Survey and monitoring of opium poppy and wheat in Afghanistan: 2003–2009

Taylor, John; Waine, Toby; Juniper, Graham R.; Simms, Daniel M.; Brewer, Tim

doi:10.1080/01431161003713028

Cited by 21 publications

(12 citation statements)

References 1 publication

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These classifications were then manually edited as some clusters contained pixels of both agriculture and natural vegetation. Editing was done by trained interpreters with access to ancillary information from high resolution commercial IKONOS imagery (Taylor et al 2010). Finally the masks were quality checked and compared with data from other years to ensure consistency of interpretation.…”

Section: Image Data and Agricultural Masksmentioning

confidence: 99%

Replacing human interpretation of agricultural land in Afghanistan with a deep convolutional neural network

Hamer

Simms

Waine

2021

International Journal of Remote Sensing

View full text Add to dashboard Cite

Afghanistans annual opium survey relies upon time-consuming human interpretation of satellite images to map the area of potential poppy cultivation for statistical sample design. Deep Convolutional Neural Networks (CNNs) have shown groundbreaking performance for image classification tasks by encoding local contextual information, in some cases outperforming trained analysts. In this study, we investigate the development of a CNN to automate the classification of agriculture from medium resolution satellite imagery as an alternative to manual interpretation. The residual network (ResNet50) CNN architecture was trained and validated for delineating the agricultural area using labelled multi-seasonal Disaster Monitoring Constellation (DMC) satellite imagery (32 m) of Helmand and Kandahar provinces. The effect of input image chip size, training sampling strategy, elevation data and multi-seasonal imagery were investigated. The best performing single year classification used an input chip size of 33 × 33 pixels, a targeted sampling strategy and transfer learning, resulting in high overall accuracy (94%). The inclusion of elevation data marginally lowered performance (93%). Multi-seasonal classification achieved an overall accuracy of 89% using the previous two years' data. Only 25% of the target year's training samples were necessary to update the model to achieve > 94% overall accuracy. A data-driven approach to automate agricultural mask production using CNNs is proposed to reduce the burden of human interpretation. The ability to continually update CNN models with new data has the potential to significantly improve automatic classification of vegetation across years.

show abstract

Section: Image Data and Agricultural Masksmentioning

confidence: 99%

Replacing human interpretation of agricultural land in Afghanistan with a deep convolutional neural network

Hamer

Simms

Waine

2021

International Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The large number of VHR Ikonos scenes were part of a statistically representative sample of crop variability. The accuracy of the dense labelling has been extensively quality checked and scrutinized, as these data were used to directly inform counter narcotics policy in Afghanistan (Taylor et al 2010). FCNs were trained end-to-end for field parcel detection using 1 km 2 image regions, sub-sampled patches, and transfer learning across three years of data.…”

Section: Introductionmentioning

confidence: 99%

Fully convolutional neural nets in-the-wild

Simms

2020

Remote Sensing Letters

View full text Add to dashboard Cite

The ground breaking performance of fully convolutional neural nets (FCNs) for semantic segmentation tasks has yet to be achieved for landcover classification, partly because a lack of suitable training data. Here the FCN8 model is trained and evaluated in real-world conditions, so called in-the-wild, for the classification of opium poppy and cereal crops at very high resolution (1 m). Densely labelled image samples from 74 Ikonos scenes were taken from 3 years of opium cultivation surveys for Helmand Province, Afghanistan. Models were trained using 1 km 2 samples, subsampled patches and transfer learning. Overall accuracy was 88% for a FCN8 model transfer-trained on all three years of data and complex features were successfully grouped into distinct field parcels from the training data alone. FCNs can be trained end-to-end using variable sized input images for pixel-level classification that combines the spatial and spectral properties of target objects in a single operation. Transfer learning improves classifier performance and can be used to share information between FCNs, demonstrating their potential to significantly improve land cover classification more generally.

show abstract

“…Satellite remote sensing has traditionally played an important role in monitoring poppy cultivation. Taylor et al [1], along with the U.S. government, used satellite remote sensing to detect poppy plots in Afghanistan for several years. Liu et al [2] used ZY-3 satellite imagery to detect poppy plots in Phongsali Province, Laos, using the single-shot detector (SSD)-based object detection method.…”

Section: Introductionmentioning

confidence: 99%

Improved UAV Opium Poppy Detection Using an Updated YOLOv3 Model

Zhou

Tian

Yuan

et al. 2019

Sensors

View full text Add to dashboard Cite

Rapid detection of illicit opium poppy plants using UAV (unmanned aerial vehicle) imagery has become an important means to prevent and combat crimes related to drug cultivation. However, current methods rely on time-consuming visual image interpretation. Here, the You Only Look Once version 3 (YOLOv3) network structure was used to assess the influence that different backbone networks have on the average precision and detection speed of an UAV-derived dataset of poppy imagery, with MobileNetv2 (MN) selected as the most suitable backbone network. A Spatial Pyramid Pooling (SPP) unit was introduced and Generalized Intersection over Union (GIoU) was used to calculate the coordinate loss. The resulting SPP-GIoU-YOLOv3-MN model improved the average precision by 1.62% (from 94.75% to 96.37%) without decreasing speed and achieved an average precision of 96.37%, with a detection speed of 29 FPS using an RTX 2080Ti platform. The sliding window method was used for detection in complete UAV images, which took approximately 2.2 sec/image, approximately 10× faster than visual interpretation. The proposed technique significantly improved the efficiency of poppy detection in UAV images while also maintaining a high detection accuracy. The proposed method is thus suitable for the rapid detection of illicit opium poppy cultivation in residential areas and farmland where UAVs with ordinary visible light cameras can be operated at low altitudes (relative height < 200 m).

show abstract

Survey and monitoring of opium poppy and wheat in Afghanistan: 2003–2009

Cited by 21 publications

References 1 publication

Replacing human interpretation of agricultural land in Afghanistan with a deep convolutional neural network

Replacing human interpretation of agricultural land in Afghanistan with a deep convolutional neural network

Fully convolutional neural nets in-the-wild

Improved UAV Opium Poppy Detection Using an Updated YOLOv3 Model

Contact Info

Product

Resources

About