Background subtraction is an important part of various computer vision applications that can detect the foreground objects by comparing the current pixels with a background model. The general approaches gradually update the background model according to the current status, but might fail in sudden illumination changes. An illumination-robust background modelling method is proposed to address this problem. The method provides quick illumination compensation using two background models with different adaption rates. Experimental results show that the proposed algorithm outperforms several state-of-art approaches and provides low computational cost.

2D-to-3D conversion has been studied over past decades and integrated to commercial 3D displays and 3DTVs. Generally, depth cues extracted from a static image are used for generating a depth map followed by depth image-based rendering for producing a stereoscopic image. Further, the motion has been considered as an important cue for motion depth estimation. In most works, motion estimation has relied on block-based motion estimation, optical flows, and their variants even though they provide inaccurate data and high computation time, posing performance bottleneck. These problems by proposing Motion History Image-based motion depth estimation method are addressed. Experimental results show that the proposed method is not only faster than the conventional methods but also outperforms them in terms of motion depth estimation.

Depth from defocus (DFD) technique calculates the blur amount in images considering that the depth and defocus blur are related to each other. Existing DFD methods generally compute the blur at edge locations and solve an optimisation problem to propagate the blur from edges to all image pixels. Solving the pixel-based optimisation problem is time-consuming, posing the performance bottleneck. Moreover, the generated depth maps are not consistent in textured areas and the blur estimation may be incorrect in the regions with soft shadows. We address these problems by proposing a superpixelbased blur estimation method. Experimental results show that the proposed method is not only faster than pixel-based blur estimation, but also can improve depth data in textured regions and soft shadows.