The author has updated the speed measurement data and modified the existing problems.
The China Traffic Sign Detection Dataset ( CCTSDB ) is derived from the training dataset proposed in A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2.
Paper address: https://doi.org/10.3390/a10040127
Github：https://github.com/csust7zhangjm/CCTSDB
The link is: https://pan.baidu.com/s/1Swb48BppUJtuE3QeCcd4Yw Extraction code: rv4s
First of all, I would like to thank the authors for providing nearly 20,000 data sets for free! ! !
The author has updated the complete CCTSDB data set. In order to facilitate domestic users to download, he deliberately uploaded the Baidu cloud disk, which includes all pictures and marked GT.
There is a folder for every 1000 pictures. When saving and downloading, non-Baidu cloud disk member users have a single limit of 3000 files. You can save them in three or three folders, and of course you can download them directly.
Benefits: Download at full speed for non-members! ! ! Baidu: Speedpan https://www.speedpan.com/ Download and use by yourself.
github original text:
The CSUST Chinese Traffic Sign Detection Benchmark China Traffic Dataset was produced by Zhang Jianming's team from the Hunan Provincial Key Laboratory of Comprehensive Transportation Big Data Intelligent Processing at Changsha University of Science and Technology.
We have uploaded the complete dataset to Baidu Cloud Disk: The link is: https://pan.baidu.com/s/1Swb48BppUJtuE3QeCcd4Yw
Extraction code: rv4s
So far, 15,734 images have been uploaded, and all groundtruths have also been uploaded. Disclaimer: At present, there are only three categories of labeling data: instruction signs, prohibition signs, and warning signs.
The specific subdivision standard data set will not be announced for the time being because it is still being produced. Please pay attention to our follow-up updates!
If you download and do research experiments, please try to cite our articles, and be sure to cite the first one:
[1] Jianming Zhang, Wei Wang, Chaoquan Lu, Jin Wang, Arun Kumar Sangaiah. Lightweight deep network for traffic sign classification. Annals of Telecommunications, 2019 online, https://doi.org/10.1007/s12243-019-00731-9.
[2] Jianming Zhang, Zhipeng Xie, Juan Sun, Xin Zou, Jin Wang. A cascaded R-CNN with multiscale attention and imbalanced samples for traffic sign detection. IEEE Access, 2020, vol. 8, pp. 29742-29754. DOI: 10.1109/ACCESS.2020.2972338.
[3] Jianming Zhang, ManTing Huang, XiaoKang Jin, XuDong Li. A real-time Chinese traffic sign detection algorithm based on modified YOLOv2 [J]. Algo
[4] Li Xudong, Zhang Jianming, Xie Zhipeng, Wang Jin. Fast detection algorithm for traffic signs based on three-scale nested residual structure [J]. Computer Research and Development, 2020, 57(5): 1022-1036. Li Xudong,
Zhang Jianming, Xie Zhipeng, Wang Jin. A Fast Traffic Sign Detection Algorithm Based on Three-Scale Nested Residual Structures[J]. Journal of Computer Research and Development, 2020, 57(5): 1022-1036.
If you have any questions: please email: [email protected]
——————————————————————————————————————————————————
Abstract of the paper:
Traffic sign detection is an important task in traffic sign recognition systems. Chinese traffic signs have their unique features compared with traffic signs of other countries. Convolutional neural networks (CNNs) have achieved a breakthrough in computer vision tasks and made great success in traffic sign classification. In this paper, we present a Chinese traffic sign detection algorithm based on a deep convolutional network. To achieve real-time Chinese traffic sign detection, we propose an end-to-end convolutional network inspired by YOLOv2. In view of the characteristics of traffic signs, we take the multiple 1 × 1 convolutional layers in intermediate layers of the network and decrease the convolutional layers in top layers to reduce the computational complexity. For effectively detecting small traffic signs, we divide the input images into dense grids to obtain finer feature maps. Moreover, we expand the Chinese traffic sign dataset (CTSD) and improve the marker information, which is available online. All experimental results evaluated according to our expanded CTSD and German Traffic Sign Detection Benchmark (GTSDB) indicate that the proposed method is the faster and more robust. The fastest detection speed achieved was 0.017 s per image.
Traffic sign detection is an important task in traffic sign recognition systems. Compared with traffic signs in other countries, Chinese traffic signs have their unique characteristics. Convolutional Neural Networks (CNNs) have achieved breakthroughs in computer vision tasks, achieving great success in traffic sign classification. In this paper, we propose a traffic sign detection algorithm based on deep convolutional networks. To achieve real-time detection of traffic signs, this paper proposes an end-to-end convolutional network based on YOLOv2. According to the characteristics of traffic signs, multiple 1×1 convolutional layers are used in the middle layer of the network, and the convolutional layers are reduced in the top layer to reduce the computational complexity. To efficiently detect small traffic signs, we densely mesh the input image to obtain finer feature maps. Additionally, we augment the China Traffic Sign Dataset (CTSD) and improve sign information available online. All experimental results evaluated against the extended CTSD and the German Traffic Sign Detection Benchmark (GTSDB) show that the proposed method is faster and more robust. The fastest detection speed obtained is 0.017 seconds per image.