Opium Poppy Detection Using Deep Learning

Opium poppies are a major source of traditional drugs, which are not only harmful to physical and mental health, but also threaten the economy and society. Monitoring poppy cultivation in key regions through remote sensing is therefore a crucial task; the location coordinates of poppy parcels represent particularly important information for their eradication by local governments. We propose a new methodology based on deep learning target detection to identify the location of poppy parcels and map their spatial distribution. We first make six training datasets with different band combinations and slide window sizes using two ZiYuan3 (ZY3) remote sensing images and separately train the single shot multibox detector (SSD) model. Then, we choose the best model and test its performance using 225 km2 verification images from Lao People’s Democratic Republic (Lao PDR), which exhibits a precision of 95% for a recall of 85%. The speed of our method is 4.5 km2/s on 1080TI Graphics Processing Unit (GPU). This study is the first attempt to monitor opium poppies with the deep learning method and achieve a high recognition rate. Our method does not require manual feature extraction and provides an alternative way to rapidly obtain the exact location coordinates of opium poppy cultivation patches.

[1]  Yongqiang Zhao,et al.  Hyperspectral Image Denoising via Sparse Representation and Low-Rank Constraint , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[2]  K. Vani,et al.  Water flow based geometric active deformable model for road network , 2015 .

[3]  Abdelmalek Toumi,et al.  Radar Target Recognition Using Salient Keypoint Descriptors and Multitask Sparse Representation , 2018, Remote. Sens..

[4]  Gui-Song Xia,et al.  Deep Learning for Remote Sensing Image Understanding , 2016, J. Sensors.

[5]  Larry S. Davis,et al.  Vehicle Detection Using Partial Least Squares , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yun Zhang,et al.  Unsupervised multiple endmember spectral mixture analysis-based detection of opium poppy fields from an EO-1 Hyperion image in Helmand, Afghanistan. , 2014, The Science of the total environment.

[7]  Xin Du,et al.  Spectral Discrimination of Opium Poppy Using Field Spectrometry , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Hong Zhang,et al.  Combing Single Shot Multibox Detector with transfer learning for ship detection using Chinese Gaofen-3 images , 2017, 2017 Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL).

[9]  Yi Su,et al.  Fast and Accurate Target Detection Based on Multiscale Saliency and Active Contour Model for High-Resolution SAR Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Gabriele Costante,et al.  Towards Monocular Digital Elevation Model (DEM) Estimation by Convolutional Neural Networks - Application on Synthetic Aperture Radar Images , 2018, ArXiv.

[11]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Haibin Duan,et al.  Artificial bee colony (ABC) optimized edge potential function (EPF) approach to target recognition for low-altitude aircraft , 2010, Pattern Recognit. Lett..

[14]  Jiahua Zhang,et al.  An unsupervised mixture-tuned matched filtering-based method for the remote sensing of opium poppy fields using EO-1 Hyperion data: an example from Helmand, Afghanistan , 2016 .

[15]  Hong Huo,et al.  Harbor Detection in Large-Scale Remote Sensing Images Using Both Deep-Learned and Topological Structure Features , 2017, 2017 10th International Symposium on Computational Intelligence and Design (ISCID).

[16]  Tapas Ranjan Martha,et al.  Segment Optimization and Data-Driven Thresholding for Knowledge-Based Landslide Detection by Object-Based Image Analysis , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[18]  Timothy A. Warner,et al.  Does spatial resolution matter? A multi-scale comparison of object-based and pixel-based methods for detecting change associated with gas well drilling operations , 2013 .

[19]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[20]  T. Waine,et al.  Improved estimates of opium cultivation in Afghanistan using imagery-based stratification , 2017 .

[21]  Junwei Han,et al.  A Survey on Object Detection in Optical Remote Sensing Images , 2016, ArXiv.

[22]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[23]  Gui-Song Xia,et al.  Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery , 2015, Remote. Sens..

[24]  Thomas Blaschke,et al.  Monitoring recovery after earthquakes through the integration of remote sensing, GIS, and ground observations: the case of L’Aquila (Italy) , 2016 .

[25]  F. Blasco,et al.  A poppy survey using high resolution remote sensing data , 1997 .

[26]  Jun Zhou,et al.  Road tracking in aerial images based on human–computer interaction and Bayesian filtering , 2006 .

[27]  Curt H. Davis,et al.  Rapid broad area search and detection of Chinese surface-to-air missile sites using deep convolutional neural networks , 2017 .

[28]  R. Bucala,et al.  Identification of the Major Site of Apolipoprotein B Modification by Advanced Glycosylation End Products Blocking Uptake by the Low Density Lipoprotein Receptor (*) , 1995, The Journal of Biological Chemistry.

[29]  Xinwei Zheng,et al.  A multi-model ensemble method based on convolutional neural networks for aircraft detection in large remote sensing images , 2018 .

[30]  Ugur Halici,et al.  Texture-Based Airport Runway Detection , 2013, IEEE Geoscience and Remote Sensing Letters.

[31]  Bingfang Wu,et al.  Opium poppy monitoring with remote sensing in North Myanmar. , 2011, The International journal on drug policy.

[32]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[33]  Pawan Kumar Joshi,et al.  SPOT vegetation multi temporal data for classifying vegetation in south central Asia , 2003 .

[34]  J. C. Taylor,et al.  Image segmentation for improved consistency in image-interpretation of opium poppy , 2016 .

[35]  Peng Gong,et al.  Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imagery , 2004 .

[36]  Zhiming Feng,et al.  Rubber plantation and its relationship with topographical factors in the border region of China, Laos and Myanmar , 2013, Journal of Geographical Sciences.

[37]  Liming Zhang,et al.  Airport Target Detection in Remote Sensing Images: A New Method Based on Two-Way Saliency , 2015, IEEE Geoscience and Remote Sensing Letters.

[38]  Bo Huang,et al.  Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery , 2018, Remote Sensing of Environment.

[39]  Allison L. Bennington.  Application of multi-spectral remote sensing for crop discrimination in Afghanistan , 2008 .

[40]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[42]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).