top of page
ADiBAS|01

 

ADiBAS |01 Automatic Digital Biometry Analysis System

In this work, we propose a tool for static body posture analysis and dynamicrange of movement estimation of the skeleton joints based on 3D anthropometric information from multi-modal data. For more information www.adibas.com

HCI |02 Human Computer Interaction

We propose a novel point cloud descriptor, calledSpherical Blurred Shape Model (SBSM), which successfully en-codes the structure density and local variabilities of an object based on shape voxel distances and a neighborhood propagationstrategy. The proposed SBSM is proven to be rotation and scale invariant, robust to noise and occlusions, highly discriminative formultiple categories of complex objects like the human hand, and computationally efficient since the SBSM complexity is linear to the number of object voxels.  In the video are described 8 human hand categories.

Multimodal |03 Multimodal surveillance

We propose an automatic system for user identification andobject recognition based on multi-modal RGB-Depth data analysis. Wemodel a RGBD environment learning a pixel-based background Gaussiandistribution. Then, user and object candidate regions are detectedand recognized online using robust statistical approaches over RGBDdescriptions.

HCI|02

 

Multi |03

 

TDAH |04

 

TDAH |04 Hyperactivity disorder analysis

In this project we automatically extract a set of pose and behavior indicators in order to support diagnostic of hyperactivity desorder.

Projects

Hupba Projects

bottom of page