Hierarchical Motion Tracking Using Matching of Sparse Features

Authors: Petr Pulc, Martin Holeňa
Publication year: 2018
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: SITIS 2018. Proceedings of the 14th International Conference on Signal-Image Technology & Internet-Based Systems
Projects: Fusion-Based Knowledge Discovery in Human Activity Data
Bibliographic citation: PULC, Petr, HOLEŇA, Martin. Hierarchical Motion Tracking Using Matching of Sparse Features. In: SANNITI DI BAJA, G., GALLO, L., YETONGNON, K., DIPANDA, A., CASTRILLÓN-SANTANA, M., CHBEIR, R., eds. SITIS 2018. Proceedings of the 14th International Conference on Signal-Image Technology & Internet-Based Systems. Los Alamitos: IEEE Computer Society CPS, 2018, S. 449-456. ISBN 978-1-5386-9385-8
Dostupné z: doi:10.1109/SITIS.2018.00075
DOI: 10.1109/SITIS.2018.00075
ID: 497814

Abstract

Fundamental approaches in motion tracking are based on registration of pixel patches from one frame to another. To ensure invariance to some changes in the image and improve the speed of discovering a match, a pyramidal approach is used to steer the process faster to optima. However, registration of the patches in high resolution is still computationally expensive. Because we require the algorithm to process Ultra HD video content in real time on commonly available hardware, especially on mid-tier graphics processing units, approaches using matching of pixel patches are not feasible. In this paper, we present and evaluate an approach inspired by motion tracking on an image pyramid. However, instead of comparing pixel patches one to another, we utilise binary image descriptors that are much shorter and inherently use a Hamming distance for their direct comparison. Evaluation of our implementation, which is available on GitHub, was carried out on the Multiple Object Tracking challenge dataset.