10.21227/7FP2-JH22
Anselmo Ferreira
Anselmo
Ferreira
https://orcid.org/0000-0002-2196-7232
Shenzhen University
Siovani Filipussi
Siovani
Filipussi
Federal University of Sao Carlos
Ramon Pires
Ramon
Pires
State University of Campinas
Geise Santos
Geise
Santos
State University of Campinas
Sandra Avila
Sandra
Avila
State University of Campinas
Jorge Lambert
Jorge
Lambert
Brazilian Federal Police
Jiwu Huang
Jiwu
Huang
Shenzhen University
Anderson Rocha
Anderson
Rocha
State University of Campinas
Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset
IEEE DataPort
2019
Remote Sensing
Computational Intelligence
Sensitive Remote Sensing Analysis; Deep Learning; Convolutional Neural Networks; Detection of drug crops
2019-06-03
Dataset
Creative Commons Attribution
Automatic classification of sensitive content in remote sensing images, such as drug crop sites, is a promising task as it can aid law-enforcement institutions fighting illegal drug dealers worldwide, while, at the same time, it can help monitoring legalized crops in countries that regulate them. However, existing art on detecting drug crops from remotesensing images is limited in some key factors not taking full advantage of the available hyperspectral info for analysis. In this paper, departing from these methods, we propose a data-driven ensemble method to detect drug sites from remote sensing images. Our method comprises different Convolutional Neural Network architectures applied to distinct image representations, which are able to represent complementary characterizations of such crops. To validate the proposed approach, we considered in ourexperiments a dataset containing Cannabis Sativa crops, spottedby police operations in a Brazilian region called the Marijuana Polygon. Results in this dataset show that our ensemble approach outperforms other data-driven and feature-engineering methods in a real-world experimental setup, in which unbalanced samples are present and acquisitions from different places are used fortraining and testing the methods, highlighting the promising useof this solution to aid police operations in detecting and collectingevidence of such sensitive content properly.