The Learning-Based Multimedia (LBMM) Lab focuses on research projects for a wide range of mobile computer vision and medical imaging applications. Our current research directions include:


Mobile Computer Vision: There is an explosive demand of running computer vision (CV) algorithms on low power mobile devices, such as smartphones and small drones. However, most existing CV algorithms are either too computational expensive for mobile devices or lack sufficient robustness to provide a satisfactory user experience. We focus on: 1) designing new light-weight and robust algorithms, and 2) adapting existing algorithms to mobile CPU, GPU, and hardware accelerators for fundamental computer vision components, such as feature extraction, recognition and tracking, etc.

Electrical and Computer Engineering
University of California, Santa Barbara
Trailer 699-102, CA, 93106
Phone:(805) 893-4852
Fax:(805) 893-3262

Heterogeneous Mobile Computing: Mainstream mobile application processors (AP) are accelerator-rich, heterogeneous multi-core SoCs. It provides high computing capability with ultra-low power consumption, yet mapping algorithms to such platforms is a challenge task due to a huge and complex design space. We are developing methods to guide the app developers to explore smart utilization of platform's computing resource and to adapt algorithms for energy minimization.


Computer-Aided Medical Image Analysis: Medical imaging techniques in diagnostics yield significant amount of information, while it is challenging for radiologists to analyze and evaluate such information accurately and efficiently. We have been developing computer-aided methods and tools for medical image analysis including 3D cerebral vessel segmentation and aneurysm detection and automatic renal compartment segmentation for Dynamic Contrast-Enhanced MRI (DCE-MRI) images.

Course on Mobile Embedded Systems:

ECE150/251: Mobile Embedded Systems: Architectures, Applications and Software Development

Professor Cheng has moved to Hong Kong University of Science and Technology (HKUST). He is establishing a new lab in HKUST and is currently looking for PhD students with proper computer vision background. If you are interested in pursuing a PhD degree at HKUST, please contact Prof. Cheng for more information.

visitors since October 2006