EM-GPA: Generalized Procrustes analysis with hidden variables for 3D shape modeling

Aligning shapes is essential in many computer vision problems and generalized Procrustes analysis (GPA) is one of the most popular algorithms to align shapes. However, if some of the shape data are missing, GPA cannot be applied. In this paper, we propose EM-GPA, which extends GPA to handle shapes with hidden (missing) variables by using the expectation-maximization (EM) algorithm. For example, 2D shapes can be considered as 3D shapes with missing depth information due to the projection of 3D shapes into the image plane. For a set of 2D shapes, EM-GPA finds scales, rotations and 3D shapes along with their mean and covariance matrix for 3D shape modeling. A distinctive characteristic of EM-GPA is that it does not enforce any rank constraint often appeared in other work and instead uses GPA constraints to resolve the ambiguity in finding scales, rotations, and 3D shapes. The experimental results show that EM-GPA can recover depth information accurately even when the noise level is high and there are a large number of missing variables. By using the images from the FRGC database, we show that EM-GPA can successfully align 2D shapes by taking the missing information into consideration. We also demonstrate that the 3D mean shape and its covariance matrix are accurately estimated. As an application of EM-GPA, we construct a 2D + 3D AAM (active appearance model) using the 3D shapes obtained by EM-GPA, and it gives a similar success rate in model fitting compared to the method using real 3D shapes. EM-GPA is not limited to the case of missing depth information, but it can be easily extended to more general cases.     

Color laser printer forensic based on noisy feature and support vector machine classifier

Digital forensics in the ubiquitous era can enhance and protect the reliability of multimedia content where this content is accessed, manipulated, and distributed using high quality computer devices. Color laser printer forensics is a kind of digital forensics which identifies the printing source of color printed materials such as fine arts, money, and document and helps to catch a criminal. This paper present a new color laser printer forensic algorithm based on noisy texture analysis and support vector machine classifier that can detect which color laser printer was used to print the unknown images. Since each printer vender uses their own printing process, printed documents from different venders have a little invisible difference looks like noise. In our identification scheme, the invisible noises are estimated with the wiener-filter and the 2D Discrete Wavelet Transform (DWT) filter. Then, a gray level co-occurrence matrix (GLCM) is calculated to analyze the texture of the noise. From the GLCM, 384 statistical features are extracted and applied to train and test the support vector machine classifier for identifying the color laser printers. In the experiment, a total of 4,800 images from 8 color laser printer models were used, where half of the image is for training and the other half is for classification. Results prove that the presented algorithm performs well by achieving 99.3%, 97.4% and 88.7% accuracy for the brand, toner and model identification respectively.     

A high performance parallel DCT with OpenCL on heterogeneous computing environment

A noteworthy thing in desktop PCs is that they can provide a great opportunity to increase the performance of processing multimedia data by exploiting task- and data-parallelism with multi-core CPU and many-core GPU. This paper presents a high performance parallel implementation of 2D DCT on this heterogeneous computing environment. For this purpose, Intel TBB (threading building blocks) and OpenCL (Open Compute Language) are utilized for task- and data-parallelism, respectively. The simulation result shows that the parallel DCT implementations far the serial ones in processing speed. Especially, OpenCL implementation shows a linear speedup, a typical SIMD characteristic as the increase of 2D data sets.     

Disparate attributes algorithm for semantic assembly design rule management

To expedite a semantic product design environment, the relevant minimal set of design rules could optimally be distilled from the given disparate design rules. However, in disparate design rules, some attributes are frequently unused in other design rules. Treating all the attributes in all the rules increases reasoning complexity. In the situation of incomplete information, treating the attributes, which may be relevant to some rules and not to others, as “missing” ones is found to cause reasoning problems. In this paper, we present a new algorithm, i.e. the disparate attributes algorithm, for managing semantic assembly design rules. The proposed disparate attributes algorithm by identifying “inapplicable” information extends a rough set approach for managing semantic assembly design rules with systematic selection of various minimal sets of rules. To validate the disparate attributes algorithm, the approach is tested with multiple realistic assembly design cases.     

Optimal scheduling of a communication channel for the centralized control of a platoon of vehicles

This paper proposes an off-line optimal channel scheduling algorithm for an interconnected vehicle control system. The optimal sequence obtained through the scheduling algorithm provides a switching controller with the best switching order if the controller can access only one plant at each time slot over the shared communication medium. Interconnected systems require the string stability as well as the dynamic stability of each unit. This paper shows that integrating the simple string stable control law with the approximately optimal linear-quadratic (LQ) tracker gives the optimal channel scheduling algorithm.     

Polar-Cartesian Hybrid Transforms: A novel 2D range scan registration algorithm

Registration of range scans is commonly required in many localization and mapping algorithms. In this paper, we introduce a novel approach called Polar-Cartesian Hybrid Transforms for pair-wise registration of range scans. The proposed algorithm iteratively establishes correspondences by searching the points with closest polar angles in the polar coordinate frame. An angular look-up table is constructed based on the properties of the laser range finder to accelerate the searching procedure. In order to speed up the convergence, we compute the difference of polar range of every matched point pair to select the most contributing correspondences. After the correspondences are determined, the transformation is computed in Cartesian coordinate frame using a point-to-line metric. Combining the advantages of the polar and Cartesian coordinate frames, both robustness and efficiency are greatly improved compared with an up-to-date ICP algorithm.     

Map building method for urban gas pipelines based on landmark detection

This paper presents a map building method for an in-pipe robot to navigate inside urban gas pipelines autonomously, whose configuration is unknown or partially known. In the first, we explain the reason why the navigation in the pipeline is difficult and then, present a method for obtaining a robot’s posture by using a pipeline’s unique geometrical features. The robot can obtain its heading direction by detecting the standardized geometries of pipe elements. Based on the method, we propose a robot controller consisting of discrete and continuous controllers. The discrete controller is activated by pre-defined events and generates appropriate paths for exploration. The continuous controller receives the desired path and physically moves the robot to the desired path. The method is implemented in an in-pipe robot, called MRINSPECT-V and its effectiveness is validated.     

Development of a quadruped walking robot AiDIN-III using biologically inspired kinematic analysis

This paper presents a bio-inspired mechanism design for a quadruped walking robot. The approach is derived from the observation on the behaviors of quadruped locomotion, skeletal structure, and the study on the stability of walking based on morphological analysis. In the first, we define the design parameters such as the dimensions of the body and limbs, the center of mass position, and locomotion mechanisms based on surveys on the literatures from biologists. Then, by using the parameters, we propose an useful framework for determining the design parameters of a quadruped walking robot. For implementations, we manufacture a dog-type self-contained quadruped walking robot, named AiDIN-III (Artificial Digitigrade for Natural Environment version III) and the effectiveness of the proposed idea is validated via experimental works.     

Effects of wheelchair-based rehabilitation on the physical functions and health perception of stroke patients

The purpose of this study was to investigate the effect of wheelchair-based rehabilitation on the physical functions, health perception, and blood lipids according to the length of time since the stroke. Wheelchair-based rehabilitation progressed for 60 min per session, five times per week for 6 weeks. Physical functions, health perception (SF-36), and blood lipids were measured before and after rehabilitation. Physical fitness for physical function such as agility, grip strength, lower-body muscular endurance, flexibility, and posture control significantly improved after 6 weeks of rehabilitation. Health perception improved significantly with physical and mental health according to time since the stroke occurred. Overall, 6 weeks of wheelchair-based rehabilitation had a positive effect on the physical function and health perception regardless of stroke duration. Wheelchair-based rehabilitation had a more positive effect on the physical functions and health perception on the patients who suffered their stroke most recently. We suggested that wheelchair-based rehabilitation is necessary even through wheelchair based for chronic stroke patients, and it was useful their improved of quality of life.     

Surface slope effects on shingling frequency and postural balance in a simulated roofing task

The purpose of this study was to investigate the influence of surface slopes (18 degrees , 26 degrees , 34 degrees ) on the maximum acceptable roof shingling frequency for males performing a simulated roof-shingling task. The psychophysical roof shingling frequency was also compared to the postural sway and trunk motion values. The maximum acceptable roof shingling frequency and selected trunk motion decreased significantly with an increase in slope. Postural sway however increased significantly with an increase in slope. The study also revealed that workers were experiencing a greater postural sway at the earlier phase of task on the steeper surface. This suggests that there might be an adaptation period associated with working on a slope and the body's ability to compensate for a loss of balance. Therefore, more emphasis should be given to the workers in this adaptation period, with additional monitoring and cautionary measures. Collectively, the findings of the study could be utilized for improving work practices on roofs, while reducing the potential risks of falls in roofing construction.