Researches

			A Content-Adaptive Resizing Framework for Boosting Computation Speed of Background Modeling Methods The novel content-adaptive resizing framework (CARF) to boost the computation speed of BM methods in high-resolution surveillance videos.
			Spatiotemporal Coherence based Annotation Placement for Surveillance Videos The novel annotation placement approach for revealing information of foreground objects in surveillance videos.
			Event Based Surveillance Video Synopsis Using Trajectory Kinematics Descriptors Video synopsis has been shown its promising perfor-mance in visual surveillance and efficiently reduce the lengths of the surveillance videos.
			USEQ: Ultra-Fast Superpixel Extraction via Quantization & USEAQ: Ultra-fast Superpixel Extraction via Adaptive Sampling from Quantizations The novel superpixel extraction method named USEQ to generate regular and compact superpixels.
			Video Saliency Map Detection by Dominant Camera Motion Removal THE human visual system (HVS) perceives the world and provides visual information for human beings.
			Temporal Color Consistency based Video Reproduction for Dichromats The goal of this research is to reproduce videos to enhance the visibility for color vision deficient viewers and the temporal color consistency has to be guaranteed.
			Image Recoloring for Dichromats Based on Priority Order of Colors This project aims to repaint images to enhance the accessibility for CVD viewers with naturalness preserving.
			Shot Change Detection via Local Keypoint Matching In this paper, we propose an approach to solve this problem based on local keypoint matching of the video frames. Experimental results show that the proposed algorithm is effective for all kinds of shot changes.
			Contrast Context Histogram This paper presents a new invariant local descriptor, contrast context histogram (CCH), for object recognition. It represents the contrast distributions of a local region, and serves as a local distinctive descriptor of this region.
			Helicobacter pylori Diagnosis from Endoscopic Images This study presented a computer-aided diagnosis system to assist physicians to diagnose the existence of Helicobacter pylori ( H. pylori ) from endoscopic images without invasive biopsy during endoscopy.
			Tangible Photo-Realistic Virtual Museum We present a tangible photo-realistic virtual museum system that couples augmented panorama and vision-based tracking with tangible interface to achieve the real-time interaction between the visitor and the exhibitions.
			Two-image Camera Self-Calibration We present an improved algorithm for two-image camera self-calibration and Euclidean structure recovery, where the effective focal lengths of both cameras are assumed to be the only unknown intrinsic parameters.