HOPKINS 155 DATASET
DESCRIPTION AND PURPOSE

The Hopkins 155 Dataset has been created with the goal of providing an extensive benchmark for testing feature based motion segmentation algorithms. It contains video sequences along with the features extracted and tracked in all the frames. The ground-truth segmentation is also provided for comparison purposes. The data is stored in the .MAT file format.

CONTENT

Our dataset contains sequences with two and three motions. The sequences can be roughly divided into three categories:

The following table presents some information about the dataset: the number of sequences, the average number of tracked features and the average number of frames for each one of the categories aformentioned, distinguishing also between sequences with two and three motions.

2 Motions3 Motions
# Seq.PointsFrames# Seq.PointsFrames
Checkerboard78291282643728
Traffic3124130733231
Others1115540212231
All120266303539829

Some samples from the Hopkins 155 dataset
Hopkins 155+16: Additional sequences with missing data and outliers

We provide 16 additional sequences that contain missing data or both missing data and outliers and more than three motions. These sequences have the same format and complement the standard Hopkins 155 dataset. We call the aggregated dataset Hopkins 155+16. These sequences can be downloaded from the Download section below.

Some samples from the Hopkins 155 additional sequences

RESULTS

We collected the results obtained on the Hopkins 155 dataset by various motion segmentation algorithm presented in the literature. Please see the corresponding section in the Motion Segmentation research page

DOWNLOAD

To download the Hopkins 155+16 dataset, please refer to the Data page.
To download our MATLAB implementation of some motion segmentation algorithms (GPCA, LSA, RANSAC), please refer to the Code page.

OTHER CODE
Code is available online for some of the motion segmentation algorithms.
PUBLICATIONS
[1]
R. Tron and R. Vidal.
IEEE International Conference on Computer Vision and Pattern Recognition, June 2007.