该数据集是来自伊利诺伊州芝加哥市交通摄像头的增强随机屏幕截图的集合。在数据中，所有车辆都被标记在一个名为 的类别中car。标签由边界框组成，并以 YOLOv5 PyTorch 格式存储。

Acknowledgements

Snyder, Corey; Do, Minh (2019): Data for STREETS: A Novel Camera Network Dataset for Traffic Flow. University of Illinois at Urbana-Champaign. https://doi.org/10.13012/B2IDB-3671567_V1

前言总结一下视频监控的数据集，用于目标检测、跟踪。一、UA-DETRAC 数据集UA-DETRAC是一个具有挑战性的真实世界多目标检测和多目标跟踪基准。该数据集包括在中国北京和天津的24个不同地点使用Cannon EOS 550D相机拍摄的10小时视频。视频以每秒25帧（fps）的速度录制，分辨率为960×540像素。UA-DETRAC数据集中有超过14万个帧，手动注释了8250个车辆，总共有121万个标记的对象边界框。官方还对目标检测和多目标跟踪中的最新方法以及本网站中详述的评估指标进行基

Detection 相机会晃动，就算左下角显示camere stable，也是晃。unstable的应该是手持相机。 Related Dataset Caltech Pedestrian Detection Benchmark: including 10 hours of vi…

文章目录交通标志、信号灯相关的数据集1. 国内数据集1. Chinese Traffic Sign Database (好像是长沙理工大学的)2. Tsinghua-Tencent 100K Tutorial（信号标志，没有灯的）3. 一个游戏中的交通标志数据集；4. 滴滴数据集（没有交通标志）5. 百度 ApolloScape 数据集（只有信号灯、没有交通标志；且信号灯的数据集只能在线使用）2....

在交通领域，很多问题的研究和算法的实现都基于交通网络数据。如果你恰好在在相关领域做研究，又为找不到优质全面的网络数据而发愁。不要着急！Lab将为你介绍一个专业的交通网络数据网站，网站里有很多相关的网络…

本数据集包含北京3万多个交通摄像头的地理位置、朝向、邻近道路，可用于地理信息可视化。

车辆重识别、行人检测数据集、多摄像头数据集

道路监控摄像头-车辆 数据集

Related Dataset

Caltech Pedestrian Detection Benchmark: including 10 hours of videos with 350,000 annotated pedestrian bounding boxes taken from a moving vehicle with the viewpoint of the driver.

KITTI Detection Benchmark: including 14,999 frames comprising a total of 80,256 labeled objects taken from a moving vehicle with the viewpoint of the driver.

MIT Street Scene: Each image was taken from a DSC-F717 camera at in and around Boston, MA, and was then labeled by hand with polygons surrounding each example of 9 object categories, including cars, pedestrians, bicycles, buildings, trees, skies, roads, sidewalks, and stores.

KAIST Benchmark: Multispectral pedestrian detection benchmark which provides well aligned color-thermal image pairs captured by a beam splitter based special hardware.

CVC-ADAS: A series of pedestrian sequences including pedestrian videos acquired on-board, virtual-world pedestrians, and occluded pedestrians.

ETHZ: A series of video sequences with annotated pedestrians captured from a stroller in the urban scenes.

PASCAL VOC: Diverse object views and poses in static images.

ImageNet: A image database consists of 14,197,122 images