Developed a stereo camera employing a multi-shift approach to preserve far object detection performance and obtain wider FOV without using expensive image sensors. We also developed an object detection system based on top view image subtraction method, enabling pedestrian and cyclist detection in the monocular region created at the outer region of the stereo camera FOV. Achieve high accuracy for detection and distance measurement at the monocular region by using the disparity information from the central region to estimate the camera posture and correct it in real-time.

Person verification method based on behavioral patterns from complex human movements. Behavioral patterns are represented by anthropometric and kinematic features of human body motion acquired by a Kinect RGBD sensor. Focus on complex movements to demonstrate that independent and rhythmic movement of body parts carries a significant amount of behavioral information. Statistical approach by Gaussian mixture models to model the individual behavioral patterns. Demonstrated that subject-preferred movements are more robust against forgery attacks and variations over time than predetermined subject-independent movements.

A person verification method using behavioral patterns of human upper body motion. Behavioral patterns are represented by three-dimensional features obtained from a time-of-flight camera. Use a statistical approach to model the behavioral patterns using Gaussian mixture models (GMM) and support vector machines. Demonstrated that the proposed approach is robust against variations in body motion over time.

Novel approach to identify and/or verify persons by using three-dimensional dynamic and structural features extracted from human motion depicted on image streams. These features are extracted from body landmarks which are detected and tracked when the person is asked to perform specific movements, representing the dynamics of specific parts of the body, as well as the structural traits formed by the pose of the person. Gaussian mixture model (GMM) based systems are tested on a dataset containing arm movements. Experimental results confirmed that the proposed approach is promising for person authentication tasks.

This paper presents a robotics inspired behavioural AI technique to simulate characters’ personalities in a multi-award winning commercial video game. Furthermore, the paper describes a study with users.

This paper proposes and explores a novel approach to express emotions in cyberworlds through a flock of virtual beings. Emotions are represented in terms of the arousal and valence dimensions and they are visually expressed in a simple way through the behaviour and appearance of the individuals in the flock. In particular, the arousal value parameterizes the Reynolds’ flocking algorithm, and the valence value determines the number of different colors in the flock. Furthermore, the paper describes a study with users, whose interesting results are also discussed.