Computer Vision
Computer Vision
Research Area

The computer vision group at HRI is conducting cutting edge research in computer vision, machine learning, and sensor fusion. We develop algorithms and prototype systems for driver assistance and autonomous systems. 

​​​​Using the latest sensor technologies on board of our experimental vehicle, our goals are to self-localize with sufficient accuracy for autonomous navigation and to detect and recognize all traffic participants and relevant infrastructural elements in the scene. To solve these problems, we develop state-of-the-art vision and learning algorithms that are trained and evaluated on  large data sets that have been recorded under a wide variety of conditions.

Projects

The goal of the project is to achieve robust lane-level localization for cars using low cost mass producible sensors.
We have developed online algorithms to transfer motion from a human demonstrator to Honda's humanoid robot, ASIMO.
The goal is to develop driving aids that enhance the driver's situational awareness and give drivers a sense of confidence and trust in the vehicles they are operating.
This project presents a control theoretic approach for human pose estimation from a set of key feature points detected using depth image streams obtained from a time of flight imaging device.
We are developing a real-time system that detects and tracks traffic participants.
We aim to develop a robust pedestrian detection algorithm that can handle partial occlussions.
We are taking advantage of our autonomous driving platform to create a comprehensive repository of annotated sensor data that provide computer vision benchmarks and training data to support advanced driving assist and autonomous driving applications.
Utilizing the latest wearable sensing technologies and patented motion prediction algorithms, the goal is to predict human movement and perform biomechanical computations based on those predictions.