Project

CV Project 1:  Intelligent scissor

Function: Cut the image like Photoshop, i.e.find some certain contour on the image, and get the image with contour and mask.

Main algorithm: Shortest path by Dijkstra.

source code: https://github.com/qintony/intelligent-scissor

CV Project 2:  face detection

Function: Cut the image like Photoshop, i.e.find some certain contour on the image, and get the image with contour and mask.

Main step: get_positive_features.m, extract HOG descriptor
get_random_negative_features.m, extract HOG descriptor
train SVM

source code: https://github.com/qintony/facedetect

 

CV Project 4:  photometric stereo

This is a project on photometric stereo reconstruction. An object is observed by a fixed camera under different illumination. So we have a dense set of images to start with. The challenge is to infer a 2.5D surface description of the object (that is, a depth model), despite that the captured data are severely contaminated by shadows, highlights, transparency and that the light calibration is inaccurate. The steps of the project are:

Initial normal estimation

Normal refinement by MRF using graph cuts

Depth reconstruction by shape-from-shapelets

source code: https://github.com/qintony/photometric_stereo

Mind controlled aerial robots

tools: Emotive and AR drone;