Skip to Content

Image processing

Visual Detection and Recognition of Drug Markers in a Mobile App

Company/Entity: 
contracted by VinciLab Healthcare, S.L.

C.V.G.-U.P.M. has developed the Image Processing and Pattern Recognition algorithms included in the application  VinciPort® which is  the first mobile app for drug detection,  contracted by VinciLab Healthcare, S.L. (www.vincilab.com)

Until now drug dconsupmtion has been detected manually and only very recently some companies have start to automatize this process with very costly and non-portable devices.

Starting date: 
March 2013
Finishing date: 
August 2013

A Visual System for Autonomous Air-to-Air Refuelling Tasks

A Visual System for Autonomous Air-to-Air Refuelling Tasks
A hierarchical visual tracking algorithm is proposed and developed for the purposes of tracking a drogue during the capture stage of autonomous aerial refuelling, and of estimating its 3D position.
Views

 

A hierarchical visual tracking algorithm is proposed and developed for the purposes of tracking a drogue during the capture stage of autonomous aerial refuelling, and of estimating its 3D position.

Researches: 

UAS See-and-Avoid using two different approaches of Fuzzy Control

Publication
UAS See-and-Avoid using two different approaches of Fuzzy Control
This work presents two UAS See and Avoid approaches using Fuzzy Control. We compare the performance of each controller when a Cross-Entropy method is applied to optimase the parameters for one of the controllers. Each controller receive information from an image processing frontend that detect and track targets in the environment. Visual information is then used under a visual servoing approach to perform autonomous avoidance. Experimental flight trials using a small quadrotor were performed to validate and compare the behaviour of both controllers.
Congresses name: 

2012 International Conference on Unmanned Aircraft Systems (ICUAS'12)

Place: 

Philadelphia, PA, USA

Date: 
June 12-15, 2012

Visual Registration and Mosaic for Unmanned Aerial Vehicle

Visual Registration and Mosaic for Unmanned Aerial Vehicle
Unmanned Aerial Vehicles (UAVs) always execute the tasks in the Unknown Envrionments, such as Inside of Building and Outside of (High) Terrains, however, the whole informations, such as Obstacles and Special Targets in different direction and distance(depth of image), about these unknown envrionments can help UAVs to carry out the tasks autonomously better or operators to make a better decision for the whole task, and the Field of View (FOV) for camera also always small, it means that UAV often just show the local environment using just one camera, however, the Registration and Mosaic algorithms can solve this limitation in order to obtain a much larger FOV.
Views

    Unmanned Aerial Vehicles (UAVs) always execute the tasks in the Unknown Envrionments, such as Inside of Building and Outside of (High) Terrains, however, the whole informations, such as Obstacles and Special Targets in different direction and distance(depth of image), about these unknown envrionments can help UAVs to carry out the tasks autonomously better or operators to make a better decision for the whole task, and the Field of View (FOV) for camera also always small, it means that UAV often just show the local environment using just one camera, however, the Registration and Mosaic algorithms can solve this limitation in order to obtain a much larger FOV.

Abstract:

Researches: 

Vision-based pose estimation using 3D markers

Vision-based pose estimation using 3D markers
Sometimes, UAVs fly in GPS-denied environments, where there is no easy way for them to determine their own pose, relative to their surroundings. This research line tries to address this problem using visual information from an onboard camera.
Views

Unmanned Aerial Vehicles (UAVs) already have many applications and, as a good platform for service robotics, their number is rapidly increasing. Sometimes, UAVs must fly in GPS-denied environments, where there is no easy way for them to determine their own pose, relative to their surroundings. This research line tries to address this problem using visual information from an onboard camera.

Researches: 

A Multi-resolution Image Alignment Technique Based on Direct Methods for Pose Estimation of Aerial Vehicles

Publication
A Multi-resolution Image Alignment Technique Based on Direct Methods for Pose Estimation of Aerial Vehicles
In this paper, we seek to expand the use of direct methods in real-time applications by proposing a vision-based strategy for pose estimation of aerial vehicles. The vast majority of approaches make use of features to estimate motion. Conversely, the strategy we propose is based on a MR (Multi-Resolution) implementation of an image registration technique (Inverse Compositional Image Alignment ICIA) using direct methods. An on-board camera in a downwards-looking configuration, and the assumption of planar scenes, are the bases of the algorithm. The motion between frames (rotation and translation) is recovered by decomposing the frame-to-frame homography obtained by the ICIA algorithm applied to a patch that covers around the 80% of the image. When the visual estimation is required (e.g. GPS drop-out), this motion is integrated with the previous known estimation of the vehicles' state, obtained from the on-board sensors (GPS/IMU), and the subsequent estimations are based only on the vision-based motion estimations. The proposed strategy is tested with real flight data in representative stages of a flight: cruise, landing, and take-off, being two of those stages considered critical: take-off and landing. The performance of the pose estimation strategy is analyzed by comparing it with the GPS/IMU estimations. Results show correlation between the visual estimation obtained with the MR-ICIA and the GPS/IMU data, that demonstrate that the visual estimation can be used to provide a good approximation of the vehicle's state when it is required (e.g. GPS drop-outs). In terms of performance, the proposed strategy is able to maintain an estimation of the vehicle's state for more than one minute, at real-time frame rates based, only on visual information.
Congresses name: 

International Conference on Digital Image Computing: Techniques and Applications

Place: 

Noosa, Queensland Australia

Date: 
2011, December, 6-8

Abstract- In this paper, we seek to expand the use of direct methods in real-time applications by proposing a vision-based strategy for pose estimation of aerial vehicles. The vast majority of approaches make use of features to estimate motion. Conversely, the strategy we propose is based on a MR (Multi-Resolution) implementation of an image registration technique (Inverse Compositional Image Alignment ICIA) using direct methods. An on-board camera in a downwards-looking configuration, and the assumption of planar scenes, are the bases of the algorithm.

Multi-rotors UAV for hydrothermal alterations in the Costa Rica Volcanic Mountains

Company/Entity: 
U.P.M. y U. de Costa Rica

PARTNERS

Computer Vision Group at U.P.M. 

Hidrobiology Group at U.P.M.

Topography and Geomatic at U.P.M.

University of Costa Rica

Starting date: 
2011-02-01
Finishing date: 
2012-01-31
Publication
mini UAV inspecting the Poas Vulcan in Costa Rica
The Pelican UAV has successfully accomplished several flights over three different Vulcans in Costa Rica (Turrialba, Poas and Irazu), aimed to inspect the changing hydrothermal conditions affected by the vulcanos .

Hierarchical Multi-Parametric and Multi-Resolution Strategy (HMPMR) for Tracking

Hierarchical Multi-Parametric and Multi-Resolution Strategy (HMPMR) for Tracking
A strategy for improving the object tracking problem using direct methods and achieving real-time frame rates is proposed. The algorithm is based on a hierarchical strategy in terms of image resolution and number of parameters estimated in each resolution, that we call H_MPMR.
Views


A strategy for improving the object tracking problem using direct methods is proposed. It is focused on being robust under partial occlusions, large frame to frame motions, vibrations, and 3D changes, accomplishing the tracking task at real-time frame rates.

"On-board and Ground Visual Pose Estimation Techniques for UAV Control"

Publication
On-board and Ground Visual Pose Estimation Techniques for UAV Control
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 on-board 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. Both strategies are tested with a VTOL (Vertical take-off and landing) UAV, and results show good behavior of the visual systems (precision in the estimation and frame rate) when estimating the helicopter’s position and using the extracted information to control the UAV.
Journal: 
Journal of Intelligent & Robotic Systems

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

Paper reference: 
Volume 61, Issue 1-4, Pages 301-320. DOI: 10.1007/s10846-010-9505-9
Publication Date: 
MARCH 2011

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 on-board 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.

"Fuzzy Controller for UAV-landing task using 3D-position Visual Estimation."

Publication
Autolanding succeful test publish in the last IEEE-WCCI International Congress at Barcelona
A Fuzzy controller was used to control the altitutude of the helicopter using the visual information obtained by the homography estimation of a helipad.
Congresses name: 

IEEE World Congress on Computational Intelligence (IEEE WCCI 2010-IEEEFUZZ2010).

Place: 

Barcelona, Spain.

Date: 
July 18-23, 2010.

 Abstract. In this paper is presented an application of a Fuzzy Controller for a landing task of an Unmanned Aerial Vehicle using the 3D-position estimation based on visual tracking of piecewise planar objects. This application allows the UAV to land on scenarios in which it is only possible to use visual information to obtain the position of the vehicle. The uses of the homography allows a realtime estimation of the UAV’s pose with respect to an helipad using a monocular camera.

Syndicate content