{"title":"用自动视觉检测系统进行实验","authors":"E.C. Chalfont, B. Bon, W.S. Kim","doi":"10.1109/ICAR.1997.620298","DOIUrl":null,"url":null,"abstract":"Experiments were performed with the JPL automated visual inspection system that detects potential flaws in the exterior of the Space Station by comparing reference and comparison images. The imaging system consists of cameras, strobe lights, an image processor, and a simulated sunlight source. Two color CCD cameras with electronic shuttering (Toshiba IK-M41A) and two strobe lights (EG&G MVS5000) are mounted on the end of a seven DOF Robotics Research Corporation arm as part of an integrated multi-sensor end effector. The entire robot arm is mounted on a l DOF mobile rail platform. Three main components evaluated are: 1) image-differencing-based ambient light compensation, 2) electronic-shuttering-based ambient light rejection, and 3) image registration. The results indicate that the ambient light compensation algorithm yields 0.01% to 0.4% false flaws with lab-simulated sunlight changing front 25%; to 100% intensity. Electronic shuttering with synchronized strobe lighting reduces false flaws considerably. As exposure shortens from 1/60 (fully open) to 1/1000 second, false flaws decrease 100-fold from 0.4% to 0.004%. The current registration algorithm corrects a very limited range of misregistration, correcting approximately 4 pixels of pure translational shifts over the inspection surface. A more robust image registration algorithm that can correct both translational and rotational shifts over 10 pixels misregistration would be highly desirable.","PeriodicalId":228876,"journal":{"name":"1997 8th International Conference on Advanced Robotics. Proceedings. ICAR'97","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1997-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Experiments with an automated visual inspection system\",\"authors\":\"E.C. Chalfont, B. Bon, W.S. Kim\",\"doi\":\"10.1109/ICAR.1997.620298\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Experiments were performed with the JPL automated visual inspection system that detects potential flaws in the exterior of the Space Station by comparing reference and comparison images. The imaging system consists of cameras, strobe lights, an image processor, and a simulated sunlight source. Two color CCD cameras with electronic shuttering (Toshiba IK-M41A) and two strobe lights (EG&G MVS5000) are mounted on the end of a seven DOF Robotics Research Corporation arm as part of an integrated multi-sensor end effector. The entire robot arm is mounted on a l DOF mobile rail platform. Three main components evaluated are: 1) image-differencing-based ambient light compensation, 2) electronic-shuttering-based ambient light rejection, and 3) image registration. The results indicate that the ambient light compensation algorithm yields 0.01% to 0.4% false flaws with lab-simulated sunlight changing front 25%; to 100% intensity. Electronic shuttering with synchronized strobe lighting reduces false flaws considerably. As exposure shortens from 1/60 (fully open) to 1/1000 second, false flaws decrease 100-fold from 0.4% to 0.004%. The current registration algorithm corrects a very limited range of misregistration, correcting approximately 4 pixels of pure translational shifts over the inspection surface. A more robust image registration algorithm that can correct both translational and rotational shifts over 10 pixels misregistration would be highly desirable.\",\"PeriodicalId\":228876,\"journal\":{\"name\":\"1997 8th International Conference on Advanced Robotics. Proceedings. ICAR'97\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1997-07-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"1997 8th International Conference on Advanced Robotics. Proceedings. ICAR'97\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAR.1997.620298\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"1997 8th International Conference on Advanced Robotics. Proceedings. ICAR'97","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAR.1997.620298","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Experiments with an automated visual inspection system
Experiments were performed with the JPL automated visual inspection system that detects potential flaws in the exterior of the Space Station by comparing reference and comparison images. The imaging system consists of cameras, strobe lights, an image processor, and a simulated sunlight source. Two color CCD cameras with electronic shuttering (Toshiba IK-M41A) and two strobe lights (EG&G MVS5000) are mounted on the end of a seven DOF Robotics Research Corporation arm as part of an integrated multi-sensor end effector. The entire robot arm is mounted on a l DOF mobile rail platform. Three main components evaluated are: 1) image-differencing-based ambient light compensation, 2) electronic-shuttering-based ambient light rejection, and 3) image registration. The results indicate that the ambient light compensation algorithm yields 0.01% to 0.4% false flaws with lab-simulated sunlight changing front 25%; to 100% intensity. Electronic shuttering with synchronized strobe lighting reduces false flaws considerably. As exposure shortens from 1/60 (fully open) to 1/1000 second, false flaws decrease 100-fold from 0.4% to 0.004%. The current registration algorithm corrects a very limited range of misregistration, correcting approximately 4 pixels of pure translational shifts over the inspection surface. A more robust image registration algorithm that can correct both translational and rotational shifts over 10 pixels misregistration would be highly desirable.