Search results for "mobile robotic"

showing 4 items of 4 documents

Scale invariant line matching on the sphere

2013

International audience; This paper proposes a novel approach of line matching across images captured by different types of cameras, from perspective to omnidirectional ones. Based on the spherical mapping, this method utilizes spherical SIFT point features to boost line matching and searches line correspondences using an affine invariant measure of similarity. It permits to unify the commonest cameras and to process heterogeneous images with the least distortion of visual information.

0209 industrial biotechnologySimilarity (geometry)[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processingmobile roboticComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-invariant feature transformTime to contactmobile robotic.02 engineering and technology[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processingMeasure (mathematics)obstacle avoidance020901 industrial engineering & automation[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processingomnidirectional visionDistortion0202 electrical engineering electronic engineering information engineeringPoint (geometry)Computer visionCollision detectioncollision detectionMathematics[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingbusiness.industryPerspective (graphical)Computer Science::Computer Vision and Pattern RecognitionLine (geometry)020201 artificial intelligence & image processingArtificial intelligencebusiness[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
researchProduct

Gradient-based time to contact on paracatadioptric camera

2013

International audience; The problem of time to contact or time to collision (TTC) estimation is largely discussed in perspective images. However, a few works have dealt with images of catadioptric sensors despite of their utility in robotics applications. The objective of this paper is to develop a novel model for estimating TTC with catadioptric images relative to a planar surface, and to demonstrate that TTC can be estimated only with derivative brightness and image coordinates. This model, called "gradient based time to contact", does not need high processing such as explicit estimation of optical flow and feature detection/or tracking. The proposed method allows to estimate TTC and give…

0209 industrial biotechnology[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processing[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingComputer sciencemobile roboticComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONOptical flowTime to contactmobile robotic.[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processing02 engineering and technologyobstacle avoidanceCatadioptric system020901 industrial engineering & automation[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processingomnidirectional visionObstacle avoidance0202 electrical engineering electronic engineering information engineeringcollision detectionCollision detectionComputer visionImage sensor[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processingFeature detection (computer vision)Orientation (computer vision)business.industryPerspective (graphical)Mobile robot020201 artificial intelligence & image processingArtificial intelligencebusiness[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing2013 IEEE International Conference on Image Processing
researchProduct

Indoor Scene Understanding using Non-Conventional Cameras

2020

Humans understand environments effortlessly, under a wide variety of conditions, by the virtue of visual perception. Computer vision for similar visual understanding is highly desirable, so that machines can perform complex tasks by interacting with the real world, to assist or entertain humans. In this regard, we are particularly interested in indoor environments, where humans spend nearly all their lifetime.This thesis specifically addresses the problems that arise during the quest of the hierarchical visual understanding of indoor scenes.On the side of sensing the wide 3D world, we propose to use non-conventional cameras, namely 360º imaging and 3D sensors. On the side of understanding, …

Intelligence artificielle - Robotique mobile - Vision par ordinateur[INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV]Artificial IntelligenceVision par ordinateur[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Robotique mobile[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionIntelligence artificielleMobile roboticsMobile robotics - Artificial Intelligence - computer vision[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
researchProduct

Deep Reinforcement Learning with Omnidirectional Images: application to UAV Navigation in Forests

2022

Deep Reinforcement Learning (DRL) is highly efficient for solving complex tasks such as drone obstacle avoidance using cameras. However, these methods are often limited by the camera perception capabilities. In this paper, we demonstrate that point-goal navigation performances can be improved by using cameras with a wider Field-Of-View (FOV). To this end, we present a DRL solution based on equirectangular images and demonstrates its relevance, especially compared to its perspective version. Several visual modalities are compared: ground truth depth, RGB, and depth directly estimated from these 360°R GB images using Deep Learning methods. Next, we propose a spherical adaptation to take into …

[INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO]Vision for robotsPerception systemsMobile robotics
researchProduct