Point Features Detector of Brightness Anomalies in Monochrome Images of a Real-time Video Sequence

DOI

10.2991/mmsta-19.2019.40How to use a DOI?

Keywords

Harris corner method; blobs detector; image stabilization; optical flow; Lucas-Kanade method

Abstract

Previously, the authors proposed an algorithm for detecting point objects in an image, applying the Harris corner detector. However, this algorithm has one drawback, which is associated with high computational complexity and the slight ability to use this approach in real-time video processing tasks. For these purposes, we propose a new approach of searching point objects on a complex background, which can also be adapted for large-scale objects search. The basis of the new approach is the analysis of all contrasting spots (blobs) in the image, as well as the trajectory analysis of frame-by-frame processing of the video sequence. The novelty of the method lies in the combination of the approach of analyzing local features descriptors of the image applying graph algorithms and extrapolating the values of the camera offset by the least squares method.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Iakov Korovin
AU  - Maxim Khisamutdinov
AU  - Donat Ivanov
PY  - 2019/12
DA  - 2019/12
TI  - Point Features Detector of Brightness Anomalies in Monochrome Images of a Real-time Video Sequence
BT  - Proceedings of the 2019 2nd International Conference on Mathematics, Modeling and Simulation Technologies and Applications (MMSTA 2019)
PB  - Atlantis Press
SP  - 187
EP  - 190
SN  - 2352-538X
UR  - https://doi.org/10.2991/mmsta-19.2019.40
DO  - 10.2991/mmsta-19.2019.40
ID  - Korovin2019/12
ER  -