The Research Group "Artificial Vision Applications (A.V.A.)" is a consolidated group at IMIBIC. It is constituted by 7 PhD researchers in the field of Computer Engineering. The research carried out by our group is both basic and applied. Our applied research focuses on developing solutions of Computer Vision with applications to Biomedicine. All members of the group are professors at the University of Córdoba.
Our two main interests are to address new proposals for basic research in Computer Vision, and to apply its research results to health problems involving the use of medical images.
Computer technologies in the field of Computer Vision have many potential and promising applications in health. Good examples of current trends in the field are Medical robotics and the automatic analysis of the mobility of people affected by different diseases, among many others.
In the last 5 years (2013-17) we have published more than 15 articles in JCR journals specifically in the field of Computer Vision and Pattern Recognition. Most of the publications solve basic research questions that allow developing applications to solve clinical problems. Examples of such application are patenting a human mobility analysis system and creation of a spin-off company to commercialize the product, and the development of the 3D Vision system for the surgical robot called BROCA.
We currently carry out two main projects. The first, of basic research, aims to propose new mechanisms of fusion of visual information (color, texture, key-points...) to improve 3D reconstruction processes. The second project has the objective to develop a vision system, of low cost, to ensure that the position of a patient during radiotherapy sessions is exactly the same as the position of the patient during the TAC session that will take place before the treatment and during which the specific area with tumour to be treated is planned. The vision technology we develop will be able to capture in real time and in an interactive manner the exact position of the patient’s body during the TAC session, and later guide the positioning of the patient for the radiotherapy session, thus avoiding errors in targeting the radiotherapy and radiating health tissue
Our group maintains collaborations with international research groups, including regular research stays by the group members in the different collaborating centers. Some examples of international institutions with which we collaborate are the University of Orebro (Sweden), the Technical University of Munich (Germany), the University of Malta or the INRIA Research Institute (France). In addition, we maintain regular relations with several national companies developing customized vision systems.
Our research in 3D scanning aims to improve current state of the art 3D scanning methods to increase robustness and reduce its price.
We aim to detect and estimate the 2D pose of humans in stereo image pairs from realistic stereo videos.
We develop new methods for Augmented Reality applications.
The goal of this research line is to estimate the 3D location of human body parts in a multi camera setup without using markers.
We aim to automatically recognize person-person interactions. We address this problem by combining visual and audio sources.
Image segmentation and edge detection are necessary steps for analysis shape. Shape of objects contain important information useful to recognize them. However, this information may contain redundant data. Polygonal approximations are an important tool useful for data reduction and object recognition.
Our research in this area aims to recognize individuals by analysing their gait
- Computer vision
- image segmentation
- pattern recognition
- 3D reconstruction
- augmented reality
- human recognition
- human pose estimation
Our website: A.V.A
The website includes detailed information about our research, results, teaching activities, and members of the group. The contact email address for our groups is email@example.com
FOREUM Abstract Award 2019 to Juan Luis Garrido Castro by the Foundation for Research in Rheumatology.