LTDNet: A Lightweight Text Detector for Real-Time Arbitrary-Shape Traffic Text Detection

• Published in: IEEE/CAA journal of automatica sinica Vol. 12; no. 8; pp. 1648 - 1660
• Main Authors: Wang, Runmin, Zhu, Yanbin, Zhu, Ziyu, Cui, Lingxin, Wan, Zukun, Zhu, Anna, Ding, Yajun, Qian, Shengyou, Gao, Changxin, Sang, Nong
• Format: Journal Article
• Language: English
• Published: Chinese Association of Automation (CAA) 01.08.2025
• Subjects: Accuracy; Attention mechanism; Convolutional neural networks; Detectors; Feature extraction; feature fusion; Natural language processing; Optical character recognition; point-to-edge distance vector; Real-time systems; Shape; Text detection; traffic text detection; Vectors
• ISSN: 2329-9266; 2329-9274
• DOI: 10.1109/JAS.2024.125022

Traffic text detection plays a vital role in understanding traffic scenes. Traffic text, a distinct subset of natural scene text, faces specific challenges not found in natural scene text detection, including false alarms from non-traffic text sources, such as roadside advertisements and building signs. Existing state-of-the-art methods employ increasingly complex detection frameworks to pursue higher accuracy, leading to challenges with real-time performance. In response to this issue, we propose a real-time and efficient traffic text detector named LTDNet, which strikes a balance between accuracy and real-time capabilities. LTDNet integrates three essential techniques to address these challenges effectively. First, a cascaded multilevel feature fusion network is employed to mitigate the limitations of lightweight backbone networks, thereby enhancing detection accuracy. Second, a lightweight feature attention module is introduced to enhance inference speed without compromising accuracy. Finally, a novel point-to-edge distance vector loss function is proposed to precisely localize text instance boundaries within traffic contexts. The superiority of our method is validated through extensive experiments on five publicly available datasets, demonstrating its state-of-the-art performance. The code will be released at https://github.com/runminwang/LTDNet.