6533b820fe1ef96bd127a562

RESEARCH PRODUCT

Gradient-based time to contact on paracatadioptric camera

S. El FkihiDriss AboutajdineCédric DemonceauxEl Mustapha MouaddibFatima Zahra Benamar

subject

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 processing

description

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 gives additional information about the orientation of planar surface. It was tested on simulated and real datasets.

https://doi.org/10.1109/icip.2013.6738002