The emergence of low cost sensors capable of providing texture and depth information of a scene is enabling the deployment of several applications such as gesture and object recognition and three-dimensional reconstruction of environments. However, commercially available sensors output low resolution data, which may not be suitable when more detailed information is necessary. With the purpose o...

Hand posture estimation attracts researchers because of its many applications. Hand posture recognition systems simulate the hand postures by using mathematical algorithms. Convolutional neural networks have provided the best results in the hand posture recognition so far. In this paper, we propose a new method to estimate the hand skeletal posture by using deep convolutional neural networks. T...

When using a monocular camera for detection or observation, one only obtain two-dimensional information, which is far from adequate surgical robot manipulation and workpiece detection. Therefore, at this scale, obtaining three-dimensional information of the observed object, especially depth estimation surface points each has become key issue. This paper proposes two methods to solve problem def...

We propose a framework for depth estimation from a set of calibrated images, captured with a moving camera with varying parameters. Our framework respects the physical limits of the camera, and considers various effects such as motion parallax, defocus blur, zooming and occlusions which are often unavoidable. In fact, the stereo [1] and the depth from defocus [2] are essentially special cases i...

In order to perceive depth from binocular disparities the visual system has to identify matching features of the two retinal images. Normally, the assigned disparity is unambiguously determined by monocularly visible matching constraints. The assigned disparity is ambiguous when matching is unconstrained, such as when we view an isolated long oblique disparate line. Recently we found that in or...