数据集发布网址：GitHub - csust7zhangjm/CCTSDB2021
论文原文：HCIS | All Issue
Human-Centric Computing and Information Sciences 期刊JCR Q1，中科院二区。
数据集下载链接：
链接：百度网盘 请输入提取码
提取码：nygx
使用数据集请帮忙引用原作者论文：
[1] Jianming Zhang, Xin Zou, Li-Dan Kuang, Jin Wang, R. Simon Sherratt, Xiaofeng Yu. CCTSDB 2021: A more comprehensive traffic sign detection benchmark. Human-centric Computing and Information Sciences, 2022, vol. 12, Article number: 23. DOI: 10.22967/HCIS.2022.12.023.
[2] Jianming Zhang, Wei Wang, Chaoquan Lu, Jin Wang, Arun Kumar Sangaiah. Lightweight deep network for traffic sign classification. Annals of Telecommunications, 2020, vol. 75, no. 7-8, pp. 369-379. DOI: 10.1007/s12243-019-00731-9.
[3] 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.
摘要译文：
摘要
交通标志是引导汽车行驶的最重要信息之一，交通标志的检测是自主驾驶和智能交通系统的重要组成部分。构建一个具有多个样本和足够属性类别的交通标志数据集将推动交通标志检测研究的发展。在本文中，我们提出了一个新的中国交通标志检测基准，该基准在CCTSDB 2017的基础上添加了4000多幅真实交通场景图像和相应的详细注释，并用困难的样本替换了许多原始的易检测图像，以适应复杂多变的检测环境。由于困难样本数量的增加，新的基准测试与旧版本相比可以在一定程度上提高检测网络的鲁棒性。同时，我们创建了新的专用测试集，并根据三个方面对其进行分类：类别含义、符号大小和天气条件。最后，我们在新的基准上对九种经典的交通标志检测算法进行了综合评价。我们提出的基准测试可以帮助确定该算法未来的研究方向，并开发出更精确的交通标志检测算法，具有更高的鲁棒性和实时性。
原文摘要：
Abstract
Traffic signs are one of the most important information that guide cars to travel, and the detection of traffic signs is an important component of autonomous driving and intelligent transportation systems. Constructing a traffic sign dataset with many samples and sufficient attribute categories will promote the development of traffic sign detection research. In this paper, we propose a new Chinese traffic sign detection benchmark, which adds more than 4,000 real traffic scene images and corresponding detailed annotations based on our CCTSDB 2017, and replaces many original easily-detected images with difficult samples to adapt to the complex and changing detection environment. Due to the increase of the number of difficult samples, the new benchmark can improve the robustness of the detection network to some extent compared to the old version. At the same time, we create new dedicated test sets and categorize them according to three aspects: category meanings, sign sizes, and weather conditions. Finally, we present a comprehensive evaluation of nine classic traffic sign detection algorithms on the new benchmark. Our proposed benchmark can help determine the future research direction of the algorithm and develop a more precise traffic sign detection algorithm with higher robustness and real-time performance.
网站译文：
在cctsdb 2021数据集中，训练集和阳性样本测试集共有17856幅图像。图像中的交通标志按其含义分为强制、禁止和警告。
共有16356个编号为00000-18991的训练集图像。
阳性样本测试集有1500幅图像，编号18992-20491。
“XML”压缩包存储训练集和阳性样本测试集的XML格式注释文件。
“train\u img”压缩包存储训练集图像。
“train\u labels”压缩包存储训练集的TXT格式注释文件。
“test\u img”压缩包存储阳性样本测试集图像。
“基于天气和环境的分类”压缩包存储根据天气和照明条件分类的阳性样本测试集的XML格式注释文件。
“基于交通标志大小分类”压缩包存储根据图像中交通标志大小分类的阳性样本测试集的XML格式注释文件。
“负片样本”包含500幅负片样本图像。
原网站内容：
In cctsdb 2021 dataset, there are 17856 images in training set and positive sample test set. The traffic signs in the image are divided into mandatory, prohibitory and warning according to their meanings.
There are 16356 training set images numbered 00000-18991.
The positive sample test set has 1500 images numbered 18992-20491.
The "XML" compressed package stores the XML format annotation files of training set and positive sample test set.
The "train_img" compressed package stores the training set images.
The "train_labels" compressed package stores the TXT format annotation file of the training set.
The "test_img" compressed package stores the positive sample test set image.
The "classification based on weather and environment" compressed package stores the XML format annotation file of the positive sample test set classified according to the weather and lighting conditions.
The "classification based on size of traffic signs" compressed package stores the XML format annotation file of the positive sample test set classified according to the size of traffic signs in the image.
"Negative samples" contains 500 negative sample images.
