Abstract:This paper presents a robust real-time rear-view camera based object detection algorithm for backup aid and parking assist applications. The system is capable of handling the challenges of stationary as well as moving objects in rear view of the host vehicle, utilizing a single car-mounted rear-view fish-eye camera.A motion-based and edge-based object detection algorithm was developed in order to detect near distance objects and distant objects respectively. Furthermore, a free-space detection algorithm was de… Show more
“…There are many proposed methods for the first category, such as [ 3 , 4 , 5 , 6 , 7 , 8 ]. Ma et al [ 3 ] proposed an object detection algorithm that uses edges and motion. The motion-information is used to determine the dynamic obstacles and the edge-information is used to determine obstacles.…”
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.
“…There are many proposed methods for the first category, such as [ 3 , 4 , 5 , 6 , 7 , 8 ]. Ma et al [ 3 ] proposed an object detection algorithm that uses edges and motion. The motion-information is used to determine the dynamic obstacles and the edge-information is used to determine obstacles.…”
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.
“…In [3] a system is presented that uses monocular input and egomotion from odometry sensors. The authors in [4] present a system for backup aid that detects obstacles from three independent methods, fused at the output stage. It assumes road boundaries are always within the video image and has some difficulty with false positives due to shadows not being totally eliminated.…”
We present a system for automatically detecting obstacles from a moving vehicle using a monocular wide angle camera. Our system was developed in the context of finding obstacles and particularly children when backing up. Camera viewpoint is transformed to a virtual bird-eye view. We developed a novel image registration algorithm to obtain ego-motion that in combination with variational dense optical flow outputs a residual motion map with respect to the ground. The residual motion map is used to identify and segment 3D and moving objects. Our main contribution is the feature-based image registration algorithm that is able to separate and obtain ground layer ego-motion accurately even in cases of ground covering only 20% of the image, outperforming RANSAC.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.