Search results

Background modelling has played an imperative role in the moving object detection as the progress of foreground extraction during video analysis and surveillance in many real-time applications. It is usually done by background subtraction. This method is uprightly based on a mathematical model with a fixed feature as a static background, where the background image is fixed with the foreground object running over it. Usually, this image is taken as the background model and is compared against every new frame of the input video sequence. In this paper, the authors presented a renewed background modelling method for foreground segmentation. The principal objective of the work is to perform the foreground object detection only in the premeditated region of interest (ROI). The ROI is calculated using the proposed algorithm reducing and raising by half (RRH). In this algorithm, the coordinate of a circle with the frame width as the diameter is considered for traversal to find the pixel difference. The change in the pixel intensity is considered to be the foreground object and the position of it is determined based on the pixel location. Most of the techniques study their updates to the pixels of the complete frame which may result in increased false rate; The proposed system deals these flaw by controlling the ROI object (the region only where the background subtraction is performed) and thus extracts a correct foreground by exactly categorizes the pixel as the foreground and mines the precise foreground object. The broad experimental results and the evaluation parameters of the proposed approach with the state of art methods were compared against the most recent background subtraction approaches. Moreover, the efficiency of the authors’ method is analyzed in different situations to prove that this method is available for real-time videos as well as videos available in the 2014 challenge change detection data set.

In this paper, the authors presented a fresh background modelling method for foreground segmentation. The main objective of the work is to perform the foreground object detection only on the premeditated ROI. The region for foreground extraction is calculated using proposed RRH algorithm. Most of the techniques study their updates to the pixels of the complete frame which may result in increased false rate; most challenging case is that, the slow moving object is updated quickly to detect the foreground region. The anticipated system deals these flaw by controlling the ROI object (the region only where the background subtraction is performed) and thus extracts a correct foreground by exactly categorizing the pixel as the foreground and mining the precise foreground object.

Plum Analytics provide a new conduit for documenting and contextualizing the public impact and reach of research within digitally networked environments. While limitations are notable, the metrics promoted through the platform can be used to build a more comprehensive view of research impact.

The algorithm used in the work was proposed by the authors and are used for experimental evaluations.

This paper proposes a novel method for human hands tracking using data from an event camera. The event camera detects changes in brightness, measuring motion, with low latency, no motion blur, low power consumption and high dynamic range. Captured frames are analysed using lightweight algorithms reporting three-dimensional (3D) hand position data. The chosen pick-and-place scenario serves as an example input for collaborative human–robot interactions and in obstacle avoidance for human–robot safety applications.

Events data are pre-processed into intensity frames. The regions of interest (ROI) are defined through object edge event activity, reducing noise. ROI features are extracted for use in-depth perception.

Event-based tracking of human hand demonstrated feasible, in real time and at a low computational cost. The proposed ROI-finding method reduces noise from intensity images, achieving up to 89% of data reduction in relation to the original, while preserving the features. The depth estimation error in relation to ground truth (measured with wearables), measured using dynamic time warping and using a single event camera, is from 15 to 30 millimetres, depending on the plane it is measured.

Tracking of human hands in 3 D space using a single event camera data and lightweight algorithms to define ROI features (hands tracking in space).

The purpose of this paper is the presentation and research of a novel sensor fusion-based system for obstacle detection and identification, which uses the millimeter-wave radar to detect the position and velocity of the obstacle. Afterwards, the image processing module uses the bounding box regression algorithm in deep learning to precisely locate and identify the obstacles.

Unlike the traditional algorithms that use radar and vision to detect obstacles separately, the purposed method of this paper uses radar to determine the approximate location of obstacles and then uses bounding box regression to achieve accurate positioning and recognition. First, the information of the obstacles can be acquired by the millimeter-wave radar, and the effective target is extracted by filtering the data. Then, use coordinate system conversion and camera parameter calibration to project the effective target to the image plane, and generate the region of interest (ROI). Finally, based on image processing and machine learning techniques, the vehicle targets in the ROI are detected and tracked.

The millimeter wave is used to determine the presence of an obstacle, and the deep learning algorithm of the image is combined to determine the shape and the class of the obstacle. The experimental results indicate that the detection rate of this method is up to 91.6 per cent, which can better implement the perception of the environment in front of the vehicle.

The originality is based on the combination of millimeter-wave sensors and deep learning. Using the bounding box regression algorithm in RCNN, the ROI detected by radar is analyzed to realize real-time obstacle detection and recognition. This method does not require processing the entire image, greatly reducing the amount of data processing and improving the efficiency of the algorithm.

Quality control and part inspection add no monetary value to a product, yet are essential processes for manufacturers who want to maintain product quality. Mass‐produced custom parts require processes that are able to perform high frequency of inspection, whilst providing rapid response to unanticipated changes in parameters such as throughputs, dimensions and tolerances. Frequent inspection of these parts significantly impacts inspection times involved. A method of reducing the impact of high‐frequency inspection on production rates is needed. This paper addresses these issues.

This paper involves the research, design, construction, assembly and implementation of an automated apparatus, used for the visual inspection of moving custom parts. Inspection occurred at user‐defined regions of interest (ROIs). Mechatronic Engineering principles are used to integrate sensor articulation, image acquisition and image‐processing systems. The apparatus is tested in a computer‐integrated manufacturing (CIM) cell for quantifying results.

Specified production rates are maintained whilst performing high frequencies of inspection, without stoppage of parts along the production line.

The limitations of these results lie in the fact that they are suited only to the speed of the CIM cell. Higher inspection rates may be achieved, and changes in the design may be required in order to make the apparatus more suitable to industrial applications.

The paper shows that it is possible to maintain high standards of quality control without significantly affecting production rates.

Current research does not focus on maintaining production rates whilst inspecting custom parts. The use of ROI inspection for moving custom parts is a relatively new concept.

A major key success factor regarding proficient Bayes threshold denoising refers to noise variance estimation. This paper focuses on assessing different noise variance estimations in three Bayes threshold models on two different characteristic brain lesions/tumor magnetic resonance imaging (MRIs).

Here, three Bayes threshold denoising models based on different noise variance estimations under the stationary wavelet transforms (SWT) domain are mainly assessed, compared to state-of-the-art non-local means (NLMs). Each of those three models, namely D1, GB and DR models, respectively, depends on the most detail wavelet subband at the first resolution level, on the entirely global detail subbands and on the detail subband in each direction/resolution. Explicit and implicit denoising performance are consecutively assessed by threshold denoising and segmentation identification results.

Implicit performance assessment points the first–second best accuracy, 0.9181 and 0.9048 Dice similarity coefficient (Dice), sequentially yielded by GB and DR; reliability is indicated by 45.66% Dice dropping of DR, compared against 53.38, 61.03 and 35.48% of D1 GB and NLMs, when increasing 0.2 to 0.9 noise level on brain lesions MRI. For brain tumor MRI under 0.2 noise level, it denotes the best accuracy of 0.9592 Dice, resulted by DR; however, 8.09% Dice dropping of DR, relative to 6.72%, 8.85 and 39.36% of D1, GB and NLMs is denoted. The lowest explicit and implicit denoising performances of NLMs are obviously pointed.

A future improvement of denoising performance possibly refers to creating a semi-supervised denoising conjunction model. Such model utilizes the denoised MRIs, resulted by DR and D1 thresholding model as uncorrupted image version along with the noisy MRIs, representing corrupted version ones during autoencoder training phase, to reconstruct the original clean image.

This paper should be of interest to readers in the areas of technologies of computing and information science, including data science and applications, computational health informatics, especially applied as a decision support tool for medical image processing.

In most cases, DR and D1 provide the first–second best implicit performances in terms of accuracy and reliability on both simulated, low-detail small-size region-of-interest (ROI) brain lesions and realistic, high-detail large-size ROI brain tumor MRIs.

This paper aims to investigate the usability of the non-iterative monotonicity approach for electrical capacitance tomography (ECT)-based object detection. This is of particular importance with respect to object detection in robotic applications.

With respect to the detection problem, the authors propose a precomputed threshold value for the exclusion test to speed up the algorithm. Furthermore, they show that the use of an inhomogeneous split-up strategy of the region of interest (ROI) improves the performance of the object detection.

The proposed split-up strategy enables to use the monotonicity approach for robotic applications, where the spatial placement of the electrodes is constrained to a planar geometry. Additionally, owing to the improvements in the exclusion tests, the selection of subregions in the ROI allows for avoiding self-detection. Furthermore, the computational costs of the algorithm are reduced owing to the use of a predefined threshold, while the detection capabilities are not significantly influenced.

The presented simulation results show that the adapted split-up strategies for the ROI improve significantly the detection performance in comparison to the traditional ROI split-up strategy. Thus, the monotonicity approach becomes applicable for ECT-based object detection for applications, where only a reduced number of electrodes with constrained spatial placement can be used, such as in robotics.

The purpose of this paper is to propose a new framework and improve a bi-directional people counting technique using an RGB-D camera to obtain accurate results with fast computation time. Therefore, it can be used in real-time applications.

First, image calibration is proposed to obtain the ratio and shift values between the depth and the RGB image. In the depth image, a person is detected as foreground by removing the background. Then, the region of interest (ROI) of the detected people is registered based on their location and mapped to an RGB image. Registered people are tracked in RGB images based on the channel and spatial reliability. Finally, people were counted when they crossed the line of interest (LOI) and their displacement distance was more than 2 m.

It was found that the proposed people counting method achieves high accuracy with fast computation time to be used in PCs and embedded systems. The precision rate is 99% with a computation time of 35 frames per second (fps) using a PC and 18 fps using the NVIDIA Jetson TX2.

The precision rate is 99% with a computation time of 35 frames per second (fps) using a PC and 18 fps using the NVIDIA Jetson TX2.

The proposed method can count the number of people entering and exiting a room at the same time. If the previous systems were limited to only one to two people in a frame, this system can count many people in a frame. In addition, this system can handle some problems in people counting, such as people who are blocked by others, people moving in another direction suddenly, and people who are standing still.

This chapter seeks to investigate the ways individualistic versus collectivistic values moderate neural responses to social exclusion among African American and White respondents. The author hypothesized that the vmPFC – a key brain region for emotion regulation – would correspond to collectivistic value moderation and the dlPFC – the cognitive control center of the brain – would be associated with individualistic value moderation.

This study used a virtual ball tossing game (Cyberball), where 17 African American and 11 White participants were excluded or included with ball tosses, while inside an fMRI scanner. Before the start of each round the participants were primed with individualism, collectivism or a comparison condition.

Results showed that (1) African Americans showed stronger neural responses to exclusion and (2) offered support for the hypothesis that the dlPFC showed greater activation in African Americans (compared to Whites) when they were primed with individualism values during exclusion. There was no support for the collectivism hypothesis.

Research limitations included a relatively small sample size (N = 28), a comparison of only two racial groups and that the partners in the game were virtual (pre-programmed by the experimenter).

This research offers an empirical framework for sociologists seeking to apply social theories into neurological studies.

Identifying effective coping strategies for historically oppressed racial groups.

The chapter is original for demonstrating the moderating effects of values on neural responses to exclusion for the first time and by offering a novel neurosociological framework.

The purpose of this paper is to explore the challenges faced by the automatic recognition systems over the conventional systems by implementing a novel approach for detecting and recognizing the vehicle license plates in order to increase the security of the vehicles. This will also increase the societal discipline among vehicle users.

From a methodological point of view, the proposed system works in three phases which includes the pre-processing of the input image from the database, applying segmentation to the processed image, and finally extracting and recognizing the image of the license plate.

The proposed paper provides an analysis that demonstrates the correctness of the algorithm to correctly capture the license plate using performance metrics such as detection rate and false positive rate. The obtained results demonstrate that the proposed algorithm detects vehicle license plates and provides detection rate of 93.34 percent with false positive rate of 6.65 percent.

The proposed license plate detection system eliminates the need of manually used systems for managing the traffic by installing the toll-booths on freeways and bridges. The design implemented in this paper attempts to capture the license plate by using three phase detection process that helps to increase the level of security and contribute in making a sustainable city.

This paper presents a distinctive approach to detect the license plate of the vehicles using the various image processing techniques such as dilation, grey-scale conversion, edge processing, etc. and finding the region of interest of the segmented image to capture the license plate of the vehicles.

In clinical analysis, medical image segmentation is an important step to study the anatomical structure. This helps to diagnose and classify abnormality in the image. The wide variations in the image modality and limitations in the acquisition process of instruments make this segmentation challenging. This paper aims to propose a semi-automatic model to tackle these challenges and to segment medical images.

The authors propose Legendre polynomial-based active contour to segment region of interest (ROI) from the noisy, low-resolution and inhomogeneous medical images using the soft computing and multi-resolution framework. In the first phase, initial segmentation (i.e. prior clustering) is obtained from low-resolution medical images using fuzzy C-mean (FCM) clustering and noise is suppressed using wavelet energy-based multi-resolution approach. In the second phase, resultant segmentation is obtained using the Legendre polynomial-based level set approach.

The proposed model is tested on different medical images such as x-ray images for brain tumor identification, magnetic resonance imaging (MRI), spine images, blood cells and blood vessels. The rigorous analysis of the model is carried out by calculating the improvement against noise, required processing time and accuracy of the segmentation. The comparative analysis concludes that the proposed model withstands the noise and succeeds to segment any type of medical modality achieving an average accuracy of 99.57%.

The proposed design is an improvement to the Legendre level set (L2S) model. The integration of FCM and wavelet transform in L2S makes model insensitive to noise and intensity inhomogeneity and hence it succeeds to segment ROI from a wide variety of medical images even for the images where L2S failed to segment them.