Fast Edge Detection Based on Mathematical Morphology for Straight Line Paths of Vision Navigation in AGV System

2013 ◽  
Vol 321-324 ◽  
pp. 1093-1097 ◽  
Author(s):  
Zhong Ming Li ◽  
Zhi Yuan Su ◽  
Jing Tian Zhang

Fast processing and recognition of image have an important influence on the real-time performance of AGV by vision navigation. The fast method of edge detection based on mathematical morphology for straight line path is proposed in this paper. Binary processing is implemented firstly for path image. Then the edge detection using morphological gradient can be executed directly, and image filtering and recognition of path edge can be realized simultaneously. Kinematics model of AGV is built and the shape of structure element in morphology processing can be adjusted in real time. The results of experiment show that recognition time of straight line path is shorten by this image processing method.

2014 ◽  
Vol 610 ◽  
pp. 429-436
Author(s):  
Xun Sun ◽  
Xuan Yu Wang ◽  
Zhi Rong Luo ◽  
Han Xiao

To solve the harmony problem of accuration, real-time with anti-noise capability on edge detection of smokescreen, the edge detection algorithm of smokescreen based on multi-scale mathematical morphological is designed, and the algorithm can effectively reduce the noise of the smokescreen image. Compared with the results of classical edge detection operator: Sobel, Roberts, Prowitt and Canny etc, it is concluded that the algorithm designed has obvious advantages in continuity, smoothness, image recognition, practical complexity, operation time and other related parameters.


2012 ◽  
Vol 490-495 ◽  
pp. 919-921
Author(s):  
Ying Bo Liang ◽  
Li Hong Zhang

A novel multi-dimension and structure element edge-detection based on mathematical morphology is presented to resolve blur problem of classical morphology when detecting an edge to reduce the noise but hard to preserve the details and edge information of the original image effectively. First,pretreatment of the image are completed by close-open operation to eliminate noise; second,do close operation to smooth image,in the end,using the operation of morphological gradient for smooting image,the ideal image edge under the environment of existing noise is obtained,and it is applied to detect the edges of welding pore images. The experimental results show that it is compared with classical Sobel operators,Canny operators and traditional edge detection algorithm, the proposed algorithm has the following distinguished advantages:accuracy of edges detected, a clear outline of the image, and can preserve more image details as well, and insensitive to noise.


2013 ◽  
Vol 467 ◽  
pp. 599-603 ◽  
Author(s):  
Hui De Li ◽  
Lian Yu Zhao

The image edge detection algorithm is one of the most important steps in the image processing, however, while the large amount of data is need to be dealt with in the detection process, it is difficult to meet real-time requirements by using the software method. In order to improve the speed of digital image processing, An embedded processing systems based on FPGA (field-programmable gate array) detection algorithm is proposed, which takes corrosion expansion algorithm of mathematical morphology as its theoretical basis to achieve the task of image edge detection, experiments result show the method is effective and feasible, and meets the real-time requirement of the image processing.


2014 ◽  
Vol 595 ◽  
pp. 289-294
Author(s):  
Yi Mian Dai ◽  
Yi Quan Wu

A novel edge detection method based on anisotropic mathematical morphology and scale multiplication in nonsubsampled contourlet transform (NSCT) domain is proposed to obtain a superior and robust performance under heavy noise. One preliminary result is obtained using anisotropic morphological gradient of the low-frequency component, yielding a single-pixel response with few pseudo edges. Due to the great ability of NSCT to localize distributed discontinuities such as edges, scale multiplication results of high-frequency components can get rid of a large amount of noise and produce well-localized edge candidates. The final result is a fusion of the detection results of low-frequency component and high-frequency components. Detailed experiments compared with other state-of-the-art methods demonstrate that the proposed method has a superior performance of edge detection and is quite robust even under heavy noise.


2021 ◽  
pp. 1-30
Author(s):  
A. Guo ◽  
Z. Zhou ◽  
R. Wang ◽  
X. Zhao ◽  
X. Zhu

Abstract The full-wing solar-powered UAV has a large aspect ratio, special configuration, and excellent aerodynamic performance. This UAV converts solar energy into electrical energy for level flight and storage to improve endurance performance. The UAV only uses a differential throttle for lateral control, and the insufficient control capability during crosswind landing results in a large lateral distance bias and leads to multiple landing failures. This paper analyzes 11 landing failures and finds that a large lateral distance bias at the beginning of the approach and the coupling of base and differential throttle control is the main reason for multiple landing failures. To improve the landing performance, a heading angle-based vector field (VF) method is applied to the straight-line and orbit paths following and two novel 3D Dubins landing paths are proposed to reduce the initial lateral control bias. The results show that the straight-line path simulation exhibits similar phenomenon with the practical failure; the single helical path has the highest lateral control accuracy; the left-arc to left-arc (L-L) path avoids the saturation of the differential throttle; and both paths effectively improve the probability of successful landing.


2017 ◽  
Vol 1 (1) ◽  
pp. 152-157 ◽  
Author(s):  
Saverio Bolognani ◽  
Elena Arcari ◽  
Florian Dorfler
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document