2D Object Detection for Autonomous Vehicles in India
收藏DataCite Commons2025-05-12 更新2025-05-17 收录
下载链接：
https://dataverse.harvard.edu/citation?persistentId=doi:10.7910/DVN/ZTRL9Y
下载链接
链接失效反馈官方服务：
资源简介：
The data for this study uses real-time images taken by the
camera as well as those available in the public domain. A
total of 2.4k images were collected. Efforts were put in by
the authors to make sure that the dataset was generalized
and consisted of multifarious images taken at different times
of the day and lighting conditions to make way for more
robust detection. Images were also selected to have a wide
variety of vehicle models in different real-time scenarios. All
given classes unless mentioned otherwise are a mixture of a
collection of scraped images from the web using a custom
python script, taken from the Google V6 image repository
or a collection of camera clicked pictures to bring diversity to
the database:
• Car
• Auto Rickshaw
• Pedestrian*
• Potholes
• Bikes
• Traffic Light
As the dataset is too large to publish, the results and the validation set have been published here. The complete dataset can be found at https://drive.google.com/drive/folders/1NgR54s_E-UjsUoqvRZrtR_BawMkVkzwo?usp=sharing.
提供机构：
Harvard Dataverse
创建时间：
2022-07-21
