Allen Y. Yang

Research Engineer, EECS, Berkeley.

PhD, 2006. ECE, University of Illinois at Urbana-Champaign.

A wonderful life is to comfort, but is not comfortable.

Address:	Contact:
Rm 307, Cory Hall UC Berkeley Berkeley, CA 94720	Email: yang AT eecs Office: 510-643-5798 Fax: 510-643-2356

What is New!
IMA Workshop on Multi-Manifold Data Modeling and Applications. October 27-30, 2008.
SIAM Review: Estimation of Subspace Arrangements with Applications in Modeling and Segmenting Mixed Data. [Editorial]
New Patent Application: Improved system for recognition of human actions. [link]
A pop-sci essay: Q&A about recent advances in face recognition and how to protect your facial identity. [PDF] ABC Bay Area News report Wired.com report Nuit Blanche report Rice Compressive Sensing report
New paper: CITRIC: A low-bandwidth wireless camera network platform. ICDSC, 2008. [PDF]
To appear in PAMI: Robust Face Recognition via Sparse Representation. [website]

Research Overview:

Having developed my academic skills during a graduate study at the University of Illinois and a postdoctoral appointment at the University of California, my general research interests encompass three closely related fields: high-dimensional pattern analysis, image and video processing, and heterogeneous sensor networks. To advance our knowledge in these interdisciplinary topics, I seek answers to the following challenging questions:

What is the fundamental limit in the estimation and segmentation of multiple geometric models (e.g., linear subspaces or nonlinear manifolds) in high-dimensional data spaces?
How to harness and effectively solve for sparse representation in a computer-based recognition framework that can provide superior pattern-recognition abilities comparable to human perception on images and videos?
Equipped with a qualified understanding on the above two topics, how should practitioners design efficient recognition algorithms and systems to collectively classify certain events of interest in a heterogeneous sensor network?

These questions fall in an emerging area of distributed pattern recognition. For example, high-bandwidth camera networks have been extensively used in large-scale urban surveillance systems to detect abnormal subjects and activities. In several high-caliber research projects such as the DARPA Grand Challenge, mobile camera sensors have been integrated with other heterogeneous sensors to support intelligent transportation. With the continuing miniaturization of mobile processors and wireless sensors, it has become possible to manufacture wearable motion sensors and biological sensors for health care investigators and clinicians to persistently monitor and analyze human body movements, blood constituents, and respiratory patterns, to name a few. I envision that new, rigorous solutions in distributed pattern recognition shall generate a notable impact to these advanced, real-world applications.

Publications

Presentations

Software

Research Interests:

Pattern Analysis: Mixture-model estimation; Distributed recognition; Compressed sensing.

Computer Vision: Motion segmentation and multiple-view geometry.

Systems: On-demand surveillance via heterogeneous sensor networks.

Current Projects:

d-Oracle: Distributed Object Recognition via a Camera Wireless Net

Harnessing the multiple-view information from a wireless camera sensor network to improve the recognition of objects or actions.

d-WAR: Distributed Wearable Action Recognition

We propose a distributed recognition method to classify human actions using a low-bandwidth wearable motion sensor network. Given a set of pre-segmented motion sequences as training examples, the algorithm simultaneously segments and classifies human actions, and it also rejects outlying actions that are not in the training set. The classification is distributedly operated on individual sensor nodes and a base station computer. Using up to eight body sensors, the algorithm achieves state-of-the-art 98.8% accuracy on a set of 12 action categories. We further demonstrate that the recognition precision only decreases gracefully using smaller subsets of sensors, which validates the robustness of the distributed framework.

Past Projects:

	Feature Selection in Face Recognition: A Sparse Representation Perspective Formulating the problem of face recognition under the emerging theory of compressed sensing, we examine the role of feature selection/dimensionality reduction from the perspective of sparse representation. Our experiments show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical is whether the number of features is sufficient and whether the sparse representation is correctly found.
	Robust Face Recognition with Facial Occlusion
	Image Analysis and Segmentation via Lossy Data Compression
	Generalized Principal Component Analysis (GPCA) An algebraic framework for modeling and segmenting mixed data using a union of subspaces, a.k.a. subspace arrangements. Yet the statistical implementation of the framework is robust to data noise and outliers.
	Symmetry-based 3-D Reconstruction from Perspective Images We investigated a unified framework to extract poses and structures of 2-D symmetric patterns from perspective images. The framework uniformly encompasses all three fundamental types of symmetry: Reflection, Rotation, and Translation, based on a systematic study of the homography groups in image induced by the symmetry groups in space. We claim the following principle: If a planar object admits rich enough symmetry, no 3-D geometric information is lost through perspective imaging.
	RoboTalk A unified robot motion interface and tele-communication protocols for controlling arms, bases, and androids. Copyright (c) Honda Research, Mountain View, CA.

Teaching:

Spring, 2008: Compressed Sensing Meets Machine Learning -- A Mini Course. [lecture 1, lecture 2, lecture 3]
Spring, 2007: Generalized Principal Component Analysis -- A Mini Course. [lecture 1, lecture 2, lecture 3]
Fall, 2006: CS294-6: Theoretical, Conceptual and Experimental Vision.

Life outside Cory

Frankly, Cory Hall feels like a bunker inside out. My phone calls are constantly being cut-off. That is the Berkeleyway saying: Hey, no sweat in an earthquake! :)
I enjoy listening to musical CDs in my apartment from a pair of Paradigm Reference Studio 20 speakers biwired to an NAD C350 amp.
Sometimes in a weekend, I will drive to St. Helena and Rutherford in Napa for a wine tasting.

Links:

		NEC Research Index			SIAM Journals Online

(Last Modified on March. 10, 2008)