A Novel Motion Detection Method Resistant to Severe Illumination Changes

TL;DR

This paper introduces a new pixel-level motion detection method that effectively handles severe illumination changes by using a novel 3D wavelet-based descriptor, outperforming existing techniques in challenging scenarios.

Contribution

The paper presents a novel 3D wavelet-based motion descriptor for motion detection and dynamic texture segmentation, improving accuracy under severe illumination variations.

Findings

Outperforms existing methods in severe illumination scenarios

Effective in dynamic texture segmentation

Validated on multiple datasets

Abstract

Recently, there has been a considerable attention given to the motion detection problem due to the explosive growth of its applications in video analysis and surveillance systems. While the previous approaches can produce good results, an accurate detection of motion remains a challenging task due to the difficulties raised by illumination variations, occlusion, camouflage, burst physical motion, dynamic texture, and environmental changes such as those on climate changes, sunlight changes during a day, etc. In this paper, we propose a novel per-pixel motion descriptor for both motion detection and dynamic texture segmentation which outperforms the current methods in the literature particularly in severe scenarios. The proposed descriptor is based on two complementary three-dimensional-discrete wavelet transform (3D-DWT) and three-dimensional wavelet leader. In this approach, a feature vector is extracted for each pixel by applying a novel three dimensional wavelet-based motion descriptor. Then, the extracted features are clustered by a clustering method such as well-known k-means algorithm or Gaussian Mixture Model (GMM). The experimental results demonstrate the effectiveness of our proposed method compared to the other motion detection approaches from the literature. The application of the proposed method and additional experimental results for the different datasets are available at (http://dspl.ce.sharif.edu/motiondetector.html).