Mochammad Hariadi

Facial motion capture with 3D active appearance models

Motion detection and tracking of facial features usually use special markers placed assistance on the part of the facial features, there is making the actor became uncomfortable in the process of making motion are applied in the world of animation either games or animated movies. Facial motion captures without any marker or marker less is one of the new techniques in Computer Vision. In this study the method used is the Active Appearance Models (AAM), which aims to detect and track a set of facial features, a variety of expressions and poses of the human face, the face orientation and movement. The image used in this study would have to have depth information that represents a 3D image, hence capturing facial images in this study used a stereo camera. Stereo camera in this study replaced with cameras that provide the depth information of a digital image. Data depth of image a point cloud consisting of data from the XYZ coordinates of a 3D representation of the world, which can then be applied to move the 3D face model, so that the resulting motion is more natural, which in turn can be used in the game and the world of animation.

Outer contour extraction of skull from CT scan images

Extraction of the outer contour of the skull is an important step in craniofacial reconstruction. The outer contour is required for surface reconstruction of the skull. In this paper, we propose a method to extract the outer contour of the skull. The extraction process consists of four stages: defining the region of interest, segmentation of the bone, noise removal and extraction of the outer contour based on scanning from the four sides of the image. The proposed method successfully extracts the outermost contour of the skull and avoids redundant data.

Crowd navigation using leader-follower algorithm based Reciprocal Velocity Obstacles

This research employs Reciprocal Velocity Obstacles (RVO) to create oscillation- and collision-free motion with multiagent navigation. By combining RVO with the steering behaviour i.e. leader following behaviour thus creating leader-follower relationship between agents. This relationship leads to the navigation to their shared destination. Each agent i.e. follower navigates to follow their leader to reach their destination together. Experimental result demonstrates the navigation of hundreds of agents in densely populated environments which showing 18% faster compared with relation-less navigation to achieve the crowd goal.

The prediction of debris flow distribution on Merapi Volcano in Central Java which involves measurements at several locations through the Ensemble Kalman Filter

Debris flow occurs in the downhill area of Merapi in Central Java is very dangerous threat that threatens human life, and destroys infrastructure facilities. Modeling of the debris flow in that area can be approximated by Eulerian continuous flow equations and discretized into dynamics systems model. This paper present the dynamic systems model and a strategy for estimate the distribution of the debris flow by Ensemble Kalman Filter (EnKF) that is combine with measurement data. The number of measurement points obtained by applying EnKF on several PDE which are part of Navier-Stokes equation. The EnkF method is prepare for prediction of debris flow distribution on Merapi Volcano downhill in Central Java using the combination of one and two dimension model of debris flow.