Search results

The aim of the research project which resulted in this work is to achieve a cost‐effective approach for instantaneous hyperspectral imaging.

This paper presents a simulation study and an experimental evaluation of a novel imaging spectroscopy technique, where multi‐channel image data are acquired instantaneously and transformed into spectra by using a statistical modelling approach. A digital colour camera equipped with an additional colour filter array was used to acquire an instantaneous single image that was demosaicked to generate a multi‐channel image. A statistical transformation approach was employed to convert this image into a hyperspectral one.

The feasibility of this method was investigated through extensive simulation and experimental tasks where promising results were obtained.

The small size of the initially acquired single instantaneous image makes this approach useful for applications where video‐rate hyperspectral imaging is required.

For the first time, a simplified prototype of this novel imaging spectroscopy technique was built and evaluated experimentally. And the results were compared with those of a more ideal simulation study. Recommendations for how to improve the prototype were also suggested as a result of the comparison between the simulation and the prototype evaluation results.

Reading fluency, which is critical for developing reading comprehension, is a fundamental skill in both school and life. However, many students with learning and behavioral disabilities are disfluent readers. To improve reading performance for these learners, educators should implement practices shown by reliable research to cause improved reading fluency. In this chapter, following a discussion of reading fluency and its importance, we describe two instructional practices that educators might use to improve students’ reading fluency: colored filters and repeated reading. The research on the colored filters is, at best, inconclusive, whereas the research literature suggests that repeated reading is an effective practice. To bridge the gap between research and practice and improve the reading fluency of students with learning and behavioral disabilities, educators and other stakeholders should prioritize the use of research-based practices (e.g., repeated reading) but avoid practices without clear research support (e.g., colored filters).

This paper seeks to construct a model for inventory management for multiple periods. The model considers not only the usual parameters, but also price quantity discount, storage and batch size constraints.

Mixed 0‐1 integer programming is applied to solve the multi‐period inventory problem and to determine an appropriate inventory level for each period. The total cost of materials in the system is minimized and the optimal purchase amount in each period is determined.

The proposed model is applied in colour filter inventory management in thin film transistor‐liquid crystal display (TFT‐LCD) manufacturing because colour filter replenishment has the characteristics of price quantity discount, large product size, batch‐sized purchase and forbidden shortage in the plant. Sensitivity analysis of major parameters of the model is also performed to depict the effects of these parameters on the solutions.

The proposed model can be tailored and applied to other inventory management problems.

Although many mathematical models are available for inventory management, this study considers some special characteristics that might be present in real practice. TFT‐LCD manufacturing is one of the most prosperous industries in Taiwan, and colour‐filter inventory management is essential for TFT‐LCD manufacturers for achieving competitive edge. The proposed model in this study can be applied to fulfil the goal.

This paper aims to present two different methods to speed up a test used in the sanitary ware industry that requires to count the number of granules that remains in the commodity after flushing. The test requires that 2,500 granules are added to the lavatory and less than 125 remain.

The problem is approached using two deep learning computer vision (CV) models. The first model is a Vision Transformers (ViT) classification approach and the second one is a U-Net paired with a connected components algorithm. Both models are trained and evaluated using a proprietary data set of 3,518 labeled images, and performance is compared.

It was found that both algorithms are able to produce competitive solutions. The U-Net algorithm achieves accuracy levels above 94% and the ViT model reach accuracy levels above 97%. At this time, the U-Net algorithm is being piloted and the ViT pilot is at the planning stage.

To the best of the authors’ knowledge, this is the first approach using CV to solve the granules problem applying ViT. In addition, this work updates the U-Net-Connected components algorithm and compares the results of both algorithms.

Visual tracking technology enables industrial robots interacting with human beings intelligently. However, due to the complexity of the tracking problem, the accuracy of visual target tracking still has great space for improvement. This paper aims to propose an accurate visual target tracking method based on standard hedging and feature fusion.

For this study, the authors first learn the discriminative information between targets and similar objects in the histogram of oriented gradients by feature optimization method, and then use standard hedging algorithms to dynamically balance the weights between different feature optimization components. Moreover, they penalize the filter coefficients by incorporating spatial regularization coefficient and extend the Kernelized Correlation Filter for robust tracking. Finally, a model update mechanism to improve the effectiveness of the tracking is proposed.

Extensive experimental results demonstrate the superior performance of the proposed method comparing to the state-of-the-art tracking methods.

Improvements to existing visual target tracking algorithms are achieved through feature fusion and standard hedging algorithms to further improve the tracking accuracy of robots on targets in reality.

This study/paper aims to present a separable identification algorithm for a multiple input single output (MISO) continuous time (CT) hybrid “Box–Jenkins”.

This paper proposes an optimal method for the identification of MISO CT hybrid “Box–Jenkins” systems with unknown time delays by using the two-stage recursive least-square (TS-RLS) identification algorithm.

The effectiveness of the proposed scheme is shown with application to a simulation example.

A two-stage recursive least-square identification method is developed for multiple input single output continuous time hybrid “Box–Jenkins” system with multiple unknown time delays from sampled data. The proposed technique allows the division of the global CT hybrid “Box–Jenkins” system into two fictitious subsystems: the first one contains the parameters of the system model, including the multiple unknown time delays, and the second contains the parameters of the noise model. Then the TS-RLS identification algorithm can be applied easily to estimate all the parameters of the studied system.

To develop customised machine vision methods for closed‐loop micro‐robotic control systems. The micro‐robots have applications in areas that require micro‐manipulation and micro‐assembly in the micron and sub‐micron range.

Several novel techniques have been developed to perform calibration, object recognition and object tracking in real‐time under a customised high‐magnification camera system. These new methods combine statistical, neural and morphological approaches.

An in‐depth view of the machine vision sub‐system that was designed for the European MiCRoN project (project no. IST‐2001‐33567) is provided. The issue of cooperation arises when several robots with a variety of on‐board tools are placed in the working environment. By combining multiple vision methods, the information obtained can be used effectively to guide the robots in achieving the pre‐planned tasks.

Some of these techniques were developed for micro‐vision but could be extended to macro‐vision. The techniques developed here are robust to noise and occlusion so they can be applied to a variety of macro‐vision areas suffering from similar limitations.

The work here will expand the use of micro‐robots as tools to manipulate and assemble objects and devices in the micron range. It is foreseen that, as the requirement for micro‐manufacturing increases, techniques like those developed in this paper will play an important role for industrial automation.

This paper extends the use of machine vision methods into the micron range.

Surveillance is the emerging concept in the current technology, as it plays a vital role in monitoring keen activities at the nooks and corner of the world. Among which moving object identifying and tracking by means of computer vision techniques is the major part in surveillance. If we consider moving object detection in video analysis is the initial step among the various computer applications. The main drawbacks of the existing object tracking method is a time-consuming approach if the video contains a high volume of information. There arise certain issues in choosing the optimum tracking technique for this huge volume of data. Further, the situation becomes worse when the tracked object varies orientation over time and also it is difficult to predict multiple objects at the same time. In order to overcome these issues here, we have intended to propose an effective method for object detection and movement tracking. In this paper, we proposed robust video object detection and tracking technique. The proposed technique is divided into three phases namely detection phase, tracking phase and evaluation phase in which detection phase contains Foreground segmentation and Noise reduction. Mixture of Adaptive Gaussian (MoAG) model is proposed to achieve the efficient foreground segmentation. In addition to it the fuzzy morphological filter model is implemented for removing the noise present in the foreground segmented frames. Moving object tracking is achieved by the blob detection which comes under tracking phase. Finally, the evaluation phase has feature extraction and classification. Texture based and quality based features are extracted from the processed frames which is given for classification. For classification we are using J48 ie, decision tree based classifier. The performance of the proposed technique is analyzed with existing techniques k-NN and MLP in terms of precision, recall, f-measure and ROC.

The purpose of this paper is to offer an introduction to the technological advances of the complementary metal–oxide–semiconductor (CMOS) image sensors along the past decades. The authors review some of those technological advances and examine potential disruptive growth directions for CMOS image sensors and proposed ways to achieve them.

Those advances include breakthroughs on image quality such as resolution, capture speed, light sensitivity and color detection and advances on the computational imaging.

The current trend is to push the innovation efforts even further, as the market requires even higher resolution, higher speed, lower power consumption and, mainly, lower cost sensors. Although CMOS image sensors are currently used in several different applications from consumer to defense to medical diagnosis, product differentiation is becoming both a requirement and a difficult goal for any image sensor manufacturer. The unique properties of CMOS process allow the integration of several signal processing techniques and are driving the impressive advancement of the computational imaging.

The authors offer a very comprehensive review of methods, techniques, designs and fabrication of CMOS image sensors that have impacted or will impact the images sensor applications and markets.

The basis for a broadened scanning framework is described, which may also function as a means for understanding how human minds filter their perceptions of the world. The framework is based on the Four‐Quadrant Integral model of Ken Wilber and the Spiral Dynamics model of Don Beck and Chris Cowan. An analytical tool (cross‐level analysis) is presented for examining views of the world in terms of both the perceptual filters of the viewer and the aspect of the world being viewed, a technique which is also useful for analysing how other scanners do their scanning. A notation for cross‐level analysis is presented and described, with examples of its use.