Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Xiong Zhihui is active.

Publication


Featured researches published by Xiong Zhihui.


workshop on digital media and its application in museum heritages | 2007

Multi-perspective Panorama Based on the Improved Pushbroom Model

Wang Wei; Gao Hui; Zhang Maojun; Xiong Zhihui

A novel approach of multi-perspective panorama (route panorama) auto-generating is presented, which is based on the integration of pushbroom model and perspective projection model. This method can avoid objects distortion and information loss caused by the rate change of the moving camera and/or the camera carrier. Further more, this method has overcome various unstabilizing factors through stability analysis and processing. Therefore, we can generate smooth MPP more easily. The experiment shows that our approach has lower demand for video/image capturing device and capturing environment, and has some advantages in imaging characteristics compared with other available approaches.


cyberworlds | 2008

View Synthesis for Virtual Walk through in Real Scene Based on Catadioptric Omnidirectional Images

Chen Wang; Xu Wei; Xiong Zhihui; Zhang Maojun

This paper proposes an approach to more conveniently and efficiently create virtual walk through in real scene from catadioptric omni directional images via view synthesis. Acquisition and unwarping process of omnidirectional image are discussed firstly, then, according to the speciality of cylindrical panoramic image, we utilize the advantage of epiline-sampling method for cylindrical image, which samples reference images along epilines as much as possible grounding on epipolar geometry. As to novel view generation after image rectification, a corresponding interpolation algorithm based on rectified images is developed. Results of proposed approach applied to both synthetic and real scene are given at the end of this paper. Experiments show that our method can reduce distortion and pixel information losing from image rectification obviously meanwhile maintain scene information well.This paper proposes an approach to more conveniently and efficiently create virtual walk through in real scene from catadioptric omni directional images via view synthesis. Acquisition and unwarping process of omnidirectional image are discussed firstly, then, according to the speciality of cylindrical panoramic image, we utilize the advantage of epiline-sampling method for cylindrical image, which samples reference images along epilines as much as possible grounding on epipolar geometry. As to novel view generation after image rectification, a corresponding interpolation algorithm based on rectified images is developed. Results of proposed approach applied to both synthetic and real scene are given at the end of this paper. Experiments show that our method can reduce distortion and pixel information losing from image rectification obviously meanwhile maintain scene information well.


Archive | 2013

Method for defogging single images based on Bayer formats rapidly

Zhang Maojun; Xiong Zhihui; Lou Jingtao; Bao Weidong; Tan Shuren; Wang Wei; Xu Wei; Liu Yu; Wang Bin; Chen Lidong


Archive | 2013

Multi-image seamless splicing method and apparatus taking panoramic image as reference

Zhang Maojun; Wang Wei; Xiong Zhihui; Xu Wei; Chen Jie; Lai Shiming


Archive | 2008

Catadioptric Omni-directional Stereo Vision and Its Applications in Moving Objects Detection

Xiong Zhihui; Chen Wang; Zhang Maojun


Archive | 2014

Overlap structural deformation-based video real-time stitching method

Xu Wei; Zhang Maojun; Wang Wei; Li Jing; Tan Shuren; Xiong Zhihui; Liu Yu; Zhang Zheng; Yin Xiaoqing; Peng Yang


Archive | 2013

Time-space condition information based moving object detection method

Bao Weidong; Xiong Zhihui; Wang Bin; Tan Shuren; Liu Yu; Wang Wei; Xu Wei; Chen Lidong; Zhang Maojun


Archive | 2013

Linkage browse method for panoramic speed dome all-in-one machine

Zhang Maojun; Liu Yu; Xu Wei; Tan Shuren; Wang Wei; Xiong Zhihui; Chen Lidong; Bao Weidong; Shi Hao


Archive | 2015

Pedestrian detection model training method based on AdaBoost classifier

Xiong Zhihui; Zhang Maojun; Wang Wei; Xu Wei; Lai Shiming; Gao Chenxu


Archive | 2014

Video de-noising method based on structure tensor and Kalman filtering

Liu Yu; Zhang Maojun; Wang Wei; Xiong Zhihui; Zuo Chenglin; Li Weili

Collaboration


Dive into the Xiong Zhihui's collaboration.

Top Co-Authors

Avatar

Zhang Maojun

National University of Defense Technology

View shared research outputs
Top Co-Authors

Avatar

Wang Wei

National University of Defense Technology

View shared research outputs
Top Co-Authors

Avatar

Xu Wei

National University of Defense Technology

View shared research outputs
Top Co-Authors

Avatar

Tan Shuren

National University of Defense Technology

View shared research outputs
Top Co-Authors

Avatar

Liu Yu

Dalian Maritime University

View shared research outputs
Top Co-Authors

Avatar

Li Jing

Chinese Academy of Sciences

View shared research outputs
Top Co-Authors

Avatar

Chen Wang

National University of Defense Technology

View shared research outputs
Top Co-Authors

Avatar

Gao Hui

National University of Defense Technology

View shared research outputs
Top Co-Authors

Avatar

Zhou Tao

National University of Defense Technology

View shared research outputs
Top Co-Authors

Avatar

Li Guohui

National University of Defense Technology

View shared research outputs
Researchain Logo
Decentralizing Knowledge