University Events

Description: TOPIC: IDENTIFICATION OF HUMAN POSES FROM IMAGES USING SPACE COMPLETION ANIMATION OF PEOPLE

LOCATION: College of Engineering Conference Room, Textile's Building - Room 101E

ABSTRACT:
Identifying human poses from images is one of the important techniques that can be used in many applications. The technique can automatically detect and estimate the 2D poses of humans in images under uncontrolled imaging conditions. The identification of human poses from images is used in some important applications such as rescuing people using robots under natural disasters and estimating fitness conditions of people by taking the images of their sport activities. The goal of this project is to detect human poses in standing positions. In the project, some image transformation techniques are applied in obtaining the format of poses from images. An existing Space Completion Animation of People (SCAPE) algorithm was implemented to perform the detection and estimation of poses from images and video. SCAPE algorithm is a data-driven method for building a human shape model that spans variation in both subject shape and poses. This algorithm is based on a representation that incorporates both articulated and non-rigid deformations. The implementation of the identification of people poses was tested and validated on multiple image sets.

NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.

Advisor: Dr. Honggang Wang
Committee Members: Dr. Liudong Xing and Dr. Lance N. Fiondella, Department of Electrical & Computer Engineering

TOPIC: IDENTIFICATION OF HUMAN POSES FROM IMAGES USING SPACE COMPLETION ANIMATION OF PEOPLE

LOCATION: College of Engineering Conference Room, Textile's Building - Room 101E

ABSTRACT:
Identifying human poses from images is one of the important techniques that can be used in many applications. The technique can automatically detect and estimate the 2D poses of humans in images under uncontrolled imaging conditions. The identification of human poses from images is used in some important applications such as rescuing people using robots under natural disasters and estimating fitness conditions of people by taking the images of their sport activities. The goal of this project is to detect human poses in standing positions. In the project, some image transformation techniques are applied in obtaining the format of poses from images. An existing Space Completion Animation of People (SCAPE) algorithm was implemented to perform the detection and estimation of poses from images and video. SCAPE algorithm is a data-driven method for building a human shape model that spans variation in both subject shape and poses. This algorithm is based on a representation that incorporates both articulated and non-rigid deformations. The implementation of the identification of people poses was tested and validated on multiple image sets.

NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.

Advisor: Dr. Honggang Wang
Committee Members: Dr. Liudong Xing and Dr. Lance N. Fiondella, Department of Electrical & Computer Engineering

*For further information, please contact Dr. Honggang Wang at 508.999.8469, or via email at hwang1@umassd.edu.