Vis enkel innførsel

dc.contributor.authorKulkarni, Mihir
dc.contributor.authorAlexis, Konstantinos
dc.description.abstractThis paper contributes a novel learning-based method for aggressive task-driven compression of depth images and their encoding as images tailored to collision prediction for robotic systems. A novel 3D image processing methodology is proposed that accounts for the robot's size in order to appropriately "inflate" the obstacles represented in the depth image and thus obtain the distance that can be traversed by the robot in a collision-free manner along any given ray within the camera frustum. Such depth-and-collision image pairs are used to train a neural network that follows the architecture of Variational Autoencoders to compress-and-transform the information in the original depth image to derive a latent representation that encodes the collision information for the given depth image. We compare our proposed task-driven encoding method with classical task-agnostic methods and demonstrate superior performance for the task of collision image prediction from extremely low-dimensional latent spaces. A set of comparative studies show that the proposed approach is capable of encoding depth image-and-collision image tuples from complex scenes with thin obstacles at long distances better than the classical methods at compression ratios as high as 4050:1.en_US
dc.rightsNavngivelse 4.0 Internasjonal*
dc.titleTask-driven Compression for Collision Encoding based on Depth Imagesen_US
dc.title.alternativeTask-driven Compression for Collision Encoding based on Depth Imagesen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.source.journalLecture Notes in Computer Science (LNCS)en_US

Tilhørende fil(er)


Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel

Navngivelse 4.0 Internasjonal
Med mindre annet er angitt, så er denne innførselen lisensiert som Navngivelse 4.0 Internasjonal