Prof. Dr.-Ing. Habil. Bogdan IONESCU

Coordinator of the Multimedia Lab, Center for Advanced Research on New Materials, Products and Innovative Processes, University "Politehnica" of Bucharest.

Coordinator of the Video Processing Group, The Image Processing and Analysis Lab, Faculty of Electronics, Telecommunications and Information Technology, University "Politehnica" of Bucharest.

Research interests: multimedia/video/image processing and analysis - multimedia content-based retrieval - machine learning for multimedia - multimedia benchmarking and evaluation - multimedia applications (e.g., video surveillance, lifelog, social media, medicine).

A 3D Synthetic Dataset for the Evaluation of 3D Human Pose Estimation Techniques

This dataset is designed to support research in the areas of computer vision that foster new technologies for improving the robustness of automatic 3D pose estimation techniques, specifically with respect to variations in (i) anthropometric measurements for male and female genders, (ii) viewing distance and angle of the subject, (iii) performed human actions and (iv) clothing (e.g., large vs tight).

The dataset comprises 288 videos, each 5 seconds long (at 24 fps), encoded using Xvid encoder (800x600 resolution, RGB images). The videos were generated using open source software and each is a combination of different human models wearing different clothes, performing different actions, and recorded from different camera positions. The purpose of creating the dataset is to have a simulation of real people performing specific actions, from specific points of view, but in a controllable way with the benefit having a precise Ground Truth. The complexity of the actions varies from easy to hard and each model has different anthropometric measurements. The Ground Truth is provided for each video, which consists of the 3D global coordinates of each joint of the skeleton, the camera position (location and orientation) and its focal length. With these values one can project from real world coordinates to camera coordinates.

The dataset was created using 2 open source tools: MakeHuman v.1.0.2 and Blender 2.73a. MakeHuman was used to create the human models, including anthropometric measurements for limbs and clothes (the .mhm files for each type of person are provided with the data). Blender was used to animate the models previously created, to create the final video and the Ground Truth. The tool allows for each action to tune the distance from the camera to the subject and the rotation angles of the camera (the .blend files for each video, containing all the data and parameters necessary to render the videos, are provided with the data).

Download the dataset:

To download the dataset, please send us the scanned signed data license agreement form (click here to download). Upon the receipt of this form, we will provide you with a link to download the data.

Acknowledgements:

Bogdan Boteanu, University "Politehnica" of Bucharest, Romania (bboteanu at alpha.imag.pub.ro), Nikolaos Sarafianos, Computational Biomedicine Lab, Department of Computer Science University of Houston, USA (nsarafianos at uh.edu), Bogdan Ionescu, University "Politehnica" of Bucharest, Romania (bionescu at alpha.imag.pub.ro), Ioannis A. Kakadiaris, Computational Biomedicine Lab, Department of Computer Science University of Houston, USA (ikakadia at central.uh.edu).