Graph attention network for detecting license plates in crowded street scenes

• Published in: Pattern recognition letters 2020-12, Vol.140, p.18-25
• Main Authors: Chowdhury, Pinaki Nath, Shivakumara, Palaiahnakote, Kanchan, Swati, Raghavendra, Ramachandra, Pal, Umapada, Lu, Tong, Lopresti, Daniel
• Format: Article
• Language: English
• Subjects: Automobiles; Benchmarks; Datasets; Image contrast; License plates; Motorcycles; Occlusion; Pedestrians; Trucks; Vehicle identification; Vehicles
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2020.09.018

•A new problem of multiple vehicles license plate detection is addressed.•Proposed a new framework that combines ResNet and GAT layers in a new way•The proposed method outperforms the existing methods. Detecting multiple license plate numbers in crowded street scenes is challenging and requires the attention of researchers. In contrast to existing methods that focus on images that are not crowded with vehicles, in this work we aim at situations that are common and complex, for example, in city environments where numerous vehicles of different types like cars, trucks, motorbike etc. may present in a single image. In such cases, one can expect large variations in license plates in terms of quality, backgrounds, and various forms of occlusion. To address these challenges, we explore Adaptive Progressive Scale Expansion based Graph Attention Network (APSEGAT). This approach extracts local information which represents the license plates irrespective of vehicle types and numbers because it works at the pixel level in a progressive way, and identifies the dominant information in the image. This may include other parts of vehicles, drivers and pedestrians, and various other background objects. To overcome this problem, we integrate concepts of graph attention networks with progressive scale expansion networks. For evaluating the proposed method, we use our own dataset, named as AMLPR, which contains images captured in different crowded street scenes in different time span, and the benchmark dataset namely, UFPR-ALPR, which provides images of a single vehicle, and another benchmark dataset called, UCSD, which contains images of cars with different orientations. Experimental results on these datasets show that the method outperforms existing methods and is effective in detecting license plate numbers in crowded street scenes. [Display omitted]