UAV obstacle detection with bio-motivated computer vision

2021 ◽  
Author(s):  
Mate Petho ◽  
Tamas Zsedrovits
Keyword(s):  
Computer Vision ◽  
Obstacle Detection

scholarly journals Computer vision based obstacle detection and target tracking for autonomous vehicles

2021 ◽  
Vol 336 ◽  
pp. 07004
Author(s):  
Ruoyu Fang ◽  
Cheng Cai
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Target Tracking ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Obstacle Detection ◽  
Pid Algorithm ◽  
Deep Learning Neural Network

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.

scholarly journals Control of a transport robot in extreme weather based on computer vision systems

2021 ◽  
Vol 2131 (3) ◽  
pp. 032027
Author(s):  
A Timofeev ◽  
F Daeef
Keyword(s):  
Computer Vision ◽  
Mobile Robot ◽  
Program Implementation ◽  
Environmental Conditions ◽  
Dynamic Environment ◽  
Video Camera ◽  
Obstacle Detection ◽  
Contour Analysis ◽  
Base Method ◽  
Computer Vision Systems

Abstract This article presents a new way to use special computer vision techniques to aim with assisting in controlling a transport robot in a dynamic environment under exceptional and difficult environmental conditions. An analysis and development of algorithm for obstacle detection in the robot’s environment proposed based on data from an RGB-D video camera using computer vision methods. Contour analysis was the base method to detecting objects featured fragment taking into account difficult vision conditions. Based on open-source library (Open CV), we adopted methods program implementation which confirmed its applicability to detect objects in mobile robot environment.

scholarly journals A New Roadway Eventual Obstacle Detection System Based on Computer Vision

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5109
Author(s):  
Mariano Gonzalez-de-Soto ◽  
Rocio Mora ◽  
José Antonio Martín-Jiménez ◽  
Diego Gonzalez-Aguilera
Keyword(s):  
Computer Vision ◽  
Open Source Software ◽  
Detection System ◽  
Low Cost ◽  
Obstacle Detection ◽  
Road Accidents ◽  
The Past ◽  
Video Images ◽  
Infra Red ◽  
Different Types

A new roadway eventual obstacle detection system based on computer vision is described and evaluated. This system uses low-cost hardware and open-source software to detect and classify moving elements in roads using infra-red and colour video images as input data. This solution represents an important advancement to prevent road accidents due to eventual obstacles which have considerably increased in the past decades, mainly with wildlife. The experimental evaluation of the system demonstrated that the proposed solution detects and classifies correctly different types of moving obstacles on roads, working robustly under different weather and illumination conditions.

scholarly journals Robotic Arm System with Computer Vision for Colour Object Sorting

2018 ◽  
Vol 7 (4.27) ◽  
pp. 50
Author(s):  
Ong Kok Meng ◽  
Ong Pauline ◽  
Low Ee Soon ◽  
Sia Chee Kiong
Keyword(s):  
Computer Vision ◽  
Degrees Of Freedom ◽  
Processing Technique ◽  
Target Object ◽  
Inverse Kinematic ◽  
Obstacle Detection ◽  
Image Processing Technique ◽  
Robotic Arm ◽  
Flower Pollination Algorithm ◽  
Forward Kinematic

This study presents the development of robotic arm with computer vision functionalities to recognise the objects with different colours, pick up the nearest target object and place it into particular location. In this paper, the overview of the robotic arm system is first presented. Then, the design of five-degrees of freedom (5-DOF) robotic arm is introduced, followed by the explanation of the image processing technique used to recognize the objects with different colours and obstacle detection. Next, the forward kinematic modelling of the robotic arm using Denavit-Hartenberg algorithm and solving the inverse kinematic of the robotic arm using modified flower pollination algorithm (MFPA) are interpreted. The result shows that the robotic arm can pick the target object accurately and place it in its particular place successfully. The concern on user safety is also been taken into consideration where the robotic arm will stop working when the user hand (obstacle) is detected and resume its process when there is no obstacle.  

Sign in / Sign up

Export Citation Format

Share Document