CCTSDB 2021 is released!
Brand New Dataset! Brand New Category! A variety of algorithm evaluation!
Everyone is welcome to use it!
Dataset release URL: GitHub - csust7zhangjm/CCTSDB2021
Original paper: HCIS | All Issue
Human-Centric Computing and Information Sciences journal JCR Q1, the second area of the Chinese Academy of Sciences.
Dataset download link:
Link: Baidu Netdisk Please enter the extraction code
Extraction code: nygx
Please help to cite the original author's paper when using the data set:
[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.
Abstract translation:
Abstract
Traffic signs are one of the most important information to guide cars, and the detection of traffic signs is an important part of autonomous driving and intelligent transportation systems. Constructing a traffic sign dataset with multiple samples and sufficient attribute categories will advance the research on traffic sign detection. In this paper, we propose a new Chinese traffic sign detection benchmark, which adds more than 4000 real traffic scene images and corresponding detailed annotations based on CCTSDB 2017, and replaces many original easy-to-detect samples with difficult samples images to adapt to the complex and changeable detection environment. Due to the increased number of difficult samples, the new benchmark can improve the robustness of the detection network to a certain extent compared to the old version. At the same time, we created new dedicated test sets and classified them according to three aspects: category meaning, symbol size, and weather conditions. Finally, we comprehensively evaluate nine classic traffic sign detection algorithms on the new benchmark. Our proposed benchmark can help determine future research directions for this algorithm and develop more accurate traffic sign detection algorithms that are more robust and real-time.
Abstract of the original text:
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.
Website translation:
In the cctsdb 2021 dataset, there are a total of 17856 images in the training set and positive sample test set. The traffic signs in the image are divided into mandatory, prohibited and warning according to their meanings.
There are 16356 training set images numbered 00000-18991 in total.
The positive sample test set has 1500 images numbered 18992-20491.
The "XML" zip file stores the annotation files in XML format for the training set and positive sample test set.
The "train_img" compressed package stores the training set images.
The "train_labels" compressed package stores the annotation files in TXT format of the training set.
The "test_img" compressed package stores positive sample test set images.
The "Weather and Environment Based Classification" zip package stores XML-formatted annotation files for the test set of positive samples classified according to weather and lighting conditions.
The "classification based on traffic sign size" compressed package stores XML format annotation files of the positive sample test set classified according to the size of traffic signs in the image.
"Negative Samples" contains 500 negative sample images.
Original website content:
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.