A Proposed Approach to Determine the Edges in SAR images

Iraqi Journal of Science ◽

10.24996/ijs.2020.61.1.21 ◽

2020 ◽

pp. 185-192

Author(s):

Rabab Farhan Abbas

Keyword(s):

Edge Detection ◽

Electromagnetic Waves ◽

Operator Method ◽

Bézier Curve ◽

Bezier Curve ◽

Edge Image ◽

Sar Images ◽

Wavelet Method ◽

Radar Images ◽

Sobel Operator

Radar is the most eminent device in the prolonged scattering era The mechanisms involve using electromagnetic waves to take Synthetic Aperture Radar (SAR) images for long reaching. The process of setting edges is one of the important processes used in many fields, including radar images, which assists in showing objects such as mobile vehicles, ships, aircraft, and meteorological and terrain forms. In order to accurately identify these objects, their edges must be detected. Many old-style methods are used to isolate the edges but they do not give good results in the determination process. Conservative methods use an operator to detect the edges, such as the Sobel operator which is used to perform edge detection where the edge does not appear well. The proposed method which combines Ridgelet transform, Bezier curve and Sobel operator is used to detect edges very efficiently. Ridghelet transform resolves the harms in the wavelet transform and it can well detect the edges in images. Bezier curve can profit gradual variation of the data and their mutability. Hence, the efficiency of the edged image is improved and, when used with Sobel operator, the quality of the edge image become very good. The data show that the advocated method has superior fallouts over the Sobel edge detection and the wavelet method in both subjective and impartial experiments. While the Peak Signal to Noise Ratio(PSNR) values were equal to 9.3812, 9.8918, 9.6521 and 9.0743using the Sobel operator method and to10.2564, 10.7927, 10.5612and 10.8633 using the wavelet method, they were increased in the proposed method to 12.6542, 12.9514, 12.8574 and 12.3013 respectively.

Download Full-text

Edge Detection of Inner Crack Defects Based on Improved Sobel Operator and Clustering Algorithm

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.55-57.467 ◽

2011 ◽

Vol 55-57 ◽

pp. 467-471 ◽

Cited By ~ 3

Author(s):

Ke Fei Wang

Keyword(s):

Edge Detection ◽

Clustering Algorithm ◽

Detection Methods ◽

Experimental Result ◽

Edge Image ◽

Positioning Accuracy ◽

Sobel Operator ◽

Image Edge Detection ◽

Image Edge ◽

Sobel Edge Detection

The classical Sobel edge detection operator has the shortcomings of low edge positioning accuracy and coarse edge, image edge detection based on improved Sobel operator and clustering algorithm was proposed. Four Sobel-like edge operators are used to improve the edge positioning accuracy and clustering algorithm are used to edge thinning. The experimental result demonstrates that the effect of the edge detection is greatly improved comparing with the traditional edge detection methods.

Download Full-text

FPGA Implementation of Fuzzy Inference System Based Edge Detection Algorithm

International Journal of Computational Intelligence and Applications ◽

10.1142/s1469026815500091 ◽

2015 ◽

Vol 14 (02) ◽

pp. 1550009

Author(s):

D. Selvathi ◽

Henry Selvaraj ◽

J. Dharani

Keyword(s):

Edge Detection ◽

Fuzzy Inference System ◽

Hardware Implementation ◽

Fuzzy Inference ◽

Detection Algorithm ◽

Fpga Implementation ◽

Human Vision ◽

Edge Image ◽

Inference System ◽

Sobel Operator

Edge detection is a very important area in the field of Computer Vision. Edge detectors behave very poorly, their behavior may fall within tolerance in specific situations and have difficulty in adapting to different situations. Human vision is inherently a multiscale phenomenon and is sensitive to orientation and elongation. This work proposes the hardware implementation of efficient fuzzy logic based algorithm, which is used to detect the edges of an image without determining the threshold value. Edge detection in software is not suited for strong real-time applications. This problem is resolved by using hardware implementation on field programmable gate arrays (FPGAs). Fuzzy inference system is developed with four input pixel containing two fuzzy sets (FSs) one for white and another for black and one output pixel containing three FSs for white, black and edge. Fuzzy if-then rules are used to modify the membership functions. Finally, Mamdanidefuzzifier method is used to form the final edge image. For comparison, the same work was implemented using sobel operator. The hardware part is developed by using Verilog language. The FPGA implementation is targeted on Virtex5 Starter kit (xc5vlx50tff1136-1) and Virtex7 starter kit (xc7vx485tffq1157-1) using the updated Xilinx PlanAhead within the ISE 13.4 development suite. The edge thickness can be changed easily by adding new rules or changing output parameters. That is, rule-based approach has flexible structure that can be easily adapted to any time or anywhere and the new fuzzy approach produces better result than sobel operator. Experimental results show the ability and high performance of the proposed algorithm.

Download Full-text

Edge detection in SAR images of transform domain

Journal of Computer Applications ◽

10.3724/sp.j.1087.2009.02402 ◽

2009 ◽

Vol 29 (9) ◽

pp. 2402-2405 ◽

Cited By ~ 2

Author(s):

Zhen MEI ◽

Wei LIN ◽

Rui-xia WANG

Keyword(s):

Edge Detection ◽

Transform Domain ◽

Sar Images

Download Full-text

A NURBS transition between a Bézier curve and its control polygon

Journal of Computational and Applied Mathematics ◽

10.1016/j.cam.2021.113626 ◽

2021 ◽

pp. 113626

Author(s):

Imre Juhász

Keyword(s):

Bézier Curve ◽

Bezier Curve ◽

Control Polygon

Download Full-text

Optimal Bezier Curve Modification Function for Contrast Degraded Images

IEEE Transactions on Instrumentation and Measurement ◽

10.1109/tim.2021.3073320 ◽

2021 ◽

Vol 70 ◽

pp. 1-10

Author(s):

Bharath Subramani ◽

Ashish Kumar Bhandari ◽

Magudeeswaran Veluchamy

Keyword(s):

Bézier Curve ◽

Bezier Curve ◽

Degraded Images

Download Full-text

Automatic Lane-Changing Decision Based on Single-Step Dynamic Game with Incomplete Information and Collision-Free Path Planning

Actuators ◽

10.3390/act10080173 ◽

2021 ◽

Vol 10 (8) ◽

pp. 173

Author(s):

Hongbo Wang ◽

Shihan Xu ◽

Longze Deng

Keyword(s):

Path Planning ◽

Dynamic Game ◽

Single Step ◽

Bézier Curve ◽

Vehicle Safety ◽

Bezier Curve ◽

Lane Change ◽

Hardware In The Loop ◽

Power Performance ◽

Lane Changing

Traffic accidents are often caused by improper lane changes. Although the safety of lane-changing has attracted extensive attention in the vehicle and traffic fields, there are few studies considering the lateral comfort of vehicle users in lane-changing decision-making. Lane-changing decision-making by single-step dynamic game with incomplete information and path planning based on Bézier curve are proposed in this paper to coordinate vehicle lane-changing performance from safety payoff, velocity payoff, and comfort payoff. First, the lane-changing safety distance which is improved by collecting lane-changing data through simulated driving, and lane-changing time obtained by Bézier curve path planning are introduced into the game payoff, so that the selection of the lane-changing start time considers the vehicle safety, power performance and passenger comfort of the lane-changing process. Second, the lane-changing path without collision to the forward vehicle is obtained through the constrained Bézier curve, and the Bézier curve is further constrained to obtain a smoother lane-changing path. The path tracking sliding mode controller of front wheel angle compensation by radical basis function neural network is designed. Finally, the model in the loop simulation and the hardware in the loop experiment are carried out to verify the advantages of the proposed method. The results of three lane-changing conditions designed in the hardware in the loop experiment show that the vehicle safety, power performance, and passenger comfort of the vehicle controlled by the proposed method are better than that of human drivers in discretionary lane change and mandatory lane change scenarios.

Download Full-text