期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 25, 期 4, 页码 861-873出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2009.2022424
关键词
Computational neuroscience; gist of a scene; image classification; image statistics; landmark recognition; robot localization; robot vision; saliency; scene recognition
类别
资金
- National Science Foundation
- Human Frontier Science Program
- National Geospatial Intelligence Agency
- Defense Advanced Research Projects Agency
We present a robot localization system using biologically inspired vision. Our system models two extensively studied human visual capabilities: 1) extracting the gist of a scene to produce a coarse localization hypothesis and 2) refining it by locating salient landmark points in the scene. Gist is computed here as a holistic statistical signature of the image, thereby yielding abstract scene classification and layout. Saliency is computed as a measure of interest at every image location, which efficiently directs the time-consuming landmark-identification process toward the most likely candidate locations in the image. The gist features and salient regions are then further processed using a Monte Carlo localization algorithm to allow the robot to generate its position. We test the system in three different outdoor environments-building complex (38.4m x 54.86 m area, 13 966 testing images), vegetation-filled park (82.3m x 109.73 m area, 26 397 testing images), and open-field park (137.16 m x 178.31 m area, 34 711 testing images)-each with its own challenges. The system is able to localize, on average, within 0.98, 2.63, and 3.46 m, respectively, even with multiple kidnapped-robot instances.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据