The Acacia longifolia species is known for its rapid growth and dissemination,causing loss of biodiversity in the affected areas.In order to avoid the uncontrolled spread of this species,it is important to effectively...The Acacia longifolia species is known for its rapid growth and dissemination,causing loss of biodiversity in the affected areas.In order to avoid the uncontrolled spread of this species,it is important to effectively monitor its distribution on the agroforestry regions.For this purpose,this paper proposes the use of Convolutional Neural Networks(CNN)for the detection of Acacia longifolia,from images acquired by an unmanned aerial vehicle.Two models based on the same CNN architecture were elaborated.One classifies image patches into one of nine possible classes,which are later converted into a binary model;this model presented an accuracy of 98:6%and 98:5%in the validation and training sets,respectively.The second model was trained directly for binary classification and showed an accuracy of 98:8%and 98:7%for the validation and test sets,respectively.The results show that the use of multiple classes,useful to provide the aerial vehicle with richer semantic information regarding the environment,does not hamper the accuracy of Acacia longifolia detection in the classifier’s primary task.The presented system also includes a method for increasing classification’s accuracy by consulting an expert to review the model’s predictions on an automatically selected sub-set of the samples.展开更多
文摘The Acacia longifolia species is known for its rapid growth and dissemination,causing loss of biodiversity in the affected areas.In order to avoid the uncontrolled spread of this species,it is important to effectively monitor its distribution on the agroforestry regions.For this purpose,this paper proposes the use of Convolutional Neural Networks(CNN)for the detection of Acacia longifolia,from images acquired by an unmanned aerial vehicle.Two models based on the same CNN architecture were elaborated.One classifies image patches into one of nine possible classes,which are later converted into a binary model;this model presented an accuracy of 98:6%and 98:5%in the validation and training sets,respectively.The second model was trained directly for binary classification and showed an accuracy of 98:8%and 98:7%for the validation and test sets,respectively.The results show that the use of multiple classes,useful to provide the aerial vehicle with richer semantic information regarding the environment,does not hamper the accuracy of Acacia longifolia detection in the classifier’s primary task.The presented system also includes a method for increasing classification’s accuracy by consulting an expert to review the model’s predictions on an automatically selected sub-set of the samples.