Evaluation of 3D CNN Semantic Mapping for Rover Navigation
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 32-36
Abstract
Terrain assessment is a key aspect for autonomous exploration rovers, surrounding environment recognition is required for multiple purposes, such as optimal trajectory planning and autonomous target identification. In this work we present a technique to generate accurate three-dimensional semantic maps for Martian environment. The algorithm uses as input a stereo image acquired by a camera mounted on a rover. Firstly, images are labeled with DeepLabv3+, which is an encoder-decoder Convolutional Neural Networl (CNN). Then, the labels obtained by the semantic segmentation are combined to stereo depth-maps in a Voxel representation. We evaluate our approach on the ESA Katwijk Beach Planetary Rover Dataset.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- SPOC: Deep Learning-based Terrain Classification for Mars Rover Missions2016
- Uncertainty comparison of three visual odometry systems in different operative conditionsMeasurement, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fully convolutional networks for semantic segmentation2015
- Traverse Performance Characterization for the Mars Science Laboratory RoverJournal of Field Robotics, 2013
- Autonomy for Mars Rovers: Past, Present, and FutureComputer, 2008
- Accurate and Efficient Stereo Processing by Semi-Global Matching and Mutual Information2005
- Probabilistic roboticsCommunications of the ACM, 2002
- MLESAC: A New Robust Estimator with Application to Estimating Image GeometryComputer Vision and Image Understanding, 2000