Human Pose Recovery and Behavior Analysis

Human Action/Gesture recognition is a challenging area of research that deals with the problem of recognizing people in images, detecting and describing body parts, including hand pose and facial expressions, inferring their spatial configuration, and performing action/gesture recognition from still images or image sequences, also including multi-modal data. Because of huge space of human configurations, body pose recovery is a difficult problem that involves dealing with several distortions: illumination changes, partial occlusions, changes in the point of view, rigid and elastic deformations, or high inter and intra-class variability, just to mention a few. Even with the high difficulty of the problem, modern Computer Vision techniques and new tendencies deserve further attention, and promising results are expected in the next years. Moreover, several subareas have been recently defined, such as Affective Computing, Social Signal Processing, Human Behavior Analysis, or Social Robotics. The effort involved in this area of research will be compensated by its potential applications: social robotics, TV production, home entertainment (multimedia content analysis), education purposes, sociology research, surveillance and security, improved quality live by means of monitoring or automatic artificial assistance, etc.




HuPBA Computer Vision Center Webpage


Projects and Research Applications


Sign recognition deals with the problem of detecting hand locations and analyze their structure and movement to determine actions and gestures.imagen 1


Medical Imaging in 3D PET/CT Human data and GPGPU:
-Linfoma segmentation
-Mental disorder analysis
Inpatient monitoringimagen 3

In this project we monitorize impaired people in order to automatically detect behaviors of patients in hospitals, such as pain or agitation, and consequently send a report to the psysician.

CARE Respite 2015 promotion video

 Social networksiamgen 4 imagen 44

Conversational indicators related to Social Signal Processing.


Hyperactivity disorder analysis: in this project we automatically extract a set of pose and behavior indicators in order to support diagnostic of hyperactivity desorder.imagen 5Video sample Physiotherapy and sports corporal analysis: in this project we automatically extract a set of human landmarks and measure corporal indicators from RGBD data for physiotherapy, rehabilitation, and fitness conditioning. ADiBAS project webpage


3D HuPBA avatars in Virtual and Augmented Reality
captura 7

Facial analysis and affective computing


Face tracking video     Facial expression analysis sample

Multi-modal human pose and behavior analysis capruta 8

HUPBA in Sports
 Multi-modal and multi-view surveillancec2

Social robotics


Multi-robot Human Computer Interaction video

 Multi-modal Assisted Living c4Video sample – Taking a pill

Care Respite

Human Computer Interacttion and Smart Cities (Living labs and smart environments)c8 c7

Multi-modal biometry analysis
Human analysis from pressure mapspressure