Detecting and Shadows in the HSV Color Space Using Dynamic Thresholds

Abstract

The detection of moving objects in a video sequence is an essential step in almost all the systems of vision by computer. However, because of the dynamic change in natural scenes, the detection of movement becomes a more difficult task. In this work, we propose a new method for the detection moving objects that is robust to shadows, noise and illumination changes. For this purpose, the detection phase of the proposed method is an adaptation of the MOG approach where the foreground is extracted by considering the HSV color space. To allow the method not to take shadows into consideration during the detection process, we developed a new shade removal technique based on a dynamic thresholding of detected pixels of the foreground. The calculation model of the threshold is established by two statistical analysis tools that take into account the degree of the shadow in the scene and the robustness to noise. Experiments undertaken on a set of video sequences showed that the method put forward provides better results compared to existing methods that are limited to using static thresholds.

Cotton Yield Estimation From Aerial Imagery Using Machine Learning Approaches

“…This suggests that RGB color space information alone was not a robust enough descriptor to properly extract the cotton pixels, as previous studies have noted. Other color spaces, in particular HSV and CIELAB color models, increase invariance with respect to luminosity and lighting changes and are more robust than the RGB color space in relation to the presence of shadows (Hdioud et al, 2018 ). In this study, we applied an SVM model to classify image pixels using RGB, HSV, and CIELAB color spaces information.…”