Tightly-coupled LIDAR and computer vision integration for vehicle detection
- 1 June 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19310587,p. 604-609
- https://doi.org/10.1109/ivs.2009.5164346
Abstract
In many driver assistance systems and autonomous driving applications, both LIDAR and computer vision (CV) sensors are often used to detect vehicles. LIDAR provides excellent range information to different objects. However, it is difficult 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 this paper, a tightly-coupled LIDAR/CV integrated system is proposed for vehicle detection. This sensing system is mounted on the front of a test vehicle, facing forward. The LIDAR sensor estimates possible vehicle positions. This information is then transformed into the image coordinates. different regions of interest (ROIs) in the imagery are defined based on the LIDAR object hypotheses. An Adaboost object classifier is then utilized to detect the vehicle 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. The main contribution of this paper is that the complementary advantages of two sensors are utilized. The LIDAR scanning data are applied for classifier correction. And the output of the Adaboost classifier is used to provide distance and dimension information. Experimental results are presented to illustrate that this LIDAR/CV system is reliable. It can be used in applications such as traffic surveillance and roadway navigation tasks.Keywords
This publication has 11 references indexed in Scilit:
- Radar-Vision Fusion with an Application to Car-Following using an Improved AdaBoost Detection AlgorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A Lidar and Vision-based Approach for Pedestrian and Vehicle Detection and TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Vehicle Detection with Three Dimensional Object ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Vehicle detection combining gradient analysis and adaboost classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- An active trinocular vision system of sensing indoor navigation environment for mobile robotsSensors and Actuators A: Physical, 2005
- Rapid object detection using a boosted cascade of simple featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Vehicle detection fusing 2D visual featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object DetectionPublished by Springer Nature ,2003
- Real-time vehicle following through a novel symmetry-based approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A flexible new technique for camera calibrationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000