Fast Multiple Objects Detection and Tracking Fusing Color Camera and 3D LIDAR for Intelligent Vehicles

被引：0

作者：

Hwang, Soonmin ^{[1
]}

Kim, Namil ^{[1
]}

Choi, Yukyung ^{[1
]}

Lee, Seokju ^{[1
]}

Kweon, In So ^{[1
]}

机构：

[1] Korea Adv Inst Sci & Technol, Robot & Comp Vis Lab, Dept Elect Engn, Daejeon 305701, South Korea

来源：

2016 13TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS AND AMBIENT INTELLIGENCE (URAI) | 2016年

关键词：

DATMO; Sensor fusion;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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. In our experiments, we show that our framework can achieve the faster speed (similar to 4Hz) than the state-of-the-art methods reported in KITTI benchmark (> 1Hz).

引用

页码：234 / 239

页数：6