Motion Segmentation

The Hopkins 155 dataset consists of 156 video sequences of two or three motions. Each video sequence motion corresponds to a low-dimensional subspace. There are 39−550 data vectors drawn from two or three motions for each video sequence. Source: Symmetric low-rank representation for subspace clustering Image Source: http://www.vision.jhu.edu/data/hopkins155/

ApolloScape is a large dataset consisting of over 140,000 video frames (73 street scene videos) from various locations in China under varying weather conditions. Pixel-wise semantic annotation of the recorded data is provided in 2D, with point-wise semantic annotation in 3D for 28 classes. In addition, the dataset contains lane marking annotations in 2D. Source: A2D2: Audi Autonomous Driving Dataset Image Source: https://arxiv.org/pdf/1803.06184.pdf

A large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egOCentric video frames over 4000 sequences collected by 4 participants interacting with 800 different object instances from 16 categories over 610 different indoor rooms.

Includes accurate pixel-wise motion masks, egomotion and ground truth depth. Source: EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras

Includes challenging sequences and extensive data stratification in-terms of camera and object motion, velocity magnitudes, direction, and rotational speeds. Source: 0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event Camera

Extension of the official KITTI'15 dataset. independently moving instance segmentation ground truth to cover all moving objects, not just a selection of cars and vans. - Instance Motion Segmentation of all moving objects - Binary Motion Segmentation (background/foreground) - Validation Masks Dataset contains: - Instance Motion Segmenation for the training split of the KITTI'15 dataset

Please find more details of this dataset at https://alex-xun-xu.github.io/ProjectPage/CVPR_18/index.html 3D motion segmentation has been the key problem in computer vision research due to the application in structure from motion and robotics. Traditional motion segmentation approaches are often evaluated on artificial dataset like Hopkins 155 [1] and its variants. Because the vanishing camera translation effect is often overlooked, these approaches would fail in real world scenes where camera is carrying out significant translation and scene has complex structure. We proposed the KT3DMoSeg to address the 3D motion segmentation problem in real world scenes. The KT3DMoSeg dataset was created upon the KITTI benchmark [2] by manually selecting 22 sequences and labelling each individual foreground object. We select sequence with more significant camera translation so camera mounted on moving cars are preferred. We are interested in the interplay of multiple motions, so clips with more than 3 motions are also chosen, as long as these moving objects contain enough features for forming motion hypotheses. 22 short clips, each with 10-20 frames, are chosen for evaluation. We extract dense trajectories from each sequence using [3] and prune out trajectories shorter than 5 frames. Reference [1] R. Tron and R. Vidal. A Benchmark for the Comparison of 3-D Motion Segmentation Algorithms. CVPR, 2007. [2] A. Geiger, P. Lenz, C. Stiller, and R. Urtasun. Vision meets robotics: The kitti dataset. International Journal of Robotics Research, 2013. [3] N. Sundaram, T. Brox, and K. Keutzer. Dense point trajectories by GPU-accelerated large displacement optical flow. In ECCV, 2010.