Jongmoo Choi

Signal Separation Coding for Robust Depth Imaging Based on Structured Light

This paper presents an original approach to coding the light patterns for robust depth imaging based on structured light. We have discovered that the degradation of precision and robustness, seen in most conventional approaches to structured light, comes mainly from the overlapping of multiple codes in the signal received at a camera pixel, where the overlapped codes are from the neighbouring and/or, even, distant pixels of the projecting mirror array. Considering the criticality of separating the overlapped codes to precision and robustness, we propose a novel signal separation code, referred to here as “Hierarchical Orthogonal Code (HOC),” for depth imaging. HOC provides not only the separation of overlapped codes, but also a robust decision on pixel correspondence with error correction based on a contextual likelihood among the sets of separated codes from neighbouring camera pixels. The experimental results have shown that the proposed HOC significantly enhances the robustness and precision in depth imaging, compared to the best known conventional approaches. The proposed approach opens a greater feasibility of applying structured light based depth imaging to a 3D modelling of cluttered workspace for home service robots.

Face Recognition Based on ICA Combined with FLD

Recently in face recognition, as opposed to our expectation, the performance of an ICA (Independent Component Analysis) method combined with LDA (Linear Discriminant Analysis) was reported as lower than an ICA only based method. This research points out that (ICA+LDA) methods have not got a fair comparison for evaluating its recognition performance. In order to incorporate class specific information into ICA, we have employed FLD (Fisher Linear Discriminant) and have proposed our (ICA+FLD) method. In the experimental results, we report that our (ICA+FLD) method has better performance than ICA only based methods as well as other representative methods such as Eigenface and Fisherface methods.

An active 3D robot camera for home environment

Service robots, such as robots working in a home environment, need very robust and reliable sensing mechanisms. In this paper, we present a 3D camera based on structured light suitable for robots working in the home environment. First, we show that the degradation of precision and robustness comes mainly from the overlapping of multiple codes in the signal received at a camera pixel. Then, we propose a novel signal separation coding providing not only the separation of overlapped codes, but also a robust decision on pixel correspondence with error correction. The proposed method was implemented using an invisible IR (infrared) pattern of lights in order to avoid user inconvenience in the home environment. The experimental results showed that the proposed algorithm significantly enhances the robustness and precision in depth imaging, compared to the best known conventional approaches. The proposed approach opens a greater feasibility of applying structured light based depth imaging to the 3D modeling of a cluttered workspace for home service robots.

A real-time face recognition system using multiple mean faces and dual mode Fisherfaces

This research features an automatic face detection and recognition system. The purpose of the system is for access control to a building or an office. The main feature of the system is face detection and face recognition robust to illumination changes. A novel template matching technique using multiple mean faces (MMF) of various sizes, luminance, and rotations is employed to achieve robust face detection. The system is also capable of operating in two different modes for face recognition: under normal illumination condition and under severe illumination changes.

Face recognition based on locally salient ICA information

ICA (Independent Component Analysis) is contrasted with PCA (Principal Component Analysis) in that ICA basis images are spatially localized, highlighting salient feature regions corresponding to eyes, eye brows, nose and lips. However, ICA basis images do not display perfectly local characteristic in the sense that pixels that do not belong to locally salient feature regions still have some weight values. These pixels in the non-salient regions contribute to the degradation of the recognition performance. We have proposed a novel method based on ICA that only employ locally salient information. The new method effectively implements the idea of ”recognition by parts” for the problem of face recognition. Experimental results using AT&T, Harvard, FERET and AR databases show that the recognition performance of the proposed method outperforms that of PCA and ICA methods especially in the cases of facial images that have partial occlusions and local distortions such as changes in facial expression and at low dimensions.

A real-time 3D IR camera based on hierarchical orthogonal coding

We present a real-time 3D camera based on IR (infrared) structured light suitable for robots working in home environment. First, we implemented a HOC (hierarchical orthogonal coding) based FPGA board. The HOC gives robust depth images because the signal separation coding provides not only the separation of overlapped codes, but also a robust decision on pixel correspondence with error correction. The FPGA module can handle high computational cost of HOC based signal separation coding. Second, we implemented a compact optic system of the camera to project and receive IR structured light. The invisible IR pattern light provides users inconvenient in the home environment. Various objects and workspaces which has continuous and/or non-continuous surface are tested and, sensitivity to illumination change and processing time are analyzed. The experiment results show the robust performance for surface smoothness, color, and materials of objects used in home environment. The proposed approach opens a greater feasibility of applying structured light based depth imaging to a 3D modeling of cluttered workspace for home service robots

A Real-Time Wall Detection Method for Indoor Environments

This paper presents an effective and real-time approach for detecting walls in indoor environment. This approach relies on the fact that the rear of the opaque walls is not visible. Thus, to detect the walls in an indoor environment a set of hypothetical walls, based on the ceiling edges or ground level edges, are considered; and their validity is checked using point cloud, generated by a sensor. A certainty factor is calculated for each detected wall, which is updated continuously based on the newly gathered sensory information. Furthermore, the certainty of the walls can be updated using other source of information for better and more reliable wall detection. The novelty of this approach is in its capability to handle environments, with texture-less walls, in real-time. The algorithm has been implemented in simulation, and tested in real environment and has shown effective, reliable and real-time performance

Robust Skin Color Segmentation Using a 2D Plane of RGB Color Space

This research features a new method for skin color segmentation using a 2D plane in the RGB color space. The RGB color values of the input color image do not need to be converted into HSI or YIQ color coordinates that have popularly been used for color segmentation. We have observed an important fact that skin colors in the RGB color space are approximately distributed in a linear fashion. Based on this fact, we have applied PCA (Principal Component Analysis) techniques to RGB values of skin colors from a set of training images. We detect skin regions by the lookup of skin color histogram computed based on a 2D color plane of which two axes correspond to two directions with smallest spread of skin colors.

PrimeEye: A Real-Time Face Detection and Recognition System Robust to Illumination Changes

This research features a real-time face detection and recognition system named PrimeEye. The purpose of the system is for access control to a building or an office. The main feature of the system is face detection and face recognition robust to illumination changes. A simple adaptive thresholding technique for skin color segmentation is employed to achieve robust face detection. The system is also capable of operating in two different modes for face recognition: under normal illumination condition and under severe illumination changes. The experimental results show that the SKKUfaces method is better than the Fisherfaces method in the case of severe illumination changes. In the normal illumination condition, the Fisherfaces method is better than the SKKUfaces method.

A Robust Depth Imaging Sensor Based on Signal Separation Coding

We present a depth imaging sensor based on signal separation coding. Since conventional approaches to structured light system depend on unrealistic assumptions about a workspace, such as absent of reflection or discontinuous, a depth image may collapse in a real home environment when the workspace has specular objects reflecting the active signal to the environment. In order to handle erroneous data caused by reflection and blurring, we used a two cameras and one projector system. The geometric constraint among them has been analyzed and applied to an error detection and correction procedure. The system achieves pixel correspondences not only within epipolar lines but also between epipolar lines efficiently. The experimental results have shown that the proposed system significantly enhances the robustness in depth imaging, compared to the conventional approaches. The proposed approach opens a greater feasibility of applying structured light based depth imaging in a cluttered workspace for home service robots.