Yigong Zhang

Face Recognition With Pose Variations and Misalignment via Orthogonal Procrustes Regression

A linear regression-based method is a hot topic in face recognition community. Recently, sparse representation and collaborative representation-based classifiers for face recognition have been proposed and attracted great attention. However, most of the existing regression analysis-based methods are sensitive to pose variations. In this paper, we introduce the orthogonal Procrustes problem (OPP) as a model to handle pose variations existed in 2D face images. OPP seeks an optimal linear transformation between two images with different poses so as to make the transformed image best fits the other one. We integrate OPP into the regression model and propose the orthogonal Procrustes regression (OPR) model. To address the problem that the linear transformation is not suitable for handling highly non-linear pose variation, we further adopt a progressive strategy and propose the stacked OPR. As a practical framework, OPR can handle face alignment, pose correction, and face representation simultaneously. We optimize the proposed model via an efficient alternating iterative algorithm, and experimental results on three popular face databases, such as CMU PIE database, CMU Multi-PIE database, and LFW database, demonstrate the effectiveness of our proposed method.

Dual approximated nuclear norm based matrix regression via adaptive line search scheme

Face recognition with partial occlusion is one of the urgent and challenging problems in the pattern recognition research. Using the Alternating Direction Method of Multipliers (ADMM), the recently proposed nuclear norm based matrix regression model (NMR) has been shown a great potential in dealing with the structural noise. And yet, ADMM needs to bring into an auxiliary variable and only exploits the convexity of NMR. Compared with ADMM, the gradient based methods are simpler. To make use of these methods, this paper considers the Approximated NMR (ANMR) model. Utilizing the singular value shrinkage operator and strong convexity of ANMR, the dual problem of ANMR (DANMR) is derived and a crucial result is obtained: the primal optimal solution of ANMR can be converted as the matrix function associated with the dual optimal solution. Due to the differentiability of DANMR, an adaptive line search scheme is developed to solve it. This approach combines the advantages of the accelerated gradient technique and adaptive parameters updating strategy. Therefore, a convergence rate of O(1/N2) can be guaranteed. Experimental results show the superiority of the proposed algorithm over some existing methods.

When Dijkstra meets vanishing point: a stereo vision approach for road detection

In this paper, we propose a vanishing-point constrained Dijkstra road model for road detection in a stereo-vision paradigm. First, the stereo-camera is used to generate the u- and v-disparity maps of road image, from which the horizon can be extracted. With the horizon and ground region constraints, we can robustly locate the vanishing point of road region. Second, a weighted graph is constructed using all pixels of the image, and the detected vanishing point is treated as the source node of the graph. By computing a vanishing-point constrained Dijkstra minimum-cost map, where both disparity and gradient of gray image are used to calculate cost between two neighbor pixels, the problem of detecting road borders in image is transformed into that of finding two shortest paths that originate from the vanishing point to two pixels in the last row of image. The proposed approach has been implemented and tested over 2600 grayscale images of different road scenes in the KITTI data set. The experimental results demonstrate that this training-free approach can detect horizon, vanishing point, and road regions very accurately and robustly. It can achieve promising performance.

Lidar-based urban road detection by histograms of normalized inverse depths and line scanning

In this paper, we propose to fuse the geometric information of a 3D Lidar and a monocular camera to detect the urban road region ahead of an autonomous vehicle. Our method takes advantage of both the high definition of 3D Lidar data and the continuity of road in image representation. First, we obtain an efficient representation of Lidar data, an organized 2D inverse depth map, by projecting the spatially unorganized 3D Lidar points onto the cameras image plane. The approximate road regions can be quickly estimated by extracting vertical and horizontal histograms of the normalized inverse depths. To accurately find the road area, a row and column scanning strategy is applied in the approximate road region. We have carried out experiments on the public KITTI-Road benchmark, and achieve one of the best performance among the Lidar-based road detection methods without learning procedure.

Maximum clique based RGB-D visual odometry

In this paper, we propose a new feature-point based RGB-D visual odometry approach for estimating the relative camera motion from two consecutive frames. The approach differs from most feature-point based RGB-D visual odometry approaches in two key aspects: (1) we do not directly use point correspondences to compute relative motion, instead, we link each two distinct points to form a line segment, then utilize correspondences of the generated line segments to estimate relative motion; (2) considering the measurement noise of the RGB-D camera, we design a threshold technique to control the size of maximum clique. Several experiments on real-world dataset show that our method achieved improved accuracy when compared with other recent RGB-D based odometry methods.