• Home
  • Search
  • Semantic SLAM based on visual SLAM and object detection
  • Cite Icon1
  • https://doi.org/10.5768/jao202142.0102002Copy DOI Icon

Semantic SLAM based on visual SLAM and object detection

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Semantic information is essential for mobile robots to understand the content of the environment and perform complex tasks. Aiming at the problem that the point clouds constructed by ORB-SLAM2 is too sparse and lacks semantic information, a dense point cloud semantic map of the environment by combining the object detection algorithm with visual SLAM technology was constructed. First of all, the object detection network YOLO v3 and object regularization were used to accurately obtain the 2D label of the object. At the same time, the ORB-SLAM2 algorithm was used to construct the environment's sparse point cloud map. The color image with 2D labels, corresponding depth images, and key frames were used to generate dense point cloud labels with semantic information. Then the graph-based segmentation algorithm was used to segment the dense point cloud, and the point cloud labels were fused with the segmented point cloud so as to construct a dense point cloud semantic map of the environment. The proposed method was tested on the TUM public data set and the experimental results show that the method can construct a better semantic map. Compared with the traditional ORB-SLAM2 algorithm, this system reduces the absolute pose error and absolute trajectory error of the camera by 16.02% and 15.86% respectively, in the process of constructing the map, which improves the mapping accuracy. In order to reduce the storage space of point cloud maps and facilitate mobile robots' navigation and avoidance, the constructed semantic maps are finally converted into octree maps.

Similar Papers
  • PDF
  • Research Article
  • Citations1

Semantic Visual SLAM Algorithm Based on Improved DeepLabV3+ Model and LK Optical Flow

  • Jul 02, 2024
  • Applied Sciences
  • Yiming Li +4
  • Research Article
  • Citations33

Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam.

  • Oct 06, 2022
  • Sensors
  • Ying Sun +9
  • Research Article
  • Citations2

Map construction algorithm based on dense point cloud

  • Oct 29, 2024
  • IET Image Processing
  • Chengjie Liu +4
  • PDF
  • Research Article
  • Citations10

Point clouds segmentation of rapeseed siliques based on sparse-dense point clouds mapping.

  • Jul 14, 2023
  • Frontiers in Plant Science
  • Yuhui Qiao +8
  • Conference Article
  • Citations3

A New Semantic SLAM Mapping Algorithm Based on Improved YOLOv5

  • Oct 23, 2021
  • Weixiang Shen +3
  • Conference Article
  • Citations1

Fast 3D Object Detection with RGB-D Images Using Graph Convolutional Network

  • Jan 09, 2022
  • Masahiro Takahashi +3
  • Research Article
  • Citations2

3D Reconstruction System Based on Multi Sensor

  • Jan 01, 2022
  • International Journal of Advanced Network, Monitoring and Controls
  • Fan Yu +1
  • Research Article
  • Citations1

A Pre-Procession Module for Point-Based Deep Learning in Dense Point Clouds in the Ship Engineering Field

  • Nov 28, 2023
  • Journal of Marine Science and Engineering
  • Shilin Huo +5
  • Conference Article
  • Citations3

Denoising Algorithm Based on Local Distance Weighted Statistics for Photon Counting Lidar Point Data

  • Jul 01, 2019
  • Weiqi Lian +4
  • Conference Article
  • Citations16

DenseFusion: Large-Scale Online Dense Pointcloud and DSM Mapping for UAVs

  • Oct 24, 2020
  • Lin Chen +5
  • Conference Article
  • Citations6

Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

  • Jul 10, 2022
  • Prajval Kumar Murali +3
  • PDF
  • Research Article
  • Citations1

RGB pixel information fusion segmentation of dense point cloud data for transmission and distribution 3D digital corridors

  • Jan 01, 2024
  • Applied Mathematics and Nonlinear Sciences
  • Duanjiao Li +4
  • Research Article
  • Citations8

Deep Learning Based Semantic Labelling of 3D Point Cloud in Visual SLAM

  • Sep 01, 2018
  • IOP Conference Series: Materials Science and Engineering
  • Xuxiang Qi +2
  • Conference Article

GFFS: Gravitational-Force Feature Real Time Segmentation of 3D Point Cloud

  • Apr 14, 2022
  • Chunhao Shi +6
  • Research Article
  • Citations18

A novel point cloud simplification method with integration of multiple-feature fusion and density uniformity

  • Oct 12, 2021
  • Measurement Science and Technology
  • Nuo Chen +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.