Semantic 3D Occupancy Mapping through Efficient High Order CRFs

07/24/2017
by   Shichao Yang, et al.
0

Semantic 3D mapping can be used for many applications such as robot navigation and virtual interaction. In recent years, there has been great progress in semantic segmentation and geometric 3D mapping. However, it is still challenging to combine these two tasks for accurate and large-scale semantic mapping from images. In the paper, we propose an incremental and (near) real-time semantic mapping system. A 3D scrolling occupancy grid map is built to represent the world, which is memory and computationally efficient and bounded for large scale environments. We utilize the CNN segmentation as prior prediction and further optimize 3D grid labels through a novel CRF model. Superpixels are utilized to enforce smoothness and form robust P N high order potential. An efficient mean field inference is developed for the graph optimization. We evaluate our system on the KITTI dataset and improve the segmentation accuracy by 10

READ FULL TEXT

page 1

page 3

page 5

page 8

research
02/28/2018

Multimodal Sensor-Based Semantic 3D Mapping for a Large-Scale Environment

Semantic 3D mapping is one of the most important fields in robotics, and...
research
01/04/2020

Visual Semantic SLAM with Landmarks for Large-Scale Outdoor Environment

Semantic SLAM is an important field in autonomous driving and intelligen...
research
03/11/2022

Efficient and Robust Semantic Mapping for Indoor Environments

A key proficiency an autonomous mobile robot must have to perform high-l...
research
09/18/2020

Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation

In this paper, we propose a multi-resolution deep-learning architecture ...
research
07/01/2015

Beyond Semantic Image Segmentation : Exploring Efficient Inference in Video

We explore the efficiency of the CRF inference module beyond image level...
research
03/02/2022

Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications

In this paper, we present a complete pipeline for 3D semantic mapping so...
research
03/07/2018

Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation

We propose an efficient and scalable method for incrementally building a...

Please sign up or login with your details

Forgot password? Click here to reset