Overview

In the vision lab at the University of Michigan we explore a number of critical problems in the area of computer vision. We focus on the analysis and modeling of visual scenes from static images as well as video sequences. Our research goals include: i) the semantic understanding of materials, objects, and actions within a scene; ii) modeling the spatial organization and layout of the scene and its behavior in time. The algorithms developed in our group enable the design of machines that can perform real-world visual tasks such as autonomous navigation, visual surveillance, or content-based image and video indexing.

Photo Gallery

Here are some highlights from our featured projects:

Monitoring with D4AR (4 Dimensional Augmented Reality) Models Monitoring with D4AR (4 Dimensional Augmented Reality) Models.

Collective Activities Recognition Collective Activities Recognition.

Hierarchical Classification of Images by Sparse Approximation Hierarchical Classification of Images by Sparse Approximation.

Estimating the Aspect Layout of Object Categories Learn more about our Work.

Efficient and Exact Inference using Branch-and-Bound Learn more about our Work.

Semantic Structure From Motion (SSFM) Semantic Structure From Motion.

Multi-target tracking with Single Moving Camera Learn more about our Work.

Articulated Part-based Model for Joint Object Detection and Pose Estimation Learn more about our Work.

A Unified Framework for Multi-Target Tracking and Collective Activity Recognition Learn more about our Work.

Relating Things and Stuff via Object Property Interactions Learn more about our Work.

Created by Wen Cui / Graphics by Laura Leal-Taixe’ / Webmaster: Yingze Bao