On the Analysis of the Depth Error on the Road Plane for Monocular Vision-Based Robot Navigation

2013 IEEE International Conference on Automation Science and Engineering (CASE)

et al. 2013

Self Cite

We develop algorithms that can assist robot to perform building exterior mapping, which is important for building energy retrofitting. In this task, a robot needs to identify building facades in its localization and mapping process, which in turn can be used to assist robot navigation. Existing localization and mapping algorithms rely on low level features such as point clouds and line segments and cannot be directly applied to our task. We attack this problem by employing a multiple layer feature graph (MFG), which contains five different features ranging from raw key points to planes and vanishing points in 3D, in an extended Kalman filter (EKF) framework. We analyze how errors are generated and propagated in the MFG construction process, and then apply MFG data as observations for the EKF to map building facades. We have implemented and tested our MFG-EKF method at three different sites. Experimental results show that building facades are successfully constructed in modern urban environments with mean relative errors of plane depth less than 4.66%.

Section: Related Workmentioning

confidence: 99%

Automatic building exterior mapping using multilayer feature graphs

2013 IEEE International Conference on Automation Science and Engineering (CASE)

et al. 2013

Self Cite

“…Depending on the purpose of the system, researchers focus on different aspects such as vision-based navigation [1] in general, simultaneous localization and mapping (SLAM) [2] and visual odometry [3]. In this paper, our work only focuses on visual odometry.…”

Section: Related Workmentioning

confidence: 99%

On the error analysis of vertical line pair-based monocular visual odometry in urban area

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

2009

Self Cite

Abstract-When a robot travels in urban area, Global Positional System (GPS) signals might be obstructed by buildings. Hence visual odometry is a choice. We notice that the vertical edges from high buildings and poles of street lights are a very stable set of features that can be easily extracted. Thus, we develop a monocular vision-based odometry system that utilizes the vertical edges from the scene to estimate the robot egomotion. Since it only takes a single vertical line pair to estimate the robot ego-motion on the road plane, here we model the ego-motion estimation process and analyze how the choice of different vertical line pair impacts the accuracy of the egomotion estimation process. The resulting closed form error model can assist to choose an appropriate pair of vertical lines to reduce the error in computation. We have implemented the proposed method and validated the error analysis results in physical experiments.

“…We have developed appearancebased method [35], investigated how depth error affects navigation [36], and used vertical line segments for visual odometry tasks [37], [38]. In the process, we have realized it is necessary to combine benefits of different features to assist navigation which leads to this work.…”

Section: Related Workmentioning

confidence: 99%

A two-view based multilayer feature graph for robot navigation

2012 IEEE International Conference on Robotics and Automation

et al. 2012

Self Cite

Abstract-To facilitate scene understanding and robot navigation in a modern urban area, we design a multilayer feature graph (MFG) based on two views from an on-board camera. The nodes of an MFG are features such as scale invariant feature transformation (SIFT) feature points, line segments, lines, and planes while edges of the MFG represent different geometric relationships such as adjacency, parallelism, collinearity, and coplanarity. MFG also connects the features in two views and the corresponding 3D coordinate system. Building on SIFT feature points and line segments, MFG is constructed using feature fusion which incrementally, iteratively, and extensively verifies the aforementioned geometric relationships using random sample consensus (RANSAC) framework. Physical experiments show that MFG can be successfully constructed in urban area and the construction method is demonstrated to be very robust in identifying feature correspondence.I. INTRODUCTION When a mobile robot travels in a modern urban environment, the robot often needs visual signals from its onboard camera to assist navigation. A typical modern urban environment is usually rectilinear and consists of many structured objects and distinctive features such as vertical walls, parallel edges, orthogonal planes, etc. Extracting such features from video frames to form a quick scene understanding can directly benefit navigation tasks such as localization, mapping, obstacle avoidance, and motion planning.Here we design a multilayer feature graph (MFG) to facilitate the scene understanding in urban area. Nodes of an MFG are features such as scale invariant feature transformation (SIFT) feature points, line segments, lines, and planes while edges of the MFG represent different geometric relationships such as adjacency, parallelism, collinearity, and coplanarity. MFG also connects the features in two views and the corresponding 3D world coordinate system. Fig. 1 illustrates the MFG in the 3D world coordinate system. We design an MFG construction method using a feature fusion process which incrementally, iteratively, and extensively verifies the aforementioned geometric relationships using random sample consensus (RANSAC) framework.We have implemented MFG construction algorithm and tested it in physical experiments. Results show that MFG can be successfully constructed from raw image data. Since the process utilizes multiple types of geometric relationships,