Robotics and Computer Vision Laboratory Login  
  Robotics and Computer Vision Laboratory kaist logo
Archive Courses

Publications
Home  >  Research  >  Publications

 
[International Conference] Fast Multiple Objects Detection and Tracking Fusing Color Camera and 3D LIDAR for Intelligent Vehicles
The International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) , August 2016
Download
  URAI2016_DATMO URAI2016_DATMO (6).pdf (2.9M) [106]
   https://sites.google.com/site/smhwangcv/datmo_sensor_fusion [125]
   https://sites.google.com/site/ykchoicv/multispectral [112]
Abstract
For many robotics and intelligent vehicle applications, detection and tracking multiple objects (DATMO) is one of the most important components. However, most of the DATMO applications have difficulty in applying real-world applications due to high computational complexity. In this paper, we propose an efficient DATMO framework that fully employs the complementary information from the color camera and the 3D LIDAR. For high efficiency, we present a segmentation scheme by using both 2D and 3D information which gives accurate segments very quickly. Finally, we show
that our framework is faster (4Hz) than the state-of-theart methods reported in KITTI benchmark (>1Hz) with competitive accuracy.
Notes
This work was supported by the Development of Autonomous Emergency Braking System for Pedestrian Protection project funded by the Ministry of Trade, Industry and Energy of Korea. (MOTIE)(No.10044775)

17-01-06 00:16
 
August 19-22, 2016
 
   
 

Robotics and Computer Vision Laboratory
KAIST | Electrical Engineering | Contact Us | Sitemap