Improved Edge Detection Method Research Articles

Boundaries identification of geological structure in lunar Oceanus Procellarum region using full gravity gradient tensor methodology

Boundary recognition visually delineates the horizontal extent of subsurface anomalies, providing a foundational basis for interpreting gravity data. Compared to gravity observations, gravity gradient data offers the benefits of multiple components and the enhancement of shortwave information in graphical representations. In our study, we investigated the delineation of geological structure boundaries in the lunar Oceanus Procellarum region using gravity gradient techniques. First, based on the observations from the Gravity Recovery and Interior Laboratory (GRAIL) mission, we obtained high-precision synthetic full tensor values of the gravity gradient as our primary research data. Moreover, to reduce curvature errors during large-scale terrain forward modeling, we applied the spherical prism of tesseroid to eliminate the effects of near-surface topography. Grounded on the Bouguer anomalies of gravity gradient, four distinct boundary recognition methods have been employed to explore the geological structure of the lunar Oceanus Procellarum region. It includes the Theta map method, the directional Theta map method, the combination of total horizontal derivative and the modulus of full tensor gravity gradient, and the improved edge detection method based on the Theta map method.The common feature of these methods is the utilization of the multi-component data combination from gravity gradient tensors, which can enhance the accuracy of edge detection. From the investigation results presented in the paper, we have found the following: 1) The improved edge detection method, based on the Theta map principle, enables better identification of the center of subsurface anomaly bodies during boundary recognition, utilizing a consistent single color in graphic displays. 2) According to the results of boundary recognition, numerous strip anomalies exist in the Oceanus Procellarum area that show less correlation with topographic relief. One possible explanation for these graphical anomalies of gravity gradient is that they serve as channels for the upwelling of mantle material during lunar evolution.

Geo‐information mapping improves Canny edge detection method

AbstractAiming at the shortcomings of the current Canny edge detection method in terms of noise removal, threshold setting, and edge recognition, this paper proposes a method for improving Canny edge detection by geo‐information mapping. The shortcomings of the traditional Canny edge detection method are analyzed by using the Canny optimal criterion and Tobler's First Law, which points out the direction of edge detection optimization by using the difference between edge properties and noise properties. The property characteristics and spatial distribution rules of edge points and edge lines are inspected using the geographic information mapping theory and technical methods, and edge identification criteria are defined at two levels of edge points and edge lines. Finally, the method model of improved Canny edge detection is constructed by combining guided filtering. The experimental results show that the improved edge detection method has the advantages of enriched edge details, accurate edge recognition, and strong self‐adaptive capability. This is a new attempt of geo‐information mapping theory and technical method in image edge detection, which has certain theoretical significance and strong practical guidance.

An Adaptive Two-Stage Load Event Detection Method for Nonintrusive Load Monitoring

Load event detection is fundamental to event-based nonintrusive load monitoring (NILM) solution. It is directly related to whether the transient and steady-state signatures of appliances can be accurately extracted. In the real world, the load composition is random and complicated, the power consumption patterns of appliances are diverse, and multiple events may occur simultaneously or near each other, all these make it difficult for any one single event detection method to achieve satisfactory robustness. In coping with this, an adaptive two-stage event detection method is proposed in this article. First, an adaptive detection threshold whose value can be adjusted adaptively according to the load fluctuations is adopted, thus improving the ability to detect events of different amplitudes. Then, considering the different event geometric features, an improved edge detection method and a window-based detection method combining moving average with moving t-test are proposed for step-like events and long-transient events, respectively, and they are executed consecutively to achieve the effective capture of the complete transient process of appliances. Furthermore, an event separation step is taken to locate and separate the near-simultaneous events which often appear in low-frequency data. Specific event detection performance evaluation metrics are also designed. Comparison test results on private and public datasets show that the proposed method achieves high detection accuracy for different events of various appliances and maintains strong robustness in different operation scenarios.

Using Improved Edge Detection Method to Detect Mining-Induced Ground Fissures Identified by Unmanned Aerial Vehicle Remote Sensing

Information on the ground fissures induced by coal mining is important to the safety of coal mine production and the management of environment in the mining area. In order to identify these fissures timely and accurately, a new method was proposed in the present paper, which is based on an unmanned aerial vehicle (UAV) equipped with a visible light camera and an infrared camera. According to such equipment, edge detection technology was used to detect mining-induced ground fissures. Field experiments show high efficiency of the UAV in monitoring the mining-induced ground fissures. Furthermore, a reasonable time period between 3:00 am and 5:00 am under the studied conditions helps UAV infrared remote sensing identify fissures preferably. The Roberts operator, Sobel operator, Prewitt operator, Canny operator and Laplacian operator were tested to detect the fissures in the visible image, infrared image and fused image. An improved edge detection method was proposed which based on the Laplacian of Gaussian, Canny and mathematical morphology operators. The peak signal-to-noise rate, effective edge rate, Pratt’s figure of merit and F-measure indicated that the proposed method was superior to the other methods. In addition, the fissures in infrared images at different times can be accurately detected by the proposed method except at 7:00 am, 1:00 pm and 3:00 pm.

Research on Edge Detection Method Based on Improved HED Network

Aiming at the problem of rough and fuzzy edges generated by the current edge detection technology based on HED network, an improved edge detection method for HED network is proposed. First, the useful information captured by each convolutional layer of HED becomes rougher as the size of the acceptance field increases. The improved HED network makes use of all the information of the convolution layer to capture more targets in a larger range, or make the local boundaries of the targets possible. The improved HED makes full use of the multi-scale and multi-level information of the target to obtain high-precision and high-quality edge maps, which lays a good foundation for image segmentation.

Foreign object recognition technology for port transportation channel based on automatic image recognition

In the port transportation, the transportation vehicle is extremely easy to cause a bad condition in the transportation process due to the influence of foreign matter, and the current foreign matter detection is still carried out by manual methods. Based on this, this study is based on the automatic image recognition technology, using the binocular imaging system for video collection and analyzing the video images for foreign object recognition. We use extreme median filtering to perform image noise processing and improve the traditional Canny edge detection algorithm to obtain an improved edge detection method for Canny operator. The algorithm is used to perform image edge detection, and the image gray histogram is used to enhance the foreign object image processing. Combined with the experimental analysis, the detection method of this study has certain effects, which can be used for foreign object identification in port transportation channels and can provide theoretical reference for subsequent related research.

Oil Spill Detection from Synthetic Aperture Radar Image through Improved Edge Detection Method

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

Edge Detection with Non-uniform Assembly Coefficients and Self-Adaptive Merge Weights for RGB Image

Abstract We discuss an improved edge detection method with non-uniform assembly coefficients and self-adaptive merge weights for RGB image based on morphology operators and gradient. First, we present edge detection with non-uniform assembly coefficients for grey-level image, while previous methods are with uniform assembly coefficients. And then, we discuss edge detection with non-uniform assembly coefficients and equal merge weights by means of multi-scales structure elements for RGB image. Finally, we propose an improved edge detection method with non-uniform assembly coefficients and self-adaptive merge weights for RGB image. The experimental results show that our method has improved the performance of edge detection.

Fast damage detection of cable-stayed bridges using an improved edge-detection method

The edge-detection method based on polynomial annihilation that was recently proposed has been applied to locate small damage in structures and demonstrated its effectiveness on beam-like structures. However, significant computational effort involved in this method lengthens the damage detection process, which forbids real-time damage detection. To alleviate this difficulty, in this article, we improve the method suggested by Surace and colleagues by first using the divided difference approach on the identified mode shapes to identify the regions in which jump discontinuities are potentially located and then only applying the polynomial annihilation derivative detector to data points in the identified regions. In this way, the computational burden of this approach is significantly relieved, while the accuracy of damage location is still maintained. The improved method has been validated by numerical simulations on a complex cable-stayed bridge model. This approach does not require baseline response data of structures.

Semiautomatic interpretation of microgravity data from subsurface cavities using curvature gradient tensor matrix

ABSTRACTWe propose an effective technique, based on eigenvalues of the curvature gradient tensor matrix (CGTM), to determine edges and depths of shallow subsurface cavities. The new technique is similar to the tilt angle and tilt‐depth methods in edge detection and depth estimation, respectively. Our improvement to this method is that the vertical derivative of the tilt angle is replaced by an eigenvalue of the CGTM. Zero contours of eigenvalues of the CGTM can be used to outline the edges of causative sources, and the characteristic is similar to the vertical derivative of gravity field. Therefore, we use the smaller of the two eigenvalues to replace the vertical derivative in the numerator of the tilt angle, and this results in an improved edge detection method. In addition, we deduce a new depth estimation method using the point mass model parameters which can be used to estimate the centre depths of shallow causative sources. The new method is tested on a synthetic model with and without noise. It demonstrates that the new method is simple, robust and accurate. Finally, we apply the method on the measured gravity data of a mining subsidence area from Liaoyuan, Northeast of China. The results show a good correspondence with the inversion results of electrical resistivity tomography (ERT) data. Such results can serve as preliminary depth estimates and location of near surface cavities.

Multi-information Based Safe Area Step Selection Algorithm for UAV’s Emergency Forced Landing

In order to solve the problem of forced landing in emergency for Unmanned Aerial Vehicles (UAVs), a multi-information based algorithm for selecting forced landing area by step is proposed. In order to extract the slowly varying edges and weak edges in an aerial image, this algorithm adopted improved edge detection method to detect landing area without obstacles. To select the detected safe areas which are suitable for landing in terms of size and shape, four masks with adequate coverage were designed. The elevation data of the areas were acquired to analyze its terrain. By extracting features of color and texture based on Gray Level Co-Occurrence Matrix (GLCM), fast classification and recognition of landing areas was carried out based on Support Vector Machine (SVM) classifier. Simulation results show that the algorithm, comparing with Bayesian classifier, presents a more fast and accurate classification and selection of the landing areas, fulfilling the demand of forced landing for UAVs in emergency.

Application of Image Processing in Plasma Jet Morphological Analysis

The morphology of plasma jet (PJ) directly demonstrates whether the procedure of spray processes is stable. The paper proposes an acquisition system of PJ images and an improved edge detection method is presented to get the morphology of PJ. Firstly, the PJ images are gray enhanced to remove the influence of noises. Then they are enhanced with edge sharpening. At last, they are edge detected through Canny, Laplacian and Sobel operator. From the results we can see that the improved method can get more clear and more complete PJ image morphology than traditional one. The processing methods provide foundation for the online detection of PJ morphology and for diagnosing the forming quality.

Human face detection in a complex background

The human face is a complex pattern. Finding human faces automatically in a scene is a difficult yet significant problem. It is the first important step in a fully automatic human face recognition system. In this paper a new method to locate human faces in a complex background is proposed. This system utilizes a hierarchical knowledge-based method and consists of three levels. The higher two levels are based on mosaic images at different resolutions. In the lower level, an improved edge detection method is proposed. In this research the problem of scale is dealt with, so that the system can locate unknown human faces spanning a wide range of sizes in a complex black-and-white picture. Some experimental results are given.