SZTAKI AirMotion Benchmark Set

A Ground truth collection for object motion detection in image pairs captured by moving aerial vehicles

co-authors: Csaba Benedek, Tamás Szirányi (both MTA SZTAKI), Zoltán Kató (Univ. Szeged) and Josiane Zerubia (INRIA Sophia-Antipolis)

Description

This Benchmark set contains 83 image pairs (of size 320x240) and binary motion masks (drawn by hand), which were used for evaluation in publications [1], [2] and [3]. The images are from 3 different test sets captured by flying balloons and airplanes.

Each record constains a pair of input images and a motion mask. The input images are unregistered and taken with cca. 1-2 sec time differences under fast camera motion. The motion mask contains 'the footprints' of all intependent object displacements in the coordinate system of the first frame. Note that object tracking is not included, therefore, we extract all the image regions which correspond to moving objects in either of the two frames (a moving object may result in two blobs). More specifically, pixel s belongs to a white region of the mostion mask, if the 3-D scene point, which is projected to pixel s in the first image, changes its position in the scene’s (3-D) world coordinate system or is covered by a moving object by the time taking the second image. Otherwise, pixel s is black. For more information please contact Csaba Benedek.

Sample images:

Test set Image 1 Image 2 GT change mask

Balloon1

(52 image pairs)

Balloon2

(22)

Budapest

(9)

 

Terms of usage:

The benchmark set is free for scientific use.

- Please acknowledge the use of the benchmark by referring to our relevant publications [1], [2] and [3].
- Please notify us if a publication using the benchmark set appears.

Download:

DOWNLOAD BENCHMARK (~30MB)

For password, please contact Csaba Benedek in e-mail: benedek.csaba_at_sztaki.mta.hu

References

[1] Cs. Benedek, T. Szirányi, Z. Kato and J. Zerubia: ”Detection of Object Motion Regions in Aerial Image Pairs with a Multi-Layer Markovian Model”, IEEE Transactions on Image Processing, vol. 18, no. 10, pp. 2303-2315, 2009

[2] Cs. Benedek, T. Szirányi, Z. Kato and J. Zerubia: ”A Multi-Layer MRF Model for Object-Motion Detection in Unregistered Airborne Image-Pairs,” IEEE International Conference on Image Processing (ICIP), vol VI, pp. 141-144, presented as lecture, San Antonio, Texas, USA, September 16-19, 2007

[3] Cs. Benedek, T. Szirányi, Z . Kato and J. Zerubia , ”A three-layer MRF model for object motion detection in airborne images,” Research Report 6208 , INRIA Sophia Antipolis, France, June 2007