scholarly journals Extracting Agricultural Fields from Remote Sensing Imagery Using Graph-Based Growing Contours

2020 ◽  
Vol 12 (7) ◽  
pp. 1205 ◽  
Author(s):  
Matthias P. Wagner ◽  
Natascha Oppelt
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
Reference Data ◽  
Active Contours ◽  
Extraction Process ◽  
Agricultural Landscapes ◽  
Human Interaction ◽  
Field Size ◽  
Agricultural Fields ◽  
Remote Sensing Imagery

Knowledge of the location and extent of agricultural fields is required for many applications, including agricultural statistics, environmental monitoring, and administrative policies. Furthermore, many mapping applications, such as object-based classification, crop type distinction, or large-scale yield prediction benefit significantly from the accurate delineation of fields. Still, most existing field maps and observation systems rely on historic administrative maps or labor-intensive field campaigns. These are often expensive to maintain and quickly become outdated, especially in regions of frequently changing agricultural patterns. However, exploiting openly available remote sensing imagery (e.g., from the European Union’s Copernicus programme) may allow for frequent and efficient field mapping with minimal human interaction. We present a new approach to extracting agricultural fields at the sub-pixel level. It consists of boundary detection and a field polygon extraction step based on a newly developed, modified version of the growing snakes active contours model we refer to as graph-based growing contours. This technique is capable of extracting complex networks of boundaries present in agricultural landscapes, and is largely automatic with little supervision required. The whole detection and extraction process is designed to work independently of sensor type, resolution, or wavelength. As a test case, we applied the method to two regions of interest in a study area in the northern Germany using multi-temporal Sentinel-2 imagery. Extracted fields were compared visually and quantitatively to ground reference data. The technique proved reliable in producing polygons closely matching reference data, both in terms of boundary location and statistical proxies such as median field size and total acreage.

scholarly journals Динаміка розмірів сільськогосподарських полів як функція їх розмірів та форми

2007 ◽  
Vol 7 (3) ◽  
pp. 14-31
Author(s):  
O.V. Zhukov ◽  
V.O. Sirovatko ◽  
N.O. Ponomarenko
Keyword(s):  
Regression Analysis ◽  
Large Scale ◽  
Remote Sensing Data ◽  
Field Size ◽  
Agricultural Fields ◽  
Distribution Law ◽  
Administrative Area ◽  
Log Normal ◽  
Shape Characteristics ◽  
Shape And Size

<p>We estimated the size and shape characteristics of agricultural fields within the administrative area and identified patterns of the margin trends from 1950-1960 till the present time. Here we considered large-scale soil maps for the area of Vasilkovsky district of the Dnepropetrovsk region, which were drawn up in 1950-1960. To assess the landscape metric we used FRAGSTATS program which allow to make conformity assessment of the observed distributions of field sizes regards the normal, exponential, log-normal, gamma, Weibull, and Pareto distributions. We also used Box-Cox transformation to convert the experimental data into the normal distribution law for the further application of the transformed data in regression analysis. We estimated that the area of agricultural fields ranged from 1.20 to 269.00 hectares during the period of large-scale mapping in 1950-1960. The variation limits of the field sizes based on the results of remote sensing data and in our time they are 2,.5-266.57 hectares. Area of the fields in different periods strongly correlate and are statistically significant (<em>r</em> = 0.98, <em>p</em> = 0.00). Field sizes currently associated with the field sizes in the 50-60 years of linear regression. Shape parameters and field sizes significantly correlated, therefore, to establish the main trends of varying shape and size of fields, as well as for non-multicollinearity variables for regression analysis, we performed a multivariate factor analysis. An important aspect of the structuring of the agri-landscape is the location of settlements and, therefore, the fields distance from them. In results obtained indicate that the processes increase and decrease the size of fields in agricultural production are determined by various factors. Aspects of the shape and size of the fields associated with the dynamics of the processes that lead to variations in field areas. Fields that have shown a tendency to change their size, have different characteristics of forms and size from the stable fields. Typically, variable field size is smaller and more complex shapes.</p>

scholarly journals Improved Winter Wheat Spatial Distribution Extraction Using A Convolutional Neural Network and Partly Connected Conditional Random Field

2020 ◽  
Vol 12 (5) ◽  
pp. 821 ◽  
Author(s):  
Shouyi Wang ◽  
Zhigang Xu ◽  
Chengming Zhang ◽  
Jinghan Zhang ◽  
Zhongshan Mu ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Spatial Distribution ◽  
Winter Wheat ◽  
Random Field ◽  
Large Scale ◽  
Conditional Random Field ◽  
Pixel Classification ◽  
Classification Result ◽  
Edge Pixel ◽  
Remote Sensing Imagery

Improving the accuracy of edge pixel classification is crucial for extracting the winter wheat spatial distribution from remote sensing imagery using convolutional neural networks (CNNs). In this study, we proposed an approach using a partly connected conditional random field model (PCCRF) to refine the classification results of RefineNet, named RefineNet-PCCRF. First, we used an improved RefineNet model to initially segment remote sensing images, followed by obtaining the category probability vectors for each pixel and initial pixel-by-pixel classification result. Second, using manual labels as references, we performed a statistical analysis on the results to select pixels that required optimization. Third, based on prior knowledge, we redefined the pairwise potential energy, used a linear model to connect different levels of potential energies, and used only pixel pairs associated with the selected pixels to build the PCCRF. The trained PCCRF was then used to refine the initial pixel-by-pixel classification result. We used 37 Gaofen-2 images obtained from 2018 to 2019 of a representative Chinese winter wheat region (Tai’an City, China) to create the dataset, employed SegNet and RefineNet as the standard CNNs, and a fully connected conditional random field as the refinement methods to conduct comparison experiments. The RefineNet-PCCRF’s accuracy (94.51%), precision (92.39%), recall (90.98%), and F1-Score (91.68%) were clearly superior than the methods used for comparison. The results also show that the RefineNet-PCCRF improved the accuracy of large-scale winter wheat extraction results using remote sensing imagery.

scholarly journals Geospatial Object Detection on High Resolution Remote Sensing Imagery Based on Double Multi-Scale Feature Pyramid Network

2019 ◽  
Vol 11 (7) ◽  
pp. 755 ◽  
Author(s):  
Xiaodong Zhang ◽  
Kun Zhu ◽  
Guanzhou Chen ◽  
Xiaoliang Tan ◽  
Lifei Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Large Scale ◽  
Training Data ◽  
Validation Dataset ◽  
Remote Sensing Imagery ◽  
Scale Feature ◽  
Multi Scale ◽  
Feature Pyramid

Object detection on very-high-resolution (VHR) remote sensing imagery has attracted a lot of attention in the field of image automatic interpretation. Region-based convolutional neural networks (CNNs) have been vastly promoted in this domain, which first generate candidate regions and then accurately classify and locate the objects existing in these regions. However, the overlarge images, the complex image backgrounds and the uneven size and quantity distribution of training samples make the detection tasks more challenging, especially for small and dense objects. To solve these problems, an effective region-based VHR remote sensing imagery object detection framework named Double Multi-scale Feature Pyramid Network (DM-FPN) was proposed in this paper, which utilizes inherent multi-scale pyramidal features and combines the strong-semantic, low-resolution features and the weak-semantic, high-resolution features simultaneously. DM-FPN consists of a multi-scale region proposal network and a multi-scale object detection network, these two modules share convolutional layers and can be trained end-to-end. We proposed several multi-scale training strategies to increase the diversity of training data and overcome the size restrictions of the input images. We also proposed multi-scale inference and adaptive categorical non-maximum suppression (ACNMS) strategies to promote detection performance, especially for small and dense objects. Extensive experiments and comprehensive evaluations on large-scale DOTA dataset demonstrate the effectiveness of the proposed framework, which achieves mean average precision (mAP) value of 0.7927 on validation dataset and the best mAP value of 0.793 on testing dataset.

Sign in / Sign up

Export Citation Format

Share Document