Trinh Nguyen Hoang Home Page

Trinh, Hoang

(Vietnamese name: Trịnh Nguyên Hoàng)

PhD in Computer Science

Toyota Technological Institute at Chicago.

About me: I am a Computer Vision and Machine Learning enthusiast with substantial hands-on research experience, who have a great passion for building computer vision systems that work in the real world.

Research interests: Computer Vision, Pattern Recognition, Machine Learning and Robotics

You can find my resumé here: PDF | HTML

My website at IBM is here

Updates:

Jun 21, 2010: Joined IBM Research at T. J. Watson Research Center.

June 2010: Succesfully defended my PhD thesis.

Research Publications and Projects:

Checkout Visual Compliance Detection.
IBM project.

SAFEST: Situation Awareness for Enhanced Safer Transportation.
IBM project.

Human face and facial parts detection and segmentation.
FlashFoto project.

A Machine Learning Approach to Recovery of Scene Geometry from Images.
PhD Thesis, July 2010.

Structure and Motion from Road-Driving Stereo Sequences.
IEEE Workshop on 3D Information Extraction for Video Analysis and Mining - CVPR 2010.

Video 1: The road-driving sequence
Video 2: The depth map
Video 3: Road and sky detection
Video 4: 3D scene reconstruction

Unsupervised Learning of Stereo Vision with Monocular Cues.
(with David McAllester)
BMVC 2009.

This paper was part of a talk given by Prof. David McAllester at MLSS'09.
In this paper we used a modified version of the Stanford Stereo Dataset. You can click to download our training data and the testing data .

Stereo Pair Training of Monocular Depth Estimation.

Efficient Stereo Algorithm using Multiscale Belief Propagation on Segmented Images.
BMVC 2008.

Particle-based Belief Propagation for Structure from Motion and Dense Stereo Vision with unknown camera constraints.
(with David McAllester)
2nd Robot Vision Workshop, Proceedings. Lecture Notes in Computer Science 4931 Springer 2008, ISBN 978-3-540-78156-1.

Contact:

trinhh at us dot ibm dot com

ntrinh at ttic dot edu

Misc. stuff:

Matlab code for Radial Distortion Correction

Matlab code for computing edgemap and 8 edge orientation maps

Links:

Computer Vision conference lists.

Top conferences in Computer Vision.

Some cool and fun lectures given by Christopher Bishop.

Great minds spoken out loud.

Plan your trip within Chicago.

Technology Review published by MIT.

	Checkout Visual Compliance Detection. IBM project.
	SAFEST: Situation Awareness for Enhanced Safer Transportation. IBM project.
	Human face and facial parts detection and segmentation. FlashFoto project.
	A Machine Learning Approach to Recovery of Scene Geometry from Images. PhD Thesis, July 2010.
	Structure and Motion from Road-Driving Stereo Sequences. IEEE Workshop on 3D Information Extraction for Video Analysis and Mining - CVPR 2010. Video 1: The road-driving sequence Video 2: The depth map Video 3: Road and sky detection Video 4: 3D scene reconstruction
	Unsupervised Learning of Stereo Vision with Monocular Cues. (with David McAllester) BMVC 2009. This paper was part of a talk given by Prof. David McAllester at MLSS'09. In this paper we used a modified version of the Stanford Stereo Dataset. You can click to download our training data and the testing data .
	Stereo Pair Training of Monocular Depth Estimation.
	Efficient Stereo Algorithm using Multiscale Belief Propagation on Segmented Images. BMVC 2008.
	Particle-based Belief Propagation for Structure from Motion and Dense Stereo Vision with unknown camera constraints. (with David McAllester) 2nd Robot Vision Workshop, Proceedings. Lecture Notes in Computer Science 4931 Springer 2008, ISBN 978-3-540-78156-1.