Hongping Cai

 

 

Center for Machine Perception,  

Department of Cybernetics,

Faculty of Electrical Engineering,

Czech Technical University

Address:   

 

 

Email:

Karlovo namesti 13,

12135 Praha 2,

Czech Republic

caihongp {at} cmp.felk.cvut.cz

 

NOTE: This is my old CMP webpage. I left CMP in 2013, and now am doing computer vision research in Un. of Bath. My Bath Homepage

I am currently a research fellow in CMP, Czech Technical University in Prague, working with Prof. Jiri Matas and Dr. Tomas Werner. My current research focuses on visual detection and pose estimation of multiple texture-less objects in real time.

Research Interest

Š      Computer vision; machine learning, visual recognition and retrieval; texture-less object detection; shape detection and recognition; local image features; dimensionality reduction; visual codebook learning.

Current Project

Š      EU-project DARWIN (Dexterous Assembler Robot Working with embodied Intelligence)

- Our task in this project is to develop a reliable system for detection and pose estimation of multiple texture-less objects in real time.

                               

- Dataset: CMP-8objs download here  

8 toys with no or little textures are included for training. Each object is placed on a turntable with a black background and captured by a hand-held video camera, covering approximately a hemisphere of views. 60 images, containing multiple objects in arbitrary poses, are used for test. More details

Publication

Texture-less 3D object detection

Š       H. Cai, T. Werner and J. Matas, “Fast detection of multiple texture-less 3-D objects” International Conf. on Computer Vision System (ICVS), July, 2013.  PDFPoster

LDP

Š        H. Cai, K. Mikolajczyk, J. Matas, “Learning linear discriminant projections for dimensionality reduction of image descriptors,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 33(2): 338-352, 2011.  PDF, Matlab code

Š       H. Cai, K. Mikolajczyk and J. Matas. “Learning linear discriminant projections for dimensionality reduction of image descriptors.” British Machine Vision Conference (BMVC), Leeds, UK. vol. 1: 503-512, 2008. PDF

Codebook learning

Š       H. Cai, F. Yan and K. Mikolajczyk. “Learning weights for codebook in image classification and retrieval.” IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, U.S. June 13-18, 2010. PDF,  Poster

Kernel fusion

Š       F. Yan, K. Mikolajczyk, M. Barnard, H. Cai and J. Kittler. “Lp-Norm multiple kernel fisher discriminant analysis for object and image categorization”. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, U.S. June 13-18, 2010. PDF

Affine invariant detector

Š       H. Cai, L. Lei and Y. Su. “An affine invariant region detector using the 4th differential invariant.” IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Patrac, Greece. vol.1: 540-543, 2007. PDF

Airplane detector

- CFF

Š       H. Cai and Y. Su. “Airplane detection in remote sensing image with a circle-frequency filter”. International Conference on Space Information Technology (ICSIT), Nov.19-20, Wuhan, China, 2005. PDF