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.
	Robust Algebraic Segmentation of Mixed Rigid-Body and Planar Motions in Two Views We study segmentation of multiple rigidbody motions in a 3-D dynamic scene under perspective camera projection. Based on the well-known epipolar and homography constraints between two views, we propose a hybrid perspective constraint (HPC) to unify the representation of rigid-body and planar motions. Given a mixture of K hybrid perspective constraints, we propose an algebraic process to partition image correspondences to the individual 3-D motions, called Robust Algebraic Segmentation (RAS). We conduct extensive simulations and real experiments to validate the performance of the new algorithm. The results demonstrate that RAS achieves notably higher accuracy than most existing robust motion segmentation methods, including random sample consensus (RANSAC) and its variations. The implementation of the algorithm is also two to three times faster than the existing methods.We will make the implementation of the algorithm and the benchmark scripts available on our website.
	CITRIC: A Low-Bandwidth Wireless Camera Network Platform We propose and demonstrate a novel wireless camera network system, called CITRIC.  The core component of this system is a new hardware platform that integrates a camera, a frequency-scalable (up to 624 MHz) CPU, 16 MB FLASH, and 64 MB RAM onto a single device.  The device then connects with a standard sensor network mote to form a camera mote.  The design enables in-network processing of images to reduce communication requirements, which has traditionally been high in existing camera networks with centralized processing. We also propose a back-end client/server architecture to provide a user interface to the system and support further centralized processing for higher-level applications. Our camera mote enables a wider variety of distributed pattern recognition applications than traditional platforms because it provides more computing power and tighter integration of physical components while still consuming relatively little power.  Furthermore, the mote easily integrates with existing low-bandwidth sensor networks because it can communicate over the IEEE 802.15.4 protocol with other sensor network platforms.

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:

(Last Modified on Sep. 18, 2008)