- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) - Singapore, Singapore (2018.11.18-2018.11.21)] 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) - Virtual Commissioning of Machine Vision Applications in Aero Engine Manufacturing
摘要： New aero engine design puts new demands on the manufacturing methods with increased automation level. Therefore, the use of vision sensors for control and guiding of industrial robots is being increasingly used. In such system, it is need to customise the machine vision system with real components in the real environment which is normally done close to the start-up of the production. This paper addresses a new concept for designing, programming, analysing, testing and verifying a machine vision application early in the design phase, called Virtual Machine Vision. It is based on a robot simulation software where the real machine vision application is simulated before the implementation in the production line. To verify the Virtual Machine Vision concept an advanced stereo vision application was used. Using two captured images from the robot simulated environment, camera calibration, image analysis and stereo vision algorithms are applied to determine a desired welding joint. The information of the weld joint, i.e. robot position and orientation for the weld path, are sent from the machine vision system to the robot control system in the simulation environment and the weld path is updated. The validation of the Virtual Machine Vision concept using the stereo vision application is promising for industrial use, and it is emphasised that the same programs are used in the virtual and real word.
关键词： simulation,robotics,welding,machine vision,image processing,Virtual Machine Vision,stereo vision,camera calibration
更新于2025-09-19 17:15:36
-
[IEEE 2018 International Conference on Recent Innovations in Electrical, Electronics & Communication Engineering (ICRIEECE) - Bhubaneswar, India (2018.7.27-2018.7.28)] 2018 International Conference on Recent Innovations in Electrical, Electronics & Communication Engineering (ICRIEECE) - Simulation Of Electrical Power Generation Using Concentrated Photovoltaic Cell Through Solar Parabolic Dish Concentrator
摘要： Segmentation of partially overlapping objects with a known shape is needed in an increasing amount of various machine vision applications. This paper presents a method for segmentation of clustered partially overlapping objects with a shape that can be approximated using an ellipse. The method utilizes silhouette images, which means that it requires only that the foreground (objects) and background can be distinguished from each other. The method starts with seedpoint extraction using bounded erosion and fast radial symmetry transform. Extracted seedpoints are then utilized to associate edge points to objects in order to create contour evidence. Finally, contours of the objects are estimated by fitting ellipses to the contour evidence. The experiments on one synthetic and two different real data sets showed that the proposed method outperforms two current state-of-art approaches in overlapping objects segmentation.
关键词： image processing,overlapping objects,machine vision,convex objects,Segmentation
更新于2025-09-19 17:13:59
-
[IEEE 2019 IEEE Wireless Power Transfer Conference (WPTC) - London, United Kingdom (2019.6.18-2019.6.21)] 2019 IEEE Wireless Power Transfer Conference (WPTC) - GaN Schottky Barrier Diode for Sub-Terahertz Rectenna
摘要： Segmentation of partially overlapping objects with a known shape is needed in an increasing amount of various machine vision applications. This paper presents a method for segmentation of clustered partially overlapping objects with a shape that can be approximated using an ellipse. The method utilizes silhouette images, which means that it requires only that the foreground (objects) and background can be distinguished from each other. The method starts with seedpoint extraction using bounded erosion and fast radial symmetry transform. Extracted seedpoints are then utilized to associate edge points to objects in order to create contour evidence. Finally, contours of the objects are estimated by fitting ellipses to the contour evidence. The experiments on one synthetic and two different real data sets showed that the proposed method outperforms two current state-of-art approaches in overlapping objects segmentation.
关键词： machine vision,Segmentation,overlapping objects,convex objects,image processing
更新于2025-09-19 17:13:59
-
[IEEE 2018 11th UK-Europe-China Workshop on Millimeter Waves and Terahertz Technologies (UCMMT) - HangZhou, China (2018.9.5-2018.9.7)] 2018 11th UK-Europe-China Workshop on Millimeter Waves and Terahertz Technologies (UCMMT) - Compact Balun Filter Using Coupled Resonators
摘要： Quantitative grading of opals is a challenging task even for skilled opal assessors. Current opal evaluation practices are highly subjective due to the complexities of opal assessment and the limitations of human visual observation. In this paper, we present a novel machine vision system for the automated grading of opals—the gemological digital analyzer (GDA). The grading is based on statistical machine learning with multiple characteristics extracted from opal images. The assessment work-flow includes calibration, opal image capture, image analysis, and opal classification and grading. Experimental results show that the GDA-based grading is more consistent and objective compared with the manual evaluations conducted by the skilled opal assessors.
关键词： machine vision,Artificial intelligence,learning systems,image analysis,feature extraction
更新于2025-09-19 17:13:59
-
[IEEE IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society - Lisbon, Portugal (2019.10.14-2019.10.17)] IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society - Automatic steel bar counting in production line based on laser triangulation
摘要： Within the steel industry, hot rolling mill is the most important process in terms of quantity and variety of products. The intrinsic characteristics of such a harsh environment reduce the quantity of machine vision systems installed in this industry. Specifically, there is not industrial system in the world capable of counting reinforcing bars of any diameter with 100% of accuracy. This paper presents the development and implementation of a 3D vision system for counting reinforcing bars in a hot rolling mill overcoming the limitations of mechanical counting in existing hot rolling mills. Experimental results obtained in a real industrial environment are shown, proving the viability of the system. The proposed solution can be applied to count different diameter in actual manufacturing conditions with variable lighting conditions.
关键词： automatic rebar counting,hot rolling mill,machine vision
更新于2025-09-16 10:30:52
-
Cross-lines laser aided machine vision in tube-to-tubesheet welding for welding height control
摘要： Thermal distortion was a major issue in sheet metal welding. One particular issue to be addressed in this work for tube-to-tubesheet welding was the resultant variation in the welding torch to work distance, referred to as welding height hereafter, which can easily cause undercuts and burn-through. Unfortunately, efforts on control of welding height which was particularly critical for tube-to-tubesheet welding were limited. This paper thus introduced a machine vision system with a cross-line laser as the structured light to measure the welding height for adaptive correction and control. To extract the ICCL (intersection coordinate of cross-lines laser) which provided the variation in welding height, an image processing algorithm was proposed that segmented regions and extracted their centers. A linear relationship between WHVV (welding height variation value) and ICCL was established by least square method. Performance was tested experimentally for the experiment platform and it was found that the static and dynamic detection error were insignificant, no more than 0.007 and 0.016 mm respectively. When WHVV = 1 mm, the compensation error of 115 tubes varied from ?0.037 to +0.028 mm.
关键词： Welding height control,Cross-lines laser,Machine vision,Tube-to-tubesheet welding
更新于2025-09-12 10:27:22
-
Real-time spatter detection in laser welding with beam oscillation
摘要： Spatter formation is a longstanding issue in laser welding. This research addresses this topic and proposes a machine vision algorithm executed on a graphics processing unit to detect spatters in real time. Using this approach, a control system detecting spatter at a rate of 1 kHz and with a resolution of 900 x 900 pixels was implemented. Based on an experimental series, it is shown that the variation of the process parameters has a significant influence on the formation of spatter. It was also possible to quantify the variance of the spatter formation for a given set of process parameters.
关键词： machine vision,beam oscillation,laser welding,spatter formation,graphics processing unit
更新于2025-09-12 10:27:22
-
[IEEE 2019 Chinese Control And Decision Conference (CCDC) - Nanchang, China (2019.6.3-2019.6.5)] 2019 Chinese Control And Decision Conference (CCDC) - Research on Detection and Recognition Algorithm of Optical Fiber for Surface Defects
摘要： Based on machine vision technology, this paper studies the detection and identification technology of surface defects of optical fiber communication cables. This paper uses mathematical geometry and linear interpolation method to convert cable cylinder into plane. Based on the gray-scale characteristics of the pinhole in the picture, gray threshold and gradient amplitude are used to improve the detection rate of the pinhole. Finally, the experimental results show that this algorithm can all-around detect the surface defects of optical cable, with the minimum detection area of 0.05mm2, the diameter detection accuracy of 0.1mm, and real-time alarm for defects. In the case of a lot of dust, ensure the correct detection of conventional defects on the surface of the cable, the correct detection rate of the pinhole reaches 70%, reducing the false alarm rate of dust and water stains.
关键词： Optic Fiber,Pinhole Detecting,Defect Detecting,Machine Vision
更新于2025-09-11 14:15:04
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Unfeatured Weld Positioning Technology Based on Neural Network and Machine Vision
摘要： In machine vision, image processing technology is the basis of target recognition and positioning. When the background of the image is complex, especially when the background feature is similar to the target feature, the accuracy of the target recognition by traditional image processing methods cannot be guaranteed. In this paper, based on the background of automatic welding technology, proposing a new method of combining the neural networks and machine vision. Specifically, the image is preprocessed by using an improved convolutional auto-encoder to enhance the target features and remove the characteristics of the main interferers. Then, use image processing technology to extract the target and complete the processing of the featureless image. Finally, use a binocular camera to achieve accurate positioning of the target. This paper provides a new idea for the identification and positioning of the target.
关键词： weld positioning,machine vision,neural networks,featureless image,convolutional auto-encoder
更新于2025-09-10 09:29:36
-
[IEEE 2018 37th Chinese Control Conference (CCC) - Wuhan (2018.7.25-2018.7.27)] 2018 37th Chinese Control Conference (CCC) - A Detection System of Tool Parameter Using Machine Vision
摘要： This paper suggests a novel technique for the tool parameter measurement based on machine vision. Tool images are captured by using a machine vision system and the outer contour image of the cutter is obtained by using the machine vision technology. The HALCON image processing library is used as the development platform to build the tool parameters test system. Several algorithms including image segmentation, edge extraction and ?tting ellipse determination is used for image processing. The tool parameters such as external diameter and contour angle of tool edge can be obtained after rebuilding the contour of tool edge.The proposed scheme is shown to be reliable and effective for the automated tool parameter measurement.
关键词： tool parameter,image processing,Machine vision
更新于2025-09-10 09:29:36