N. Nasrabadi, Wei Li, Bradley G. Epranian, Charles A. Butkus
{"title":"使用Hopfield网络进行立体视觉通信","authors":"N. Nasrabadi, Wei Li, Bradley G. Epranian, Charles A. Butkus","doi":"10.1109/ICSMC.1989.71331","DOIUrl":null,"url":null,"abstract":"An optimization approach is used to solve the correspondence problem for a set of features extracted from a pair of stereo images. A cost function is defined to represent the constraints on the solution which is then mapped onto a 2-D neural network for minimization. Each neuron in the network represents a possible match between a feature in the left image and one in the right image. Correspondence is achieved by initializing all the neurons that represent the possible matches and allowing the network to use the compatibility measures between the matched points to settle down into a stable state.<<ETX>>","PeriodicalId":72691,"journal":{"name":"Conference proceedings. IEEE International Conference on Systems, Man, and Cybernetics","volume":"7 1","pages":"429-432 vol.2"},"PeriodicalIF":0.0000,"publicationDate":"1989-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Use of Hopfield network for stereo vision correspondence\",\"authors\":\"N. Nasrabadi, Wei Li, Bradley G. Epranian, Charles A. Butkus\",\"doi\":\"10.1109/ICSMC.1989.71331\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An optimization approach is used to solve the correspondence problem for a set of features extracted from a pair of stereo images. A cost function is defined to represent the constraints on the solution which is then mapped onto a 2-D neural network for minimization. Each neuron in the network represents a possible match between a feature in the left image and one in the right image. Correspondence is achieved by initializing all the neurons that represent the possible matches and allowing the network to use the compatibility measures between the matched points to settle down into a stable state.<<ETX>>\",\"PeriodicalId\":72691,\"journal\":{\"name\":\"Conference proceedings. IEEE International Conference on Systems, Man, and Cybernetics\",\"volume\":\"7 1\",\"pages\":\"429-432 vol.2\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1989-11-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Conference proceedings. IEEE International Conference on Systems, Man, and Cybernetics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSMC.1989.71331\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference proceedings. IEEE International Conference on Systems, Man, and Cybernetics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSMC.1989.71331","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Use of Hopfield network for stereo vision correspondence
An optimization approach is used to solve the correspondence problem for a set of features extracted from a pair of stereo images. A cost function is defined to represent the constraints on the solution which is then mapped onto a 2-D neural network for minimization. Each neuron in the network represents a possible match between a feature in the left image and one in the right image. Correspondence is achieved by initializing all the neurons that represent the possible matches and allowing the network to use the compatibility measures between the matched points to settle down into a stable state.<>