University of California, Riverside

Department of Electrical and Computer Engineering

A Novel LIDAR and Computer Vision Calibration Procedure

A Novel LIDAR and Computer Vision Calibration Procedure


Lili Huang

Department of Electrical Engineering
University California, Riverside

When: Tuesday, March 31, 2009
Time: 2:00pm - 3:00pm
Location: A265 Bourns Hall


During the past decade, new sensing technologies, such as inductive loops, laser range scanners, radar detectors, and computer vision sensors have been greatly enhanced and applied to the Intelligent Transportation System (ITS) area. Among all these sensor systems, computer vision-based approaches as well as LIDAR sensing techniques are the most popular and promising techniques used in ITS for traffic evaluation and management, driver assistance, and other safety related research. LIDAR provides excellent range information to different objects. However, it is difficult for LIDAR to recognize these objects as vehicles from range information alone. On the other hand, computer vision imagery allows for better recognition, but does not provide high-resolution range information. In our research, a tightly-coupled LIDAR/CV integrated system is proposed for detecting vehicles.

First of all, we proposed a unique multi-planar LIDAR and computer vision calibration algorithm. This method only requires the camera and LIDAR to observe a planar pattern at different positions and orientations. The proposed approach consists of two stages: solving a closed-form equation, followed by applying a non-linear algorithm based on a maximum likelihood criterion. Compared with the classical methods which use 'beam-visible' cameras or 3D LIDAR systems, this approach is easy to implement at a low cost. Additionally, computer simulation and real world testing have been carried out to evaluate the performance of this approach.

In the vehicle detection system, a LIDAR sensor mounting on the front bumper is used to estimate possible vehicle positions. This information is then transformed into the image coordinates. Different Regions of Interest (ROI) in the imagery are defined based the LIDAR object hypotheses. An Adaboost object classifier is then utilized to detect vehicles in ROIs. A classifier error correction approach is used to choose an optimal position of the detected vehicle. Finally, the vehicle's position and dimensions are derived from both the LIDAR and image data. In this system, the LIDAR data are applied for classifier correction. Furthermore, the output of the classifier provides distance and dimension information. Experimental results illustrate that this LIDAR/CV system is reliable, and can be used in applications such as traffic surveillance and roadway navigation task.

About the Speaker:

Lili Huang began working in the Transportation System Research Lab (TSR) at CE-CERT in Jul. 2006, doing research in vehicle navigation projects involving multi-planar LIDAR and camera. She graduated from Beijing University of Posts and Communications (BUPT), China with a M.S. degree in Electrical Engineering in Apr. 2004, and is now pursuing a PH.D. in Dept. of Electrical Engineering at University of California, Riverside. Her advisor is Dr. M. Barth. Her research interests include Intelligent Transportation Systems, Computer Vision, and Artificial Intelligence.


More in Colloquia

More Information 

General Campus Information

University of California, Riverside
900 University Ave.
Riverside, CA 92521
Tel: (951) 827-1012

Department Information

Electrical and Computer Engineering
Suite 343 Winston Chung Hall
University of California, Riverside
Riverside, CA 92521-0429

Tel: (951) 827-2484
Fax: (951) 827-2425
E-mail: E-mail/Questions