Skip to Content

Image processing

"Onboard and Ground Visual Pose Estimation Techniques for UAV Control"

Publication
Congresses name: 

The 3rd International Symposium on Unmanned Aerial Vehicles (UAV’10).

Place: 

Dubai, Arab Emirates.

Date: 
June 21-23, 2010.

 Abstract :  In this paper two techniques to control UAVs (Unmanned Aerial Vehicles) based on visual information are presented. The first one is based on the detection and tracking of planar structures from an onboard camera, while the second one is based on the detection and 3D reconstruction of the position of the UAV based on an external camera system.

Optical flow (sparse L-K) and features based matching methods

Optical flow (sparse L-K) and features based matching methods
Optical Flow and features based matching methods are used on different methods like visual tracking and servoing, homography calculation, video stabilization and mosaics building among others.
Views

 

Optical Flow and features based matching methods are used on different methods like visual tracking and servoing, homography calculation, video stabilization and mosaics building among others. 

 

We use a sparse pyramidal Lucas Kanade optical flow, as well as matching method using SURF keypoints and SURF features. 

"Trinocular Ground System to Control UAVs"

Congresses name: 

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Place: 

St Louis, USA.

Date: 
Oct 11-15,2009.

 Abstract. In this paper we introduce a real-time trinocular system to control rotary wing Unmanned Aerial Vehicles based on the 3D information extracted by cameras located on the ground. The algorithm is based on key features onboard the UAV to estimate the vehicle’s position and orientation.

Catadioptric System and Omnidirectional vision

Catadioptric System and Omnidirectional vision
Catadioptric system is a method used on robotics in order to extend the field of view given by conventional cameras. It is achieved using conic mirrors with know properties (hyperbolic, parabolic and spheric shapes) and the use of the geometric properties, in order to obtain clear images that can be modeled through the unitary sphere model.
Views


Catadioptric system is a method used  on robotics in order to extend the field of view given by conventional cameras. It  is achieved using conic mirrors with know properties (hyperbolic, parabolic and spheric shapes) and the use of the geometric properties, in order to obtain clear images that can be modeled through the unitary sphere model.

 

Color-based feature extraction and tracking

Color-based feature extraction and tracking
Color features are used as key points to detect objects of interest based on the HSV color space and the CamShift [GaryBradski1998] algorithm. The algorithms have been tested in non-controlled environments -outdoors-, with illumination changes, and in controlled environments.
Views

Color features are used as key points to detect objects of interest based on the HSV color space and the CamShift [GaryBradski1998] algorithm.

The algorithms have been tested in non-controlled environments -outdoors-, with illumination changes, and in controlled environments.

"A pan-tilt camera Fuzzy vision controller on an unmanned aerial vehicle"

Congresses name: 

The 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Place: 

St Louis, USA.

Date: 
Oct 11-15,2009.

 Abstract. This paper presents an implementation of two Fuzzy Logic controllers working in parallel for a pan-tilt camera platform on an UAV. This implementation uses a basic Lucas-Kanade tracker algorithm, which sends information about the error between the center of the object to track and the center of the image, to the Fuzzy controller.

"Visual Servoing using Fuzzy Controllers on an Unmanned Aerial Vehicle"

Congresses name: 

EUROFUSE 2009. Workshop on on preference modelling and decision analysis.

Place: 

Pamplona, Spain.

Date: 
16-18 September, 2009.

 Abstract. This paper presents an implementation of three Fuzzy Logic controllers working in parallel onboard a UAV, two for a pan-tilt camera platform and the third for control the yaw of the helicopter. This implementation uses a Lucas-Kanade tracker algorithm with a pyramidal optical  flow implementation, which gives information to follow statics and moving objects, besides the UAV vibrations and movements.

"Visual 3-D SLAM from UAVs"

Journal: 
Journal of Intelligent and Robotic Systems

0921-0296

Paper reference: 
3DSLAM
Publication Date: 
15/01/2009

 Abstract  The aim of the paper is to present, test and discuss the implementation of Visual SLAM techniques to images taken from Unmanned Aerial Vehicles (UAVs) outdoors, in partially structured environments. Every issue of the whole process is discussed in order to obtain more accurate localization and mapping from UAVs flights.

"Computer Vision Onboard UAVs for civilian tasks"

Journal: 
Journal of Intelligent and Robotic Systems

ISSN: 0921-0296 (Print) 1573-0409 (Online).

Paper reference: 
Volume 54, Numbers 1-3, pages 105-135. DOI 10.1007/s10846-008-9256-z.
Publication Date: 
07/07/2008

 Abstract. Computer vision is much more than a technique to sense and recover environmental information from an UAV. It should play a main role regarding UAVs’ functionality because of the big amount of information that can be extracted, its possible uses and applications, and its natural connection to human driven tasks, taking into account that vision is our main interface to world understanding.

"Visually Guiding Autonomous Helicopters for Civilian Tasks"

Congresses name: 

Proceedings of Innovation in UAS.

Place: 

Universidad Politécnica de Madrid. Madrid-Spain

Date: 
Nov 15-17, 2007.
Syndicate content