Seismic Swell Effect Correction Using GVF-Based Guideline

Summary The quality of high-resolution marine 8-channel air gun seismic data can be enhanced by correcting for the effects of swell using the average of previously detected depth values. To apply this correction, we detected and calculated the average two-way travel times of sea bottom depths in seismic data acquired offshore near Yeosu, Korea, and then corrected for the differences between the detected and averaged values. Automatic sea bottom detection is required to obtain sea bottom locations from numerous seismic traces. However, it is difficult to detect locations when the sea bottom signal is unclear due to noise generated by the motion of the sea. We chose reliable sea bottom locations within a certain range around the averaged sea bottom depth. We achieved reasonable detection results using our method. Correcting for swell significantly improved noisy data and produced relatively high-quality seismic sections.

In order to solve the problem that all levels of civil aviation meteorological centers are unable to provide all the possible meteorological information services that may reach the low-altitude airspace for general aviation flight, this paper proposes a real-time low-altitude meteorological intelligence image collection and processing method. Based on this method, a real-time low-altitude meteorological intelligence image collection system can be designed and implemented. The real-time low-altitude meteorological intelligence image collection system is an information system that provides real-time low-altitude airspace visibility and weather condition information services for image-based flight photography, transmission, processing, and meteorological information dissemination. It includes the image collection subsystem and image processing subsystem, meteorological information publishing Web Server. Among them: The image collection subsystem is mainly used for automatically taking images of the surrounding environment at regular intervals, and transmitting the photographs and their time and place information to the image processing system installed in the low-altitude navigational information service department through the wireless communication device; the image processing subsystem collects images and related information for further processing; the meteorological information publication Web server mainly provides general airline users with services such as consultation, inquiry, and submission of low-altitude meteorological intelligence information of relevant airspace related to images.

Image binarization is one of the fundamental methods in image processing and it is mainly used as a preprocessing for other methods in image processing. We present an image binarization method with the primary purpose to find markers such as those used in mobile 3D scanning systems. Handling a mobile 3D scanning system often includes bad conditions such as light reflection and non-uniform illumination. As the basic part of the scanning process, the proposed binarization method successfully overcomes the above problems and does it successfully. Due to the trend of increasing image size and real-time image processing we were able to achieve the required small algorithmic complexity. The paper outlines a comparison with several other methods with a focus on objects with markers including the calibration system plane of the 3D scanning system. Although it is obvious that no binarization algorithm is best for all types of images, we also give the results of the proposed method applied to historical documents.

Pores are inherent to additively manufactured components and critical especially in technical components. Since they reduce the component's fatigue life, a reliable identification and description of pores is vital to ensure the component's performance. X‐ray computed tomography (CT) is an established and non‐destructive testing method to investigate internal defects. The CT scan process can induce noise and artefacts in the resulting images which afterwards have to be reduced through image processing. To reconstruct the internal defects of a component, the images need to be segmented in defect region and bulk material by applying a threshold. The application of the threshold as well as the previous image processing alter the geometry and size of the identified defects. This contribution aims to quantify the influence of selected commercial image processing and segmentation methods on identified pores in several additively manufactured components made of AlSi10Mg and Ti6Al4V as well as in an artificial CT scan. To that aim, gray value histograms and characteristic parameters thereof are compared for different image processing tools. After the segmentation of the processed images, particle characteristics are compared. The influence of image processing and segmentation on the predicted fatigue life of the material is evaluated through the change of the largest pore in each set of data applying Murakami's empirical ‐parameter model.

Content Based Image Retrieval (CBIR) has been an active and fast growing research area in both image processing and data mining. Malaysia has been recognized with a rich marine ecosystem. Challenges of these images are low resolution, translation, and transformation invariant. In this paper, we have designed an automated CBIR system to characterize the species for future research. Gradient vector flow (GVF) has been implemented in a lot of image processing applications. Inspired by its fast image restoration algorithms we applied GVF for marine images. We evaluated different automated segmentation techniques and found GVF showing better retrieval results compared to other automated segmentation techniques.

Traditional Chinese medicine (TCM) inspection is a non-invasive diagnostic method to assess patients' internal health status which relies on visual observation by TCM doctors according to their clinical experience. With artificial intelligence (AI) technology, TCM inspection can be objectified and modernized by using image processing and analysis methods. In this paper, we make a brief survey on the objective research of intelligent inspection technologies in TCM tongue diagnosis based on image object detection, segmentation and classification methods. We summarize the current research status of objectification of image-based TCM inspection including different methods and their performances in tongue diagnosis, discuss the problems in objectification of TCM inspection and point out its future development directions for research.

Computed tomography is now widely used in cardiac surgery as a method of non-destructive study of internal structure of objects, including specific tasks, such as mathematical modeling of physiological processes, surgical interventions in augmented reality, 3D printing, and radiomics. One of the key steps in creating a 3D model from computed tomography data is segmentation the process of selecting objects in the image. Currently, there are several approaches to automating the segmentation process, including image processing methods, texture analysis and machine learning algorithms (in particular, clustering). Image processing methods are the simplest of the presented approaches and are found in various applications for segmentation of tomographic data. This paper reviews the advantages and disadvantages of various image processing methods (threshold, region growing, contour detection, and morphological watersheds) as tools for automated cardiac segmentation from computed tomography data. It was revealed that computed tomography images have characteristic features affecting the segmentation process (presence of noise, partial volume effect, etc.). The choice of the segmentation method is based on the brightness characteristics of the area of interest and also requires knowledge of the subject area, so it should be performed by a specialist with competence in anatomy and digital image processing. As independent methods of automated segmentation, the listed methods are applicable only in relatively simple cases (selection of homogeneous or high-contrast areas), otherwise, a combination of these methods, the use of machine learning algorithms or manual correction of the results is required.

This study applies methods of Image processing, Haar Cascade, and PID in building a system on an autonomous car. The working system on an autonomous car has currently gained interest for the exploration. The Image processing method is utilized to detect road markings applying algorithms (BGR to RGB, Perspective transformation, threshold, canny edge, and histogram) in navigating pixel parameter values with actual distances. The parameter values in the line detection results are applied for input to the PID system, in controlling the handling of autonomous car of five seconds settling time and 1.5 cm overshoot. On the other hand, the Haar Cascade image training requires the positive (1000) and negative (1400) sample images to obtain a statistical model. Regarding the image processing test results, the correlation between the distance of the road markings and the camera pixels is 1 cm/10 pixels. This correlation hence demonstrates an accuracy of 0.1cm/pixel. The statistic test results for detecting traffic signs are obtained at a distance of 5 cm to 120 cm, with the optimal detection results at a distance of 5 cm to 90 cm. Regarding the traffic signs' point of view at an angle of 10° to 140,° optimal detection results are obtained at an angle of 20° to 1300. Meanwhile, when testing dynamically, the detection performance depends on the angle and distance of the reading as on the results of the static test and the appropriate lighting factor on the results of training sample data on traffic signs. In addition, the results of the average accuracy of traffic sign detection are 92.3%.

Signal and imaging investigations are currently a basic step of the diagnostic, prognostic and follow-up processes of heart diseases. Besides, the need of a more efficient, cost-effective and personalized care has lead nowadays to a renaissance of clinical decision support systems (CDSS). The purpose of this paper is to present an effective way to achieve a high-level integration of signal and image processing methods in the general process of care, by means of a clinical decision support system, and to discuss the advantages of such an approach. Among several heart diseases, we treat heart failure, that for its complexity highlights best the benefits of this integration. Architectural details of the related components of the CDSS are provided with special attention to their seamless integration in the general IT infrastructure. In particular, significant and suitably designed image and signal processing algorithms are introduced to objectively and reliably evaluate important features that, in collaboration with the CDSS, can facilitate decisional problems in the heart failure domain. Furthermore, additional signal and image processing tools enrich the model baseof the CDSS.

With the rapid development of autonomous driving technology, traditional object detection algorithms often face challenges such as the trade-off between model parameters and recognition accuracy, insufficient detection accuracy, and slow detection speed when dealing with vehicle and pedestrian detection tasks in complex scenarios. To address these challenges, we propose a novel lightweight real-time driving scene detection network, FEEP-YOLO. Based on the YOLOv8 algorithm, our network not only maintains high detection accuracy but also achieves faster training speed and fewer model parameters. FEEP-YOLO employs a lightweight network, Faster Net, to significantly reduce model parameters, thereby accelerating detection speed and better meeting real-time requirements. To further improve detection accuracy, we introduce an EMA attention module into the network and optimize the bounding box loss function, adopting the EIOU loss function to enhance target features and reduce background interference. Additionally, to detect small objects more accurately, we add feature layers rich in semantic information to the detection end. Experimental results demonstrate that FEEP-YOLO outperforms YOLOv8 in terms of both detection speed and accuracy on the KITTI and SODA datasets, while significantly reducing the number of model parameters and model size. FEEP-YOLO achieves high detection speed while improving detection accuracy and reducing computational resource consumption, meeting the practical application requirements under limited computing power, memory space and power consumption. The key contribution of FEEP-YOLO lies in its ability to balance accuracy speed, and efficiency, making it a robust solution for real-time autonomous driving applications in complex environments.

The objective of this study is to quantify the in vivo kinematics of the superficial femoral artery (SFA) caused by hip and knee flexion by utilizing vascular and skeletal magnetic resonance (MR) imaging and image processing methods. Seven male healthy volunteers (56 ± 5 years old) were imaged using contrast-enhanced MR angiography in the supine and bent-leg positions using a GE Signa Excite 1.5-T scanner. Coregistered SFA coordinates from these two body positions provide the relative motion of the SFA with respect to the femur as a result of hip and knee flexion. With 86 ± 6° hip and 39 ± 6° knee flexion angles, the proximal portion of the SFA moved significantly inferiorly while the distal portion of the SFA stayed immobile in relation to the femur due to hip and knee flexion. From the supine position to the bent-leg position, the top of the SFA moved 23.5 ± 7.0 mm closer to the bottom of the SFA (p < 0.05), resulting in shortening and buckling of the SFA. The differential translations of points along the SFA indicate shortening and buckling along the length of the vessel. They also indicate that the SFA is more tethered to the bony structures at the knee compared to the thigh. The in vivo SFA kinematics obtained in this study provides insight into the interaction between the SFA and the surrounding musculoskeletal structures.

SEM microscopy is a primary method for CD measurements of features on sub-micron scale. The process of feature characterization using SEM involves several steps that include image acquisition, image processing, image analysis and data analysis. Each one of these steps carries an error margin that contributes to the overall accuracy of measurements. While performing measurements at the nanoscale resolution the accuracy of the process becomes even more critical for obtaining accurate measurements, and needs to be determined and understood. Using object with known dimensions such as linewidth of an isolated polycrystalline (poly) Si lines be useful for evaluating accuracy of the characterization process and calibrating SEM instrument. Reference materials for such evaluation are being developed by NIST. To use this approach successfully it is important to understand metrology issues involved in the image characterization process. This work will review the scope of metrology issues involved in the process of linewidth measurement using SEM imaging including image acquisition, image processing and segmentation, as well as data extraction and analysis using image analysis methods. We will review and discuss methods for evaluating accuracy throughout characterization process and obtaining reliable and repeatable measurements. The scope of study includes the use of two dimensional simulation and modeling of SEM line images, methods for grayscale image processing and segmentation, algorithms for obtaining statistically accurate linewidth measurements from the image that can be used for instrument calibration and inter-laboratory studies and are generally applicable for obtaining CD measurements of line features.

Software was developed in Python for the digital processing of object images before their detection using the You Only Look Once (YOLO) artificial neural network. Detection was carried out on object images, specifically vehicles and other road users. The preprocessing of images was performed through histogram equalization and local contrast enhancement. The original images were read from video cameras or graphic files. Image detection was performed using the medium-sized YOLO convolutional neural network model, YOLOv8m. As a result of detection, the studied objects, particularly cars, were highlighted with rectangular bounding boxes. To evaluate the accuracy of object detection, several metrics (parameters) were used: Precision, Recall, Intersection over Union (IoU), F1, and Average Precision (AP). The YOLO network was pre-trained on the Common Objects in Context dataset. The YOLO neural network returns the object recognition confidence, the coordinates of its center (x, y) on the image, and its width and height (w, h). The detected objects are marked with rectangular bounding boxes. The positioning of objects in the images was manually performed using the Roboflow tool, which allows for accurate spatial positioning of each object. The study of the impact of image preprocessing on the accuracy of object detection by the YOLO network was conducted using a typical traffic scene image. After histogram equalization, the histogram becomes more symmetrical and uniform, improving the visual quality of both dark and bright areas. This led to improved object detection accuracy across almost all metrics. The increase in detection accuracy by the IoU parameter is 0.169. The summary improvement in detection accuracy by the IoU, F1, AP parameters is 0.502. It was shown that after image preprocessing, detection accuracy increased, and all vehicles were correctly detected. The developed software can be used in various computer vision systems as well as in Internet of Things systems for remote monitoring and control.

Generalized gradient vector flow external forces for active contours

Snakes, or active contours, have been widely used in image processing applications. An external force for snakes called gradient vector flow (GVF) attempts to address traditional snake problems of initialization sensitivity and poor convergence to concavities, while generalized GVF (GGVF) aims to improve GVF snake convergence to long and thin indentations (LTIs). In this paper, we find and show that both GVF and GGVF snakes essentially yield the same performance in capturing LTIs of odd widths, and generally neither can converge to even-width LTIs. Based on a thorough investigation of the GVF and GGVF fields within the LTI during their iterative processes, we identify the crux of the convergence problem, and accordingly propose a novel external force termed as component-normalized GGVF (CN-GGVF) to eliminate the problem. CN-GGVF is obtained by normalizing each component of initial GGVF vectors with respect to its own magnitude. Experimental results and comparisons against GGVF snakes show that the proposed CN-GGVF snakes can capture LTIs regardless of odd or even widths with a remarkably faster convergence speed, while preserving other desirable properties of GGVF snakes with lower computational complexity in vector normalization.