Abstract
This study proposes an obstacle detection method that uses depth information to allow the visually impaired to avoid obstacles when they move in an unfamiliar environment. The system is composed of three parts: scene detection, obstacle detection and a vocal announcement. This study proposes a new method to remove the ground plane that overcomes the over-segmentation problem. This system addresses the over-segmentation problem by removing the edge and the initial seed position problem for the region growth method using the Connected Component Method (CCM). This system can detect static and dynamic obstacles. The system is simple, robust and efficient. The experimental results show that the proposed system is both robust and convenient.
Highlights
According to new statistics [1], there are 285 million visually impaired people relying on the guide cane or guide dogs to move around freely in the world
The system uses the region growth method to label the tags on different objects and analyzes each object to determine whether the object is a stair
Because pixels that are the same height in a depth map can have a different depth value, the curve becomes a strip, so several approximation targets, such as the minimum, the maximum, the mean and the specific value of every row of V-disparity map are used.When the obstacle is on the ground, these methods do not work
Summary
According to new statistics [1], there are 285 million visually impaired people relying on the guide cane or guide dogs to move around freely in the world. Chen et al [5] proposed an obstacle detection method that uses a saliency map This uses a threshold value to determine the position of the obstacles. Zhang et al [12] proposed an obstacle detection algorithm that uses a U-V disparity map analysis This combines straight-line fitting and the standard Hough Transform [28] to determine the location of obstacles. The method detailed in [34] does not process the ground, but segments object directly to calculate the standard deviation using an object’s depth value and determines whether it is an obstacle using the scale of the object’s standard deviation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.