Open AccessBook Chapter10.1007/978-3-319-77028-4_73

A Computer Vision Based Algorithm for Obstacle Avoidance

- 16 Apr 2018

- Vol. 738, pp 569-575

TL;DR: An algorithm based on elementary computer vision techniques that allow an UAV to identify obstacles and to avoid them, using only a trivial 5MP camera and applying six mathematical treatments on image is presented.

Abstract: This paper presents the implementation of an algorithm based on elementary computer vision techniques that allow an UAV (Unmanned Aerial Vehicle) to identify obstacles (including another UAV) and to avoid them, using only a trivial 5MP camera and applying six mathematical treatments on image. The proposed algorithm of this paper was applied in a drone in real flight. The algorithm proved to be quite efficient both in identifying obstacles ahead and in transposing the same obstacles. Another interesting result is that the algorithm can identify small mobile obstacles and avoid collisions, for example other drones.

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What are the contributions mentioned in the paper "A computer vision based algorithm for obstacle avoidance (outdoor flight)" ?

This paper presents the implementation of an algorithm based on elementary computer vision techniques that allow an UAV ( Unmanned Aerial Vehicle ) to identify obstacles ( including another UAV ) and to avoid them, using only a trivial camera and applying six mathematical treatments on image.

2. What are the future works in "A computer vision based algorithm for obstacle avoidance (outdoor flight)" ?

It is known that computer vision solutions are very sensitive to changes in lighting, so it would be interesting in future works to test their algorithm in different conditions.

Fig. 5. kernel used by the Blur openCV library function

Fig. 7. Diagram generated by the program rqt graph showing the relevant nodes and topics in the application

Citations

•Journal Article•10.11591/IJRA.V9I4.PP233-243

Tracking for inspection in energy transmission power lines using unmanned aerial vehicles: a systematic review of current and specific literature

Wander M. Martins, +5 more

- 01 Dec 2020

TL;DR: This work aims to analyze research related to the autonomous control of the UAV along the transmission lines through a systematic review of the literature (SRL), apply a viable solution and to verify the possible lacuna in this state of the art.

...read moreread less

•Journal Article•10.1088/1757-899X/928/3/032048

Vision-Based Obstacle Avoidance for Small Drone using Monocular Camera

Retaj Raheem Nhair, +1 more

- 01 Nov 2020

TL;DR: This paper proposes an obstacle avoidance technique for small size drones by using a monocular camera that uses a computer vision technique to determines the free zone along with the obstacle that may cause a crash and send feedback control to the drone.

...read moreread less

Proceedings Article•10.1109/ICOIAS.2019.00036

Quadcopter Obstacle Avoidance and Path Planning Using Flood Fill Method

Sushrut Ranade, +1 more

- 01 Feb 2019

TL;DR: The Flood Fill Method (FFM) was employed for navigating an autonomous quadcopter in a simulated environment created using MATLAB and the proposed method was compared with the traditionally used Potential Field Method.

...read moreread less

Journal Article•10.1080/1206212X.2019.1698694

Relationship between UAVs and Ambient objects with threat situational awareness through grid map-based ontology reasoning

MyungJoong Jeon, +5 more

- 04 Dec 2019

- International Journal of Computers and A...

TL;DR: This paper proposes a method to achieve threat situation awareness in UAVs based on reasoning of the relationship among objects based on logic of the ontology of objects.

...read moreread less

Proceedings Article•10.1109/CISP-BMEI51763.2020.9263661

An improved SLAM algorithm based on feature contour extraction for camera pose estimation

Jian Zhang, +2 more

- 17 Oct 2020

TL;DR: An improved SLAM algorithm based on feature contour extraction for camera pose estimation is proposed, which has higher accuracy of pose estimation than traditional algorithms.

...read moreread less

References

•Journal Article

Computer vision

Azriel Rosenfeld

- 01 Aug 1988

- Advances in Computers

TL;DR: How the field of computer (and robot) vision has evolved, particularly over the past 20 years, is described, and its central methodological paradigms are introduced.

...read moreread less

Proceedings Article•10.1109/ICCV.2003.1238654

Real-time simultaneous localisation and mapping with a single camera

Davison

- 13 Oct 2003

TL;DR: This work presents a top-down Bayesian framework for single-camera localisation via mapping of a sparse set of natural features using motion modelling and an information-guided active measurement strategy, in particular addressing the difficult issue of real-time feature initialisation via a factored sampling approach.

...read moreread less

2.1K

•Book

Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library

Adrian Kaehler, +1 more

- 14 Dec 2016

TL;DR: Whether you want to build simple or sophisticated vision applications, Learning OpenCV is the book any developer or hobbyist needs to get started, with the help of hands-on exercises in each chapter.

...read moreread less

1.3K

•Book

Machine Vision: Theory, Algorithms, Practicalities

E.R. Davies

- 01 Dec 2004

TL;DR: This work focuses on low-level processing on the three-dimensional world tackling the pespective n-point problem motion invariants and their applications and the need for speed - real-time electronic hardware systems.

...read moreread less

1.3K

Proceedings Article•10.1109/CDC.2013.6760219

Geometric control and differential flatness of a quadrotor UAV with a cable-suspended load

Koushil Sreenath, +2 more

- 01 Dec 2013

TL;DR: A quadrotor with a cable-suspended load with eight degrees of freedom and four degrees underactuation is considered and a coordinate-free dynamic model, defined on the configuration space SE(3)×S2, is obtained by taking variations on manifolds.

...read moreread less

341

A Computer Vision Based Algorithm for Obstacle Avoidance

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions mentioned in the paper "A computer vision based algorithm for obstacle avoidance (outdoor flight)" ?

2. What are the future works in "A computer vision based algorithm for obstacle avoidance (outdoor flight)" ?

Figures

Citations

Tracking for inspection in energy transmission power lines using unmanned aerial vehicles: a systematic review of current and specific literature

Vision-Based Obstacle Avoidance for Small Drone using Monocular Camera

Quadcopter Obstacle Avoidance and Path Planning Using Flood Fill Method

Relationship between UAVs and Ambient objects with threat situational awareness through grid map-based ontology reasoning

An improved SLAM algorithm based on feature contour extraction for camera pose estimation

References

Computer vision

Real-time simultaneous localisation and mapping with a single camera

Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library

Machine Vision: Theory, Algorithms, Practicalities

Geometric control and differential flatness of a quadrotor UAV with a cable-suspended load

Related Papers (5)

Research on UAV Multi-Obstacle Detection Algorithm based on Stereo Vision

Monocular vision-based obstacle detection/avoidance for unmanned aerial vehicles

Obstacle avoidance and distance measurement for unmanned aerial vehicles using monocular vision

Obstacle Avoidance For Unmanned Air Vehicles Using Image Feature Tracking

Image Preprocessing of Obstacle Avoidance for Underground Unmanned Aerial Vehicle Based on Monocular Vision