資料集 | 開源資料集（計算機視覺影象、定位、識別）
博主github：https://github.com/MichaelBeechan
博主CSDN：https://blog.csdn.net/u011344545
計算機視覺資料集：https://github.com/MichaelBeechan/CV-Datasets
Image Motion and Tracking
| 資料集 | 功能 | 解釋 | 連結 |
| Visual Tracking | Videos for evaluating visual trackers robustness |
ALOV300++ | |
| VOT2015 Benchmark |
Visual Tracking |
The dataset comprises 60 short sequences showing various objects in challenging backgrounds. |
|
| MOT Benchmark |
The Multiple Object Tracking Benchmark |
including object detection, pedestrian detection, 3D reconstruction, optical flow, single-object short-term tracking, and stereo estimation | MOTChallenge |
| THUMOS | Temporal action localization(動作定位) | UCF101、Pre-computed low-level Features (Improved DTF [1])、List of action classes and their numerical index | THUMOS Challenge 2014 |
| ActivityNet | Large Scale Activity Recognition | Untrimmed Classification Challenge、Detection Challenge | ActivityNet |
| Scene Flow Datasets |
Optical Flow | A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation | Scene Flow |
| KITTI Vision Benchmark |
Optical Flow | stereo 2012, flow 2012, odometry, object detection or tracking benchmarks | KITTI |
| MPI Sintel Dataset | Optical Flow Training & Test Data |
New training data is available! Please see the dedicated pages for Stereo and disparity, Depth and camera motion, and Segmentation. | MPI |
3D Computer Vision
| 資料集 | 功能 | 解釋 | 連結 |
| NYU Depth V2 dataset |
關於RGBD 影象場景理解的資料庫 | The NYU-Depth V2 data set is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras from the Microsoft Kinect. | NYU Depth Dataset V2 |
| SUN RGBD dataset | 3D bounding boxes和room layouts的標註 |
Dataset for IKEA 3D models and aligned images |
(Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild)PASCAL3D+ :http://cvgl.stanford.edu/projects/pascal3d.html
SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite : http://rgbd.cs.princeton.edu/
New Tsukuba Dataset：http://www.cvlab.cs.tsukuba.ac.jp/dataset/tsukubastereo.php
DTU Robot Image Data Sets：http://roboimagedata.compute.dtu.dk/
OXFORD ROBOTCAR DATASET：https://robotcar-dataset.robots.ox.ac.uk/
ShapeNet ：https://www.shapenet.org/
middlebury：http://vision.middlebury.edu/stereo/