Topic
Obstacle
About: Obstacle is a research topic. Over the lifetime, 9517 publications have been published within this topic receiving 94760 citations. The topic is also known as: impediment & barrier.
Papers published on a yearly basis
Papers
More filters
•
31 Jul 2006
TL;DR: In this paper, an obstacle detection range is synthesized with an obstacle image imaged by the camera 2 and included in the view point converted image to be in contact therewith.
Abstract: A vehicle surrounding monitoring device include at least one camera 2 installed in an own vehicle to image a video around the own vehicle, an obstacle sensor 3 for detecting an obstacle within an imaging range of the camera 2, a pixel synthesis unit 13 for receiving a camera image imaged by the camera 2 and converting the camera image into a view point converted image seen from a virtual view point above the own vehicle, and a display device 4 for displaying the view point conversion image converted by the pixel synthesis unit 13. Simultaneously when a warning is given by a warning sound upon entry of an obstacle within an obstacle detection range of the obstacle sensor 3, an image of the obstacle detection range is synthesized with an obstacle image imaged by the camera 2 and included in the view point converted image to be in contact therewith.
60 citations
•
21 Apr 1999
TL;DR: In this article, a road-vehicle communication system consisting of a road side machine BSi and a radio machine on the vehicle, and a centralized base station CS2 generates avoidance indication information based on both detected information.
Abstract: PROBLEM TO BE SOLVED: To enable each vehicle to safely and smoothly run autonomously by making a road-side controller and each vehicle requiring avoidance perform the most suitable obstacle avoiding operation in cooperation with each other. SOLUTION: Information of an obstacle detected by a running vehicle MS1 and information of the obstacle detected by a road-side sensor LS are exchanged through an road-vehicle communication system consisting of a road-side machine BSi and a radio machine on the vehicle, and a centralized base station CS2 generates avoidance indication information based on both detected information. The avoidance indication information is reported to vehicles MS1 and MS2 requiring the avoiding operation through the road-vehicle communication system, and thus the vehicle MS1 performs the avoiding operation.
60 citations
•
20 Feb 2003TL;DR: In this article, an obstacle detection device is proposed for a vehicle that detects obstacles using a distance to an object calculated by image processing and a distance calculated by radar ranging, and does not determine the object to be an obstacle when the two amounts of movement are not consistent.
Abstract: An obstacle detection device (10) for a vehicle that detects obstacles using a distance to an object calculated by image processing and a distance to the object calculated by radar ranging. This obstacle detection device (10) includes a measuring means (12,16) for measuring an amount of movement of the object at a predetermined interval of time by image processing and a measuring means (14) for measuring an amount of movement of the object at a predetermined interval of time by radar ranging, and does not determine the object to be an obstacle when the two amounts of movement are not consistent.
60 citations
••
18 Nov 2019TL;DR: A novel deep learning-based sensor fusion framework, termed as the “RVNet”, for the effective fusion of the monocular camera and long-range radar for obstacle detection, which is better than baseline algorithms in varying environmental conditions.
Abstract: Camera and radar-based obstacle detection are important research topics in environment perception for autonomous driving. Camera-based obstacle detection reports state-of-the-art accuracy, but the performance is limited in challenging environments. In challenging environments, the camera features are noisy, limiting the detection accuracy. In comparison, the radar-based obstacle detection methods using the 77 GHZ long-range radar are not affected by these challenging environments. However, the radar features are sparse with no delineation of the obstacles. The camera and radar features are complementary, and their fusion results in robust obstacle detection in varied environments. Once calibrated, the radar features can be used for localization of the image obstacles, while the camera features can be used for the delineation of the localized obstacles. We propose a novel deep learning-based sensor fusion framework, termed as the “RVNet”, for the effective fusion of the monocular camera and long-range radar for obstacle detection. The RVNet is a single shot object detection network with two input branches and two output branches. The RVNet input branches contain separate branches for the monocular camera and the radar features. The radar features are formulated using a novel feature descriptor, termed as the “sparse radar image”. For the output branches, the proposed network contains separate branches for small obstacles and big obstacles, respectively. The validation of the proposed network with state-of-the-art baseline algorithm is performed on the Nuscenes public dataset. Additionally, a detailed parameter analysis is performed with several variants of the RVNet. The experimental results show that the proposed network is better than baseline algorithms in varying environmental conditions.
60 citations
••
TL;DR: This study presents an approach to obstacle detection in a greenhouse environment using the Kinect 3D sensor, which provides synchronized color and depth information and shows that the system produces satisfactory results and is fast enough to run on a limited computer.
59 citations