Hiroyuki Ukida

Shape from Shading with Interreflections Under a Proximal Light Source: Distortion-Free Copying of an UnfoldedBook

We address the problem of recovering the 3D shape of an unfolded book surface from the shading information in a scanner image. This shape-from-shading problem in a real world environment is made difficult by a proximal, moving light source, interreflections, specular reflections, and a nonuniform albedo distribution. Taking all these factors into account, we formulate the problem as an iterative, non-linear optimization problem. Piecewise polynomial models of the 3D shape and albedo distribution are introduced to efficiently and stably compute the shape in practice. Finally, we propose a method to restore the distorted scanner image based on the reconstructed 3D shape. The image restoration experiments for real book surfaces demonstrate that much of the geometric and photometric distortions are removed by our method.

Integrated Imaging and Vision Techniques for Industrial Inspection

This pioneering text/reference presents a detailed focus on the use of machine vision techniques in industrial inspection applications. An internationally renowned selection of experts provide insights on a range of inspection tasks, drawn from their cutting-edge work in academia and industry, covering practical issues of vision system integration for real-world applications. Topics and features:presents a comprehensive review of state-of-the-art hardware and software tools for machine vision, and the evolution of algorithms for industrial inspection; includes in-depth descriptions of advanced inspection methodologies and machine vision technologies for specific needs; discusses the latest developments and future trends in imaging and vision techniques for industrial inspection tasks; provides a focus on imaging and vision system integration, implementation, and optimization; describes the pitfalls and barriers to developing successful inspection systems for smooth and efficient manufacturing process.

Measurement System of Transfer Motion for Patients With Spinal Cord Injuries

The purpose of this study is to make clear the side-approach transfer ability of spinal cord injury (SCI) patients. We evaluate the SCI patients skill and muscle power for the transfer motion by imaging patients transfer motion and measuring the floor reaction forces. In this study, the measurement of the side-approach transfer from the wheelchair to the platform was carried out in eight SCI patients who train the side-approach transfer in rehabilitation and two healthy subjects. We can understand that the brachial muscle power of left hand is necessary so that SCI patients lift about 50% of the body weight for the side-approach transfer. The force patterns and the force direction of the left hand are different among SCI patients. Using force pattern, the medical staffs can evaluate the ability of the side-approach transfer motion of each patient

Shape from shading with interreflections under proximal light source-3D shape reconstruction of unfolded book surface from a scanner image

We address the problem to recover the 3D shape of an unfolded book surface from the shading information in a scanner image. From a technical point of view, this shape from shading problem in real world environments is characterized by (1) proximal light source, (2) interreflections, (3) moving light source, (4) specular reflection, and (5) nonuniform albedo distribution. Taking all these factors into account, we first formulate the problem based on an iterative nonlinear optimization scheme. Then we introduce piecewise polynomial models of the 3D shape. Image restoration experiments for a real book surface demonstrated that geometric and photometric distortions are almost completely removed by the proposed method.<<ETX>>

Human Motion Capture System using Color Markers and Silhouette

In this paper, we discuss the motion capture system which acquire 3D human motion data using camera images. In this system, in order to detect feature points of humans parts, we use a few color markers and silhouette images of human to be able to move human without restriction. And, we estimate 3D positions of feature points by the stereo method using two cameras. Moreover, when the feature points can not be detected by occlusions, proposed system predict and modify its locations using conditions of constraints about a human body. In the experimental results using real human images, we confirm that the 3D human motions can be acquired stably and accurately under occlusions

Omni-directional 3D Measurement by Hyperbolic Mirror Cameras and Pattern Projection

In this paper, we propose an omni-directional depth measurement method using hyperbolic mirror cameras and projectors to develop circumference sensing function for autonomous mobile systems, virtual reality systems, and so on. In this method, we use two omni-directional cameras to take images of patterns projected by projectors, and estimate distances from cameras to objects by the stereo method. Especially, we use the space encoding method, vertical lines and small points as projected patterns, and we discuss appropriate pattern projection for distance measurement with omni-directional cameras. As the results of experiments, small points projection can measure distances more accurately than other projection, and we can show the effectiveness of proposed method by measuring 3D depth surrounding cameras using multiple projectors.

Visual communication using LED panel and video camera for mobile object

This study proposes an information transmission device constructed by a LED panel and a video camera. The LED panel displays various patterns of AR markers and micro QR codes. Then, from images taken by the video camera, some information and 3D position and pose of the camera from the LED panel are extracted. We are planning to apply this system for a communication between a radio-controlled helicopter and a base station. In this paper, we propose a method to distinguish AR markers and micro QR codes automatically, and show results of discriminated rates in the experiment.

3D shape, color and specular estimation using an image scanner with multiple illuminations

In this study, by using an image scanner equipped with multiple illuminations, we propose a method to estimate 3D shape, color and specular reflections of an object. We formulate this problem as the absolute depth estimation using the photometric stereo method. Our proposed method consists of two parts. The first process is the initial shape estimation. This method uses several scanned images taken by illuminations located on circumferences, and estimates object shape by using averaged images to reduce the specular reflection. The second process is an iterative estimation of specular components, color and shape. In experiments, we show shape reconstruction results using real and synthetic images, and confirm the effectiveness of our proposed method.

Measurement of Wheelchair Position for Analyzing Transfer Motion for SCI Patient

The purpose of this study is to clarify the side-approach transfer ability of spinal cord injury (SCI) patients. We have proposed the measurement system that consists of four force plates and two CCD cameras in order to analyze the transfer motion. The system measures the three-dimensional floor reaction forces and the side-view and the front-view images during each patients transfer motion. We understood that the force patterns and the force direction of the left hand are different among SCI patients by analyzing the floor reaction forces. In side-approach transfer, SCI patients diagonally move their wheelchair close to the platform and the wheelchair position is different among SCI patients. In this study, we estimate the wheelchair position by detecting the center position of the wheelchair wheel using the images and by calculating the wheelchair degree (gap angle between the wheelchair and the platform) using side-view image.

3D Shape Reconstructions Using Image Scanner under Various Number of Illuminations

In this paper, we propose new shape and color reconstruction methods using image scanner equipped with multiple illuminations. Here, we show three reconstruction algorithms in case of two, three and four light sources. These algorithms are based on the nonlinear least squares using the photometric models and color image intensities. And we estimate optimal number and positions of light sources for a shape reconstruction. As the experimental results, using four light sources which are located symmetrically under the scanning line can be recovered object shape and color accurately, and it is suitable for the actual shape scanner.