{"title":"基于随机决策森林算法的数字图像圆木自动检测","authors":"Y. V. Chiryshev, A. Kruglov, Anastasia Atamanova","doi":"10.1145/3232651.3232667","DOIUrl":null,"url":null,"abstract":"The problem of automatic detection and isolation of logs in a pile based on digital image processing is investigated within this paper. At present, the approaches to determination of the qualitative and quantitative characteristics of round timber by image processing. The paper gives a review of existing methods and presents a detection algorithm that develops the previously described approach based on the histogram of oriented gradients with random decision forest. The authors thoroughly consider the problem of detector adjustment by multiple training and empirical selection of such parameters as the number, maximum depth of trees and the characteristic size of log abuts in the images of the training sample. The parameters of the detector are selected based on the requirement of high recognition rate. Due to this adjustment the algorithm was significantly improved so it surpasses analogs or shows comparable results with respect to accuracy.","PeriodicalId":365064,"journal":{"name":"Proceedings of the 1st International Conference on Control and Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Automatic Detection of Round Timber in Digital Images Using Random Decision Forests Algorithm\",\"authors\":\"Y. V. Chiryshev, A. Kruglov, Anastasia Atamanova\",\"doi\":\"10.1145/3232651.3232667\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The problem of automatic detection and isolation of logs in a pile based on digital image processing is investigated within this paper. At present, the approaches to determination of the qualitative and quantitative characteristics of round timber by image processing. The paper gives a review of existing methods and presents a detection algorithm that develops the previously described approach based on the histogram of oriented gradients with random decision forest. The authors thoroughly consider the problem of detector adjustment by multiple training and empirical selection of such parameters as the number, maximum depth of trees and the characteristic size of log abuts in the images of the training sample. The parameters of the detector are selected based on the requirement of high recognition rate. Due to this adjustment the algorithm was significantly improved so it surpasses analogs or shows comparable results with respect to accuracy.\",\"PeriodicalId\":365064,\"journal\":{\"name\":\"Proceedings of the 1st International Conference on Control and Computer Vision\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-06-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 1st International Conference on Control and Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3232651.3232667\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 1st International Conference on Control and Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3232651.3232667","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Automatic Detection of Round Timber in Digital Images Using Random Decision Forests Algorithm
The problem of automatic detection and isolation of logs in a pile based on digital image processing is investigated within this paper. At present, the approaches to determination of the qualitative and quantitative characteristics of round timber by image processing. The paper gives a review of existing methods and presents a detection algorithm that develops the previously described approach based on the histogram of oriented gradients with random decision forest. The authors thoroughly consider the problem of detector adjustment by multiple training and empirical selection of such parameters as the number, maximum depth of trees and the characteristic size of log abuts in the images of the training sample. The parameters of the detector are selected based on the requirement of high recognition rate. Due to this adjustment the algorithm was significantly improved so it surpasses analogs or shows comparable results with respect to accuracy.