NeurAll: Towards a Unified Visual Perception Model for Automated Driving

arXiv:1902.03589v3 Announce Type: replace-cross
Abstract: Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc. However, these tasks are typically independently explored and modeled. In this paper, we propose a joint multi-task network design for learning several tasks simultaneously. Our main motivation is the computational efficiency achieved by sharing the expensive initial convolutional layers between all tasks. Indeed, the main bottleneck in automated driving systems is …

abstract arxiv automated automotive cnns convolutional neural networks cs.cv cs.lg cs.ro design driving etc however network networks neural networks object paper perception recognition slam stat.ml tasks type visual visual slam