Detecting Text in Scene and Traffic Guide Panels With Attention Anchor Mechanism
| Autor: | Jie-Bo Hou, Long-Huang Wu, Xiaobin Zhu, Chang Liu, Xu-Cheng Yin, Hongfa Wang, Chun Yang |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Ground truth
Pixel Computer science Orientation (computer vision) Mechanical Engineering Feature extraction computer.software_genre Object detection Computer Science Applications Active appearance model Robustness (computer science) ComputerApplications_MISCELLANEOUS Automotive Engineering Data mining Intelligent transportation system computer |
| Zdroj: | IEEE Transactions on Intelligent Transportation Systems. 22:6890-6899 |
| ISSN: | 1558-0016 1524-9050 |
| DOI: | 10.1109/tits.2020.2996027 |
| Popis: | Text detection in complex scene images is a challenging task for intelligent transportation. Recently, anchor mechanisms are widely utilized in scene text detection tasks. However, in existing methods, anchors are generally predefined empirically, degrading robustness to complex scenarios with various sizes and orientation variations. In this paper, we propose a novel Attention Anchor Mechanism (AAM), especially targeting at predicting appropriate anchors for each pixel. To be concrete, we regard a series of predefined anchors as basic anchors and utilize an attention model to predict weights corresponding to basic anchors. Consequently, the weighted sum of basic anchors in each pixel can obtain a predicted anchor. In this way, the gap between the predicted anchors and the corresponding ground truth boxes could be narrowed, making the network easier to regress. For facilitating the design of basic anchors, we adopt a dimension-decomposition mechanism to predict width, height, and angle of anchors, respectively. Extensive experiments on several public datasets demonstrate that our method achieves state-of-the-art performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|