Moon-sik Jeong

Simultaneous Geometric and Radiometric Adaptation to Dynamic Surfaces With a Mobile Projector-Camera System

Existing geometric and radiometric compensation methods for direct-projected augmented reality focus on static projection surfaces rather than dynamic surfaces (with varying geometry in time). We aim at providing an effective framework for projecting a sequence of augmented reality images onto dynamic surfaces without geometric and radiometric distortion. We present our design of a special pattern image for simultaneous geometric and radiometric compensation and evaluate two different techniques for embedding the pattern image into augmented reality images. The validity of the proposed method is examined through a variety of experiments with a mobile projector-camera system.

Practical Hand Skeleton Estimation Method Based on Monocular Camera

In this paper, we propose a practical hand skeleton reconstruction method using a monocular camera. The proposed method is a fundamental technology that can be applicable to future products such as wearable or mobile devices and smart TVs requiring natural hand interactions. To heighten its practicability, we designed our own hand parameters composed of global hand and local finger configurations. Based on the parameter states, a kinematic hand and its contour can be reconstructed. By adopting palm detection and tracking, global parameters can be easily estimated, which can reduce the search space required for whole parameter estimations. We can then fine-tune the coarse estimated parameters through the use of a Gauss-Newton optimization stage. Experimental results indicate that our method provides a sufficient level of accuracy to be utilized in gesture-interactive applications. The proposed method is light in terms of algorithm complexity and can be applied in real time.

Human Body Volume Recovery from Single Depth Image

We propose on-line human body volume recovery framework using only single depth image. Depth image contains partial 3d geometry information of human body surface seen from the sensor viewpoint. Previous volume reconstruction methods require multiple images from different viewpoints to reconstruct complete closed body volume. They have limitation in real-time application with dynamic objects or require multiple sensors. In this paper, we propose a generic model based human body volume recovery. First, we register the pose of the generic model to partial body surface observation from single depth image. And then remaining 3d points on unseen surface is optimized by propagating confidence of the partial observation. Experimental result shows our method captures reasonable human body volume from single depth image on-line.