RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection

被引:11
|
作者
Li, Jiachen [1 ,3 ]
Lin, Yuan [3 ]
Liu, Rongrong [3 ]
Ho, Chiu Man [3 ]
Shi, Humphrey [1 ,2 ]
机构
[1] UIUC, Urbana, IL 61801 USA
[2] Univ Oregon, Eugene, OR 97403 USA
[3] InnoPeak Technol, Palo Alto, CA 94303 USA
关键词
D O I
10.1109/CVPRW53098.2021.00267
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Segmentation-based scene text detection methods have been widely adopted for arbitrary-shaped text detection recently, since they make accurate pixel-level predictions on curved text instances and can facilitate real-time inference without time-consuming processing on anchors. However, current segmentation-based models are unable to learn the shapes of curved texts and often require complex label assignments or repeated feature aggregations for more accurate detection. In this paper, we propose RSCA: a Real-time Segmentation-based Context-Aware model for arbitrary-shaped scene text detection, which sets a strong baseline for scene text detection with two simple yet effective strategies: Local Context-Aware Upsampling and Dynamic Text-Spine Labeling, which model local spatial transformation and simplify label assignments separately. Based on these strategies, RSCA achieves state-of-the-art performance in both speed and accuracy, without complex label assignments or repeated feature aggregations. We conduct extensive experiments on multiple benchmarks to validate the effectiveness of our method. RSCA-640 reaches 83.9% F-measure at 48.3 FPS on CTW1500 dataset.
引用
收藏
页码:2349 / 2358
页数:10
相关论文
共 50 条
  • [21] CONTEXT-AWARE REAL-TIME TRACKING IN SPARSE REPRESENTATION FRAMEWORK
    Ashwini, M. J.
    Babu, R. Venkatesh
    Ramakrishnan, K. R.
    2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013), 2013, : 2450 - 2454
  • [22] Paving the Way for a Real-Time Context-Aware Predictive Architecture
    Corral-Plaza, David
    Ortiz, Guadalupe
    Boubeta-Puig, Juan
    SERVICE-ORIENTED COMPUTING - ICSOC 2017 WORKSHOPS, 2018, 10797 : 369 - 374
  • [23] Real-Time Process Adaptation: A Context-Aware Replanning Approach
    Nunes, Vanessa T.
    Santoro, Flavia M.
    Werner, Claudia M. L.
    Ralha, Celia G.
    IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2018, 48 (01): : 99 - 118
  • [24] Real-time manifold regularized context-aware correlation tracking
    Fan, Jiaqing
    Song, Huihui
    Zhang, Kaihua
    Liu, Qingshan
    Yan, Fei
    Lian, Wei
    FRONTIERS OF COMPUTER SCIENCE, 2020, 14 (02) : 334 - 348
  • [25] Real-time manifold regularized context-aware correlation tracking
    Jiaqing Fan
    Huihui Song
    Kaihua Zhang
    Qingshan Liu
    Fei Yan
    Wei Lian
    Frontiers of Computer Science, 2020, 14 : 334 - 348
  • [26] Scheduling of soft real-time systems for context-aware applications
    Wong, JL
    Liao, WP
    Li, F
    He, L
    Potkonjak, M
    DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 318 - 323
  • [27] Real-time Context-aware learning System for IoT Applications
    Das, Bhaskar
    Almhana, Jalal
    Karim, Lutful
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 305 - 310
  • [28] PCBSNet: A Pure Convolutional Bilateral Segmentation Network for Real-Time Natural Scene Text Detection
    Lian, Zhe
    Yin, Yanjun
    Zhi, Min
    Xu, Qiaozhi
    ELECTRONICS, 2023, 12 (14)
  • [29] Lightweight Context-Aware Network Using Partial-Channel Transformation for Real-Time Semantic Segmentation
    Shi, Min
    Lin, Shaowen
    Yi, Qingming
    Weng, Jian
    Luo, Aiwen
    Zhou, Yicong
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (07) : 7401 - 7416
  • [30] Context-aware local abnormality detection in crowded scene
    Zhu XiaoBin
    Jin Xin
    Zhang XiaoYu
    Li ChangSheng
    He FuGang
    Wang Lei
    SCIENCE CHINA-INFORMATION SCIENCES, 2015, 58 (05) : 1 - 11