng^1,2 

[1] Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 100083, Peoples R China

[2] Univ Sci & Technol Beijing, USTB EEasyTech Joint Lab Artificial Intelligence, Beijing 100083, Peoples R China

[3] EEasy Technol Co Ltd, Zhuhai 519000, Peoples R China

关键词: License plate detection;    Vehicle-plate relation;    Small-sized license plate;    Multi-oriented license plate;    End-to-end;   

DOI  :  10.1016/j.neucom.2021.03.040

来源: Elsevier

【 摘 要 】

License plate detection is the first and essential step of the license plate recognition system and is still challenging in real applications, such as on-road scenarios. In particular, small-sized and multi oriented license plates, mainly caused by the remote and mobile camera, are challenging to detect. We propose a novel and applicable method for degraded license plate detection via vehicle-plate relation mining in this work. The proposed method can detect the license plate in a coarse-to-fine scheme. First, we propose to estimate the plate by using the relationships between the vehicle and the license plate, which can significantly reduce the search area and precisely detect small-sized license plates. Second, we present to robustly detect the multi-oriented license plate by regressing the four corners of the license plate in the local region. The whole network is constructed in an end-to-end manner, and codes are available at https://github.com/chensonglu/LPD-end-to-end. (c) 2021 Elsevier B.V. All rights reserved.

【 授权许可】

Free