Zhengyou Zhang

Learn More
We propose a flexible new technique to easily calibrate a camera. It is well suited for use without specialized knowledge of 3D geometry or computer vision. The technique only requires the camera to observe a planar pattern shown at a few (at least two) different orientations. Either the camera or the planar pattern can be freely moved. The motion need not(More)
This paper presents a method to recognize human actions from sequences of depth maps. Specifically, we employ an action graph to model explicitly the dynamics of the actions and a bag of 3D points to characterize a set of salient postures that correspond to the nodes in the action graph. In addition, we propose a simple, but effective projection based(More)
A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense 3-D maps obtained by using a correlation-based stereo system. Geometric matching in general is a difficult unsolved problem in computer vision. Fortunately, in many practical applications, some a priori knowledge exists(More)
Two images of a single scene/object are related by the epipolar geometry, which can be described by a 3×3 singular matrix called the essential matrix if images' internal parameters are known, or the fundamental matrix otherwise. It captures all geometric information contained in two images, and its determination is very important in many applications such(More)
This paper proposes a robust approach to image matching by exploiting the only available geometric constraint, namely, the epipolar constraint. The images are uncalibrated, namely the motion between them and the camera parameters are not known. Thus, the images can be taken by diierent cameras or a single camera at diierent time instants. If we m a k e an(More)
Almost all problems in computer vision are related in one form or an other to the problem of estimating parameters from noisy data. In this tutorial, we present what is probably the most commonly used techniques for parameter es timation. These include linear least-squares (pseudo-inverse and eigen analysis); orthogonal least-squares; gradient-weighted(More)
We propose deeply-supervised nets (DSN), a method that simultaneously minimizes classification error and improves the directness and transparency of the hidden layer learning process. We focus our attention on three aspects of traditional convolutional-neuralnetwork-type (CNN-type) architectures: (1) transparency in the effect intermediate layers have on(More)
This paper describes some of the work on stereo that has been going on at INRIA in the last four years The work has concentrated on obtaining dense accurate and reliable range maps of the environment at rates compatible with the real time constraints of such applications as the navigation of mobile vehicles in man made or natural environments The class of(More)