Zhengkai Liu

Insignificant shadow detection for video segmentation

To prevent moving cast shadows from being misunderstood as part of moving objects in change detection based video segmentation, this paper proposes a novel approach to the cast shadow detection based on the edge and region information in multiple frames. First, an initial change detection mask containing moving objects and cast shadows is obtained. Then a Canny edge map is generated. After that, the shadow region is detected and removed through multiframe integration, edge matching, and region growing. Finally, a post processing procedure is used to eliminate noise and tune the boundaries of the objects. Our approach can be used for video segmentation in indoor environment. The experimental results demonstrate its good performance.

Indoor shadow detection for video segmentation

To prevent moving cast shadows from being misunderstood as part of moving objects in change detection based video segmentation, this paper proposes a novel approach to cast shadow detection based on the edge and region information in multiple frames. First, an initial change detection mask containing moving objects and cast shadows is obtained. Then, a Canny edge map is generated. After that, the shadow region is detected and removed through multi-frame integration, edge matching and region growing. Finally, a post-processing procedure is used to eliminate noise and tune the boundaries of the objects. Our approach can be used for removing moving cast shadows in indoor environments for better video segmentation. The experimental results demonstrate the good performance of our algorithm.

Spatio-temporal video error concealment using priority-ranked region-matching

When transmitted over error-prone networks, compressed video sequences may be received with errors. In this paper, we propose a priority-ranked region-matching algorithm to recover the lost area of the decoded frames, in which both temporal and spatial correlations of the video sequence are exploited. In the proposed scheme, we first calculate the priorities of all edge pixels of the lost area and generate a priority-ranked region group. Then according to their priorities, the regions in the group will search their best matching regions temporally and spatially. Finally, the lost area is recovered progressively by the corresponding pixels in the matching regions. Experimental results show that the proposed scheme achieves higher PSNR as well as better video quality in comparison with the method adopted in H.264.

Face recognition using neighborhood preserving projections

Subspace learning is one of the main directions for face recognition. In this paper, a novel unsupervised subspace learning method, Neighborhood Preserving Projections (NPP), is proposed. In contrast to traditional linear dimension reduction method, such as principal component analysis (PCA), the proposed method has good neighborhood-preserving property. The central idea is to modify the classical locally linear embedding by introducing a linear transform matrix. The transform matrix is obtained by optimizing a certain objective function. Experimental results on Yale face database and FERET face database show the effectiveness of the proposed method....

Image quality assessment based on energy of structural distortion

Objective image quality assessment (QA), which automatically evaluates the image quality consistently with human perception, is essentially important for numerous image and video processing applications. We propose a new objective QA method for full reference model based on the energy of structural distortion (ESD). Firstly, we collect the characteristics of the structural information by the normalization processing for the reference image. Secondly, the information of ESD is gained by projecting the image onto the characteristic signal of the structural information independently. Finally the objective quality score is obtained by computing the differences of ESD between the reference and distorted images. In this paper, we propose one implementation with simple parameters for our image QA. Experimental results show that the proposed method is well consistent with the subjective quality score.

An attention based spatial adaptation scheme for H.264 videos on mobiles

When browsing videos in mobile devices, people often feel that resolution greatly affects their perceptual experience in the limited screen size. In this paper, an attention based spatial video adaptation scheme is proposed to overcome display constraints by producing the region of interest. According to the size of the target display, we automatically detect and crop the informative region in each frame to generate a smooth sequence. To avoid costly fully encoding operations, we employ a set of transcoding techniques based on the H.264 standard. Experimental results show that this approach not only improves the perceptual quality but also saves the bandwidth and computation, especially for the videos which are not well edited.

Analyzing Pedestrians' Walking Patterns Using Single-Row Laser Range Scanners

We propose a novel system for analyzing pedestrians walking patterns by exploiting single-row laser range scanners that measure distances of surrounding objects by reflecting eye-safe laser beams. A walking model is built in the spatial-temporal domain to describe the periodicity of the movement of the feet, and a mean-shift technique is applied to recover model parameters. Compared with camera-based methods, our system provides a novel technique to analyze the behavior of pedestrians. The experiments show the validity of the algorithm.

Image quality assessment metrics by using directional projection

Objective image quality measure, which is a fundamental and challenging job in image processing, evaluates the image quality consistently with human perception automatically. On the assumption that any image distortion could be modeled as the difference between the directional projection-based maps of reference and distortion images, we propose a new objective quality assessment method based on directional projection for full reference model. Experimental results show that the proposed metrics are well consistent with the subjective quality score.

Fusion of SVD and LDA for face recognition

A face recognition method based on the fusion of linear discriminant analysis (LDA) and singular value decomposition (SVD) is presented. In theory, fusion of different data or classifiers can achieve better performance when they are independent of each other or they can overcome shortcomings of each other. As one of the subspace methods, LDA-based method has a drawback that LDA is sensitive (variant) to translation, rotation and other geometric transforms. SVD-based method, as an algebraic feature extraction approach, has the merit of invariance to translation, rotation and mirror transforms. By combining these two methods, it is expected that better recognition performance can be obtained. Experiment results on ORL face database show the effectiveness of the proposed method.

Off-Line Motion Description for Fast Video Stream Generation in MPEG-4 AVC/H.264

The rate-distortion optimal mode decision as well as motion estimation adopted in H.264 brings a big challenge to real-time encoding and transcoding due to the high computation complexity. In this paper, we propose a hierarchical motion description model to present the motion data of each macroblock (MB) from coarsely to finely. A preprocessing approach is developed to estimate the motion data for each MB at each quality level with regard to its reference quality, its adjacent MBs and the target bit-rate. The resulting motion data can be coded and stored as metadata in a media file or a stream. Moreover, we propose a method to readily extract the specific motion data from the model for each MB at given bit-rates. Experimental results have shown the effectiveness of our proposed motion description model in terms of coding efficiency as well as fast bit-rate adaptation in comparison with that of H.264