This paper presents a method for the extraction of blood vessels from fundus images. The proposed method is an unsupervised learning method which can automatically segment retinal blood vessels based on an adaptive random sampling algorithm. This algorithm consists in taking an adequate number of random samples in fundus images, and all the samples are contracted to the position of the blood vessels, then the retinal vessels will be revealed. The basic algorithm framework is presented in this paper and several preliminary experiments validate the feasibility and effectiveness of the proposed method.
The seam tracking system is designed for welds with very small gaps. This system is based on vision sensing technology. This system uses LED lamp as auxiliary light source, CCD camera as image acquisition unit and industrial computer as system control core. This system can extract the weld location information through a variety of image processing algorithms. After calculating the position deviation between the weld seam and torch, the system can control the actuator to look for the center of the weld. So the goal of weld seam tracking can be achieved.
Le benchmarking de performance est un thème important dans la robotique. C'est un moyen essentiel de comparer des solutions dans des conditions différentes. Dans cet article, nous nous intéressons à l'analyse comparative des performances des systèmes multi-robots dans le cadre de l'exploration et la cartographie d'espaces inconnus. Nous proposons une sélection de métriques pour comparer objectivement les algorithmes de coordination de systèmes multi-robots pour l'exploration. Ce travail est une démarche concrète pour résoudre le problème général de l'évaluation quantitative de différents algorithmes de coordination multi-robots. En plus de ces métriques, nous identifions des paramètres qui influent sur la performance de flottes robotiques. En faisant varier ces paramètres, nous arrivons à identifier les atouts et les limites d'un algorithme. Nous illustrons ces contributions avec des simulations réalistes d'une stratégie d'exploration basée sur les frontières. Ces simulations ont été mises en oeuvre à l'aide de l'intergiciel ROS (Robot Operating System). ABSTRACT. Performance benchmarking has become an important topic within robotics. It is indeed, a critical way to compare different solutions under different conditions. In this paper, we focus on performance benchmarking of multi-robot systems which explore and map unknown terrains. We summarize metrics to objectively compare different algorithms that can be applied to collaborative multi-robot exploration. This work is also a first concrete step to address the general problem of objectively comparing different multi-robot coordination algorithms. We also identify parameters that impact robotic fleet performances. By varying these parameters, we can identify strengths and limits of an algorithm. We illustrate these contributions with realistic benchmark simulations of the frontier-based exploration strategy. The simulations were implemented in ROS (Robot Operating System).
In this paper, a set of industrial X-ray film digitizing and automatic identification system is established with machine vision equipment. With this system, the industrial film can be digitalized rapidly and in high space resolution reaching to 860 DPI. The machine vision equipment includes linear CCD, light source, lens, aperture and film-moving machine. The controller is a master-slave mode, which includes a PC as the upper computer and an embedded system as the lower computer. The embedded system is composed by ARM and FPGA modules, which can control four axis motors and transmit an external trigger signals to the CCD in real-time. At last, a series of image processing algorithm is also developed in this paper to identify an industrial film that is captured to test coupling alignment of the casing pipes. The testing accuracy is 0.06mm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.