|
|
|
| Text detection of highway traffic sign based on improved EAST |
Jiuyuan HUO( ),Hao JIANG,Chen CHANG |
| School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China |
|
|
|
Abstract A traffic sign text detection algorithm (efficient traffic sign text detection, ETST) based on the efficient and accurate text detection (EAST) algorithm was proposed in order to address the issue of poor accuracy and stability in traffic sign text detection in highway scenarios. The detection performance of highway traffic sign text was improved by introducing three types of modules. Potential marker regions in an image can be quickly screened by utilizing a traditional marker pre-detection module based on color threshold segmentation and shape analysis. The recognition ability of the proposed algorithm for text at different scales was improved by integrating a multi-scale attention enhancement module. An improved parallel patch-aware attention module (NPPA) was proposed to enhance the ability of the proposed algorithm to perceive and represent local structural features. ETST effectively combined low-level texture cues with high-level semantic information by fusing multi-level feature maps in order to enhance discrimination of challenging text instances. Experiments on datasets such as ICDAR2015, CCTSDB and Total-Text demonstrated that ETST outperformed existing algorithms in key metrics such as accuracy, recall and F1 score, while achieving a processing speed of over 10 frames per second. Then the requirement of near real-time application was satisfied, and decent detection accuracy and computational efficiency were confirmed.
|
|
Received: 23 September 2025
Published: 20 July 2026
|
|
|
| Fund: 国家自然科学基金资助项目（62262038）；甘肃省重点研发计划资助项目（25YFGA045）. |
基于改进EAST的高速公路交通标识文本检测
针对高速公路场景中交通标识文本检测精度与稳定性较差的问题，提出基于高效准确文字检测(EAST)算法思路的交通标识文本检测算法(ETST). 该算法通过引入3类模块，提升高速公路交通标识文本的检测性能. 利用基于颜色阈值分割与形状分析的传统标识预检测模块，快速筛选图像中的潜在标识区域. 融合多尺度注意力增强模块，增强提出算法对不同尺度文本的识别能力. 提出改进型并行补丁感知注意力模块(NPPA)，强化所提算法对局部结构特征的感知与表达能力. 通过对多尺度特征图的联合融合，ETST能够有效整合底层纹理与高层语义信息，提升小尺寸与模糊文本的检测效果. 在ICDAR2015、CCTSDB、Total-Text等数据集上的实验证明，ETST在准确率、召回率及F1分数等核心指标上均优于现有算法，对图片的处理速度大于10帧/s，满足准实时应用需求，具有较高的检测精度与计算效率.
关键词：
交通标识文本检测,
交通标识文本检测算法,
多尺度注意力机制,
小目标文本检测,
并行补丁感知模块,
多尺度特征提取
|
|
| [1] |
林泓, 卢瑶瑶 聚焦难样本的区分尺度的文字检测方法[J]. 浙江大学学报: 工学版, 2019, 53 (8): 1506- 1516
LIN Hong, LU Yaoyao Scale differentiated text detection method focusing on hard examples[J]. Journal of Zhejiang University: Engineering Science, 2019, 53 (8): 1506- 1516
doi: 10.3785/j.issn.1008-973X.2019.08.009
|
|
|
| [2] |
TANG J, ZHANG W, LIU H, et al. Few could be better than all: feature sampling and grouping for scene text detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 4553–4562.
|
|
|
| [3] |
ZHU B, LIU F, CHEN X, et al. EK-net: real-time scene text detection with expand kernel distance [C]//2024 IEEE International Conference on Acoustics, Speech and Signal Processing. Seoul: IEEE, 2024: 6380–6384.
|
|
|
| [4] |
YAO L, TANG C, WAN Y Advanced text detection of container numbers via dual-branch adaptive multi-scale network[J]. Applied Sciences, 2025, 15 (3): 1492
doi: 10.3390/app15031492
|
|
|
| [5] |
DU Y, CHEN Z, JIA C, et al Context perception parallel decoder for scene text recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47 (6): 4668- 4683
doi: 10.1109/TPAMI.2025.3545453
|
|
|
| [6] |
WANG J, CHEN Y, DONG Z, et al Improved YOLOv5 network for real-time multi-scale traffic sign detection[J]. Neural Computing and Applications, 2023, 35 (10): 7853- 7865
doi: 10.1007/s00521-022-08077-5
|
|
|
| [7] |
LU E H C, GOZDZIKIEWICZ M, CHANG K H, et al A hierarchical approach for traffic sign recognition based on shape detection and image classification[J]. Sensors, 2022, 22 (13): 4768
doi: 10.3390/s22134768
|
|
|
| [8] |
董红召, 林少轩, 佘翊妮 交通目标YOLO检测技术的研究进展[J]. 浙江大学学报: 工学版, 2025, 59 (2): 249- 260
DONG Hongzhao, LIN Shaoxuan, SHE Yini Research progress of YOLO detection technology for traffic object[J]. Journal of Zhejiang University: Engineering Science, 2025, 59 (2): 249- 260
doi: 10.3785/j.issn.1008-973X.2025.02.003
|
|
|
| [9] |
DE LA ESCALERA A, MORENO L E, SALICHS M A, et al Road traffic sign detection and classification[J]. IEEE Transactions on Industrial Electronics, 1997, 44 (6): 848- 859
doi: 10.1109/41.649946
|
|
|
| [10] |
CAI Z, VASCONCELOS N Cascade R-CNN: high quality object detection and instance segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43 (5): 1483- 1498
|
|
|
| [11] |
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 779–788.
|
|
|
| [12] |
REDMON J, FARHADI A. YOLO9000: better, faster, stronger [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 6517–6525.
|
|
|
| [13] |
WANG C Y, BOCHKOVSKIY A, LIAO H Y M. Scaled-YOLOv4: scaling cross stage partial network [C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13029–13038.
|
|
|
| [14] |
孙超, 温蜜, 景俐娜 改进SSD算法在交通标志检测中的应用[J]. 计算机工程与应用, 2023, 59 (4): 147- 155
SUN Chao, WEN Mi, JING Lina Application of improved SSD algorithm in traffic sign detection[J]. Computer Engineering and Applications, 2023, 59 (4): 147- 155
doi: 10.3778/j.issn.1002-8331.2108-0389
|
|
|
| [15] |
HU Y, DU X, JIANG S. Online LiDAR-to-vehicle alignment using lane markings and traffic signs [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Vancouver: IEEE, 2023: 3348–3357.
|
|
|
| [16] |
ZHENG Y, ANDRIENKO O, ZHAO Y, et al. DPPD: deformable polar polygon object detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Vancouver: IEEE, 2023: 78–87.
|
|
|
| [17] |
ZHOU X, YAO C, WEN H, et al. EAST: an efficient and accurate scene text detector [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2642–2651.
|
|
|
| [18] |
OUYANG D, HE S, ZHANG G, et al. Efficient multi-scale attention module with cross-spatial learning [C]//2023 IEEE International Conference on Acoustics, Speech and Signal Processing. Rhodes Island: IEEE, 2023: 1–5.
|
|
|
| [19] |
HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13708–13717.
|
|
|
| [20] |
XU S, ZHENG S, XU W, et al. HCF-net: hierarchical context fusion network for infrared small object detection [C]//Proceedings of the IEEE International Conference on Multimedia and Expo. Niagara Falls: IEEE, 2024: 1–6.
|
|
|
| [21] |
KARATZAS D, GOMEZ-BIGORDA L, NICOLAOU A, et al. ICDAR 2015 competition on robust reading [C]//Proceedings of the 13th International Conference on Document Analysis and Recognition. Tunis: IEEE, 2015: 1156–1160.
|
|
|
| [22] |
CH’NG C K, CHAN C S. Total-text: a comprehensive dataset for scene text detection and recognition [C]//Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition. Kyoto: IEEE, 2018: 935–942.
|
|
|
| [23] |
ZHU Z, LIANG D, ZHANG S, et al. Traffic-sign detection and classification in the wild [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2110–2118.
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
