Multi-Scale Fully Convolutional Network-Based Semantic Segmentation for Mobile Robot Navigation

In computer vision and mobile robotics, autonomous navigation is crucial. It enables the robot to navigate its environment, which consists primarily of obstacles and moving objects. Robot navigation employing impediment detections, such as walls and pillars, is not only essential but also challengin...

Full description

Saved in:
Bibliographic Details
Published in:Electronics (Basel) 2023-02, Vol.12 (3), p.533
Main Authors: Dang, Thai-Viet, Bui, Ngoc-Tam
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Autonomous navigation
Cameras
Classification
Collision avoidance
Computer networks
Computer vision
Control systems
Datasets
Deep learning
Halls
Image processing
Image segmentation
Machine vision
Mobile computing
Mobile robots
Motion
Neural networks
Object recognition
Obstacle avoidance
Path planning
Pixels
Robot dynamics
Robotics
Robots
Semantic segmentation
Semantics
Sensors
Steering
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In computer vision and mobile robotics, autonomous navigation is crucial. It enables the robot to navigate its environment, which consists primarily of obstacles and moving objects. Robot navigation employing impediment detections, such as walls and pillars, is not only essential but also challenging due to real-world complications. This study provides a real-time solution to the problem of obtaining hallway scenes from an exclusive image. The authors predict a dense scene using a multi-scale fully convolutional network (FCN). The output is an image with pixel-by-pixel predictions that can be used for various navigation strategies. In addition, a method for comparing the computational cost and precision of various FCN architectures using VGG-16 is introduced. The binary semantic segmentation and optimal obstacle avoidance navigation of autonomous mobile robots are two areas in which our method outperforms the methods of competing works. The authors successfully apply perspective correction to the segmented image in order to construct the frontal view of the general area, which identifies the available moving area. The optimal obstacle avoidance strategy is comprised primarily of collision-free path planning, reasonable processing time, and smooth steering with low steering angle changes.
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics12030533