JHU Computer Vision Machine Learning

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:

Checkerboard sequences: this category consists of 104 sequences of indoor scenes taken with a handheld camera under controlled conditions. The checkerboard pattern on the objects is used to assure a large number of tracked points.
Traffic sequences: this category consists of 38 sequences of outdoor traffic scenes taken by a moving handheld camera.
Other (Articulated/non-rigid sequences): this category contains 13 sequences displaying motions constrained by joints, head and face motions, people walking, etc.

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 Motions 3 Motions

# Seq. Points Frames # Seq. Points Frames

Checkerboard 78 291 28 26 437 28

Traffic 31 241 30 7 332 31

Others 11 155 40 2 122 31

All 120 266 30 35 398 29

	2 Motions	3 Motions
Checkerboard	78	291	28	26	437	28
Traffic	31	241	30	7	332	31
Others	11	155	40	2	122	31
All	120	266	30	35	398	29


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.

Robust Motion Segmentation via Lossy Compression (ALC): http://perception.csl.illinois.edu/coding/motion/
Improved Multistage Learning for Multibody Motion Segmentation (Improved version of MSL): http://www.iim.ics.tut.ac.jp/~sugaya/public-e.html

	2 Motions			3 Motions
	# Seq.	Points	Frames	# Seq.	Points	Frames
Checkerboard	78	291	28	26	437	28
Traffic	31	241	30	7	332	31
Others	11	155	40	2	122	31
All	120	266	30	35	398	29