Visual SLAM for Automated Driving: Exploring the Applications of Deep Learning

By Stefan Milz, Georg Arbeiter, Christian Witt, Bassam Abdallah, Senthil Kumar Yogamani. 2018

103 citations recorded by the source corpus.

Deep learning has become the standard model for object detection and recognition. Recently, there is progress on using CNN models for geometric vision tasks like depth estimation, optical flow prediction or motion segmentation. However, Visual SLAM remains to be one of the areas of automated driving where CNNs are not mature for deployment in commercial automated driving systems. In this paper, we explore how deep learning can be used to replace parts of the classical Visual SLAM pipeline. Firstly, we describe the building blocks of Visual SLAM pipeline composed of standard geometric vision tasks. Then we provide an overview of Visual SLAM use cases for automated driving based on the authors' experience in commercial deployment. Finally, we discuss the opportunities of using Deep Learning to improve upon state-of-the-art classical methods.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, 3D Vision & Pose, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

In Robotics & Control

Citations in the corpus

WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving (2019, background): “Visual Odometry (VO) is necessary for creating a map from the objects detected [38].”
Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, background): “Mapping is one of the key pillars of automated driving [10].”
F-LOAM : Fast LiDAR Odometry and Mapping (2021, background): “such as autonomous driving [2], drone inspection [3], and warehouse manipulation [4].”
Synthetic Data for Deep Learning (2019, background): “Possible applications include SLAM, motion planning, and motion for control for self-driving cars (urban navigation) [177, 346, 411, 435], unmanned aerial vehicles [11, 126, 305], and more; see also general surveys of computer vision for mobile robot navigation [68,142] and perception and control fo”
All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity, Virtual Ecosystem, and Research Agenda (2021, unknown): “Although recently, convolutional neural networks (CNNs) have been applied to visual SLAM and achieved promising performance for autonomous driving with GPUs [309], it is still challenging to apply to resource-constrained mobile systems.”
NeurAll: Towards a Unified Visual Perception Model for Automated Driving (2019, background): “[20] provide a detailed overview of current applications of and future directions for CNN based Visual SLAM for automated driving.”
NeurAll: Towards a Unified Model for Visual Perception in Automated Driving (2019, background): “Milz et al. [21] provide a detailed overview of current applications of and future directions for CNN based Visual SLAM for automated driving.”