{"title":"TREE SPECIES RECOGNITION AT STANDS SCALE: VALIDITY TEST OF MULTI-TEXTURE EXTRACTED FROM MULTISEASONAL UAV-BASED IMAGERY","authors":"H. Liu","doi":"10.15666/aeer/2102_15151532","DOIUrl":null,"url":null,"abstract":". In order to evaluate the effectiveness of multi-type texture features of images of four seasons in pure stand tree species recognition, this research applied 5-band RedEdge-MX sensor to collect remote sensing data of four seasons and extracted eight texture features, including mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment and correlation, from 20 spectral bands. Maximum likelihood classification and random forest were adopted for the determination of the best window for texture extraction which resulted in the construction of optimal texture feature set in tree species recognition. Then, the performance of these texture feature sets along with their combinations in tree species recognition was analyzed. Experimental findings showed that the eight texture features of four seasonal data performed well in the recognition of pure stand tree species. Texture feature mean presented the highest performance (with overall accuracy of 88.8559%) and worst variance (84.8180%). The combination of eight texture features further improved the recognition accuracy of tree species (92.0599%) compared with single texture features. The recognition accuracy of tree species could be further improved by combining eight texture features with spectral band and digital surface model (92.7002%). Research showed that the application of multi-type texture features in typical seasons of spring, summer, autumn and winter fully captured the differences of various tree species in different bands and seasons, which could be applied to the effectively identify pure stand tree species","PeriodicalId":7975,"journal":{"name":"Applied Ecology and Environmental Research","volume":"1 1","pages":""},"PeriodicalIF":0.6000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Ecology and Environmental Research","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.15666/aeer/2102_15151532","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
. In order to evaluate the effectiveness of multi-type texture features of images of four seasons in pure stand tree species recognition, this research applied 5-band RedEdge-MX sensor to collect remote sensing data of four seasons and extracted eight texture features, including mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment and correlation, from 20 spectral bands. Maximum likelihood classification and random forest were adopted for the determination of the best window for texture extraction which resulted in the construction of optimal texture feature set in tree species recognition. Then, the performance of these texture feature sets along with their combinations in tree species recognition was analyzed. Experimental findings showed that the eight texture features of four seasonal data performed well in the recognition of pure stand tree species. Texture feature mean presented the highest performance (with overall accuracy of 88.8559%) and worst variance (84.8180%). The combination of eight texture features further improved the recognition accuracy of tree species (92.0599%) compared with single texture features. The recognition accuracy of tree species could be further improved by combining eight texture features with spectral band and digital surface model (92.7002%). Research showed that the application of multi-type texture features in typical seasons of spring, summer, autumn and winter fully captured the differences of various tree species in different bands and seasons, which could be applied to the effectively identify pure stand tree species
期刊介绍:
The Journal publishes original research papers and review articles. Researchers from all countries are invited to publish pure or applied ecological, environmental, biogeographical, zoological, botanical, paleontological, biometrical-biomathematical and quantitative ecological or multidisciplinary agricultural research of international interest on its pages.
The focus is on topics such as:
-Community, ecosystem and global ecology-
Biometrics, theoretical- and quantitative ecology-
Multidisciplinary agricultural and environmental research-
Sustainable and organic agriculture, natural resource management-
Ecological methodology, monitoring and modeling-
Biodiversity and ecosystem research, microbiology, botany and zoology-
Biostatistics and modeling in epidemiology, public health and veterinary-
Earth history, paleontology, extinctions, biogeography, biogeochemistry-
Conservation biology, environmental protection-
Ecological economics, natural capital and ecosystem services-
Climatology, meteorology, climate change, climate-ecology.
The Journal publishes theoretical papers as well as application-oriented contributions and practical case studies. There is no bias with regard to taxon or geographical area. Purely descriptive papers (like only taxonomic lists) will not be accepted for publication.