Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset

Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset

Citation Author(s):
Anselmo
Ferreira
Shenzhen University
Siovani
Filipussi
Federal University of Sao Carlos
Ramon
Pires
State University of Campinas
Geise
Santos
State University of Campinas
Sandra
Avila
State University of Campinas
Jorge
Lambert
Brazilian Federal Police
Jiwu
Huang
Shenzhen University
Anderson
Rocha
State University of Campinas
Submitted by:
Anselmo Ferreira
Last updated:
Tue, 06/04/2019 - 10:58
DOI:
10.21227/H2WD42
Data Format:
License:
Dataset Views:
238
Share / Embed Cite
Abstract: 

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 remote sensing 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 our experiments a dataset containing Cannabis Sativa crops, spotted by 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 for training and testing the methods, highlighting the promising use of this solution to aid police operations in detecting and collecting evidence of such sensitive content properly.

Instructions: 

This is the dataset related to the paper: "Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset " accepted for publication at the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. The paper can be found at https://ieeexplore.ieee.org/document/8726132

The Dataset contains several sub-folders: 

  • orig_BGRN_30: Dataset of 30x30 patches containing the original Blue, Green, Red, and Near Infrared channels
  • False color: False color representation using the original NRG channels.
  • prepare_augmented: the dataset from bags 1 and 2, considering false color and near-infrared images, but with positive samples augmentation to be suitable for our smart batches (please refer to the paper and source code for more details). This last dataset is the one used in our paper's solution.

 

You can use the dataset to generate new datasets, such as the TVI image dataset, NDVI dataset and so on. We will release the source code related to the paper very soon at https://github.com/anselmoferreira/remote-sensing-sensitive-analysis

Please don't hesitate to contact the authors of the dataset if you have problems or further doubts about it:

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Login or subscribe now. Sign up to be a Beta Tester and receive a coupon code for a free subscription to IEEE DataPort!

Embed this dataset on another website

Copy and paste the HTML code below to embed your dataset:

Share via email or social media

Click the buttons below:

facebooktwittermailshare
[1] Anselmo Ferreira, Siovani Filipussi, Ramon Pires, Geise Santos, Sandra Avila, Jorge Lambert, Jiwu Huang, Anderson Rocha, "Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset", IEEE Dataport, 2018. [Online]. Available: http://dx.doi.org/10.21227/H2WD42. Accessed: Aug. 23, 2019.
@data{h2wd42-18,
doi = {10.21227/H2WD42},
url = {http://dx.doi.org/10.21227/H2WD42},
author = {Anselmo Ferreira; Siovani Filipussi; Ramon Pires; Geise Santos; Sandra Avila; Jorge Lambert; Jiwu Huang; Anderson Rocha },
publisher = {IEEE Dataport},
title = {Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset},
year = {2018} }
TY - DATA
T1 - Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset
AU - Anselmo Ferreira; Siovani Filipussi; Ramon Pires; Geise Santos; Sandra Avila; Jorge Lambert; Jiwu Huang; Anderson Rocha
PY - 2018
PB - IEEE Dataport
UR - 10.21227/H2WD42
ER -
Anselmo Ferreira, Siovani Filipussi, Ramon Pires, Geise Santos, Sandra Avila, Jorge Lambert, Jiwu Huang, Anderson Rocha. (2018). Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset. IEEE Dataport. http://dx.doi.org/10.21227/H2WD42
Anselmo Ferreira, Siovani Filipussi, Ramon Pires, Geise Santos, Sandra Avila, Jorge Lambert, Jiwu Huang, Anderson Rocha, 2018. Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset. Available at: http://dx.doi.org/10.21227/H2WD42.
Anselmo Ferreira, Siovani Filipussi, Ramon Pires, Geise Santos, Sandra Avila, Jorge Lambert, Jiwu Huang, Anderson Rocha. (2018). "Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset." Web.
1. Anselmo Ferreira, Siovani Filipussi, Ramon Pires, Geise Santos, Sandra Avila, Jorge Lambert, Jiwu Huang, Anderson Rocha. Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset [Internet]. IEEE Dataport; 2018. Available from : http://dx.doi.org/10.21227/H2WD42
Anselmo Ferreira, Siovani Filipussi, Ramon Pires, Geise Santos, Sandra Avila, Jorge Lambert, Jiwu Huang, Anderson Rocha. "Eyes in the Skies: A Data-driven Fusion Approach to Identifying Drug Crops from Remote Sensing Images Dataset." doi: 10.21227/H2WD42