scholarly journals Advanced Fully Convolutional Networks for Agricultural Field Boundary Detection

2021 ◽  
Vol 13 (4) ◽  
pp. 722
Author(s):  
Alireza Taravat ◽  
Matthias P. Wagner ◽  
Rogerio Bonifacio ◽  
David Petit
Keyword(s):  
Network Architecture ◽  
Spatial Information ◽  
Cropping Systems ◽  
Boundary Detection ◽  
Jaccard Coefficient ◽  
Agricultural Field ◽  
Field Boundary ◽  
Convolutional Network ◽  
Fully Convolutional Networks ◽  
Field Boundaries

Accurate spatial information of agricultural fields is important for providing actionable information to farmers, managers, and policymakers. On the other hand, the automated detection of field boundaries is a challenging task due to their small size, irregular shape and the use of mixed-cropping systems making field boundaries vaguely defined. In this paper, we propose a strategy for field boundary detection based on the fully convolutional network architecture called ResU-Net. The benefits of this model are two-fold: first, residual units ease training of deep networks. Second, rich skip connections within the network could facilitate information propagation, allowing us to design networks with fewer parameters but better performance in comparison with the traditional U-Net model. An extensive experimental analysis is performed over the whole of Denmark using Sentinel-2 images and comparing several U-Net and ResU-Net field boundary detection algorithms. The presented results show that the ResU-Net model has a better performance with an average F1 score of 0.90 and average Jaccard coefficient of 0.80 in comparison to the U-Net model with an average F1 score of 0.88 and an average Jaccard coefficient of 0.77.

scholarly journals A DEEP LEARNING ARCHITECTURE FOR BATCH-MODE FULLY AUTOMATED FIELD BOUNDARY DETECTION

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 1009-1016
Author(s):  
L. Meyer ◽  
F. Lemarchand ◽  
P. Sidiropoulos
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Boundary Detection ◽  
Detection Problem ◽  
Field Boundary ◽  
Batch Mode ◽  
Deep Learning Algorithm ◽  
Positive Results ◽  
Sentinel 2

Abstract. The accurate split of large areas of land into discrete fields is a crucial step for several agriculture-related remote sensing pipelines. This work aims to fully automate this tedious and resource-demanding process using a state-of-the-art deep learning algorithm with only a single Sentinel-2 image as input. The Mask R-CNN, which has forged its success upon instance segmentation for objects from everyday life, is adapted for the field boundary detection problem. Such model automatically generates closed geometries without any heavy post-processing. When tested with satellite imagery from Denmark, this tailored model correctly predicts field boundaries with an overall accuracy of 0.79. Besides, it demonstrates a robust knowledge generalisation with positive results over different geographies, as it gets an overall accuracy of 0.71 when used over areas in France.

scholarly journals Deep Learning and Adaptive Graph-Based Growing Contours for Agricultural Field Extraction

2020 ◽  
Vol 12 (12) ◽  
pp. 1990
Author(s):  
Matthias P. Wagner ◽  
Natascha Oppelt
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Agricultural Research ◽  
Hessian Matrix ◽  
Boundary Detection ◽  
Image Features ◽  
Agricultural Landscapes ◽  
Agricultural Field ◽  
Field Boundary ◽  
Crop Type

Field mapping and information on agricultural landscapes is of increasing importance for many applications. Monitoring schemes and national cadasters provide a rich source of information but their maintenance and regular updating is costly and labor-intensive. Automatized mapping of fields based on remote sensing imagery may aid in this task and allow for a faster and more regular observation. Although remote sensing has seen extensive use in agricultural research topics, such as plant health monitoring, crop type classification, yield prediction, and irrigation, field delineation and extraction has seen comparatively little research interest. In this study, we present a field boundary detection technique based on deep learning and a variety of image features, and combine it with the graph-based growing contours (GGC) method to extract agricultural fields in a study area in northern Germany. The boundary detection step only requires red, green, and blue (RGB) data and is therefore largely independent of the sensor used. We compare different image features based on color and luminosity information and evaluate their usefulness for the task of field boundary detection. A model based on texture metrics, gradient information, Hessian matrix eigenvalues, and local statistics showed good results with accuracies up to 88.2%, an area under the ROC curve (AUC) of up to 0.94, and F1 score of up to 0.88. The exclusive use of these universal image features may also facilitate transferability to other regions. We further present modifications to the GGC method intended to aid in upscaling of the method through process acceleration with a minimal effect on results. We combined the boundary detection results with the GGC method for field polygon extraction. Results were promising, with the new GGC version performing similarly or better than the original version while experiencing an acceleration of 1.3× to 2.3× on different subsets and input complexities. Further research may explore other applications of the GGC method outside agricultural remote sensing and field extraction.

The Relationship Between Leader–Member Exchange and Employees’ Proactive Behaviors

2019 ◽  
Vol 18 (2) ◽  
pp. 106-111
Author(s):  
Fong-Yi Lai ◽  
Szu-Chi Lu ◽  
Cheng-Chen Lin ◽  
Yu-Chin Lee
Keyword(s):  
Hierarchical Linear Modeling ◽  
Future Research ◽  
Leader Member Exchange ◽  
Voice Behavior ◽  
Linear Modeling ◽  
Team Members ◽  
Member Exchange ◽  
Multi Temporal ◽  
The Relationship ◽  
Practical Implications

Abstract. The present study proposed that, unlike prior leader–member exchange (LMX) research which often implicitly assumed that each leader develops equal-quality relationships with their supervisors (leader’s LMX; LLX), every leader develops different relationships with their supervisors and, in turn, receive different amounts of resources. Moreover, these differentiated relationships with superiors will influence how leader–member relationship quality affects team members’ voice and creativity. We adopted a multi-temporal (three wave) and multi-source (leaders and employees) research design. Hypotheses were tested on a sample of 227 bank employees working in 52 departments. Results of the hierarchical linear modeling (HLM) analysis showed that LLX moderates the relationship between LMX and team members’ voice behavior and creative performance. Strengths, limitations, practical implications, and directions for future research are discussed.

A Summary Report on Second World War Activity at Watery Lane, Church Crookham, Hampshire

2019 ◽  
Vol 74 (1) ◽  
pp. 170-176
Author(s):  
Matt Nichol
Keyword(s):  
Second World War ◽  
Late Prehistoric ◽  
Timber Structures ◽  
Summary Report ◽  
World War ◽  
Archaeological Excavation ◽  
Field Boundary ◽  
Development Area ◽  
Five Phases ◽  
Second World

An archaeological excavation of four areas approximately 0.39ha in total, of land at Watery Lane, Church Crookham, Hampshire, was undertaken by Cotswold Archaeology in November and December 2016. It followed the recording of two Pill Boxes and a trial trench evaluation of a wider development area. In all four areas archaeological features were identified. The artefactual evidence indicated five phases of archaeological activity, with features dating from the late prehistoric, medieval, medieval/post-medieval, and post-medieval to modern wartime period. Several heavily truncated isolated prehistoric features were identified, as were field boundary ditches of medieval to the post-medieval date. Many undated, but presumed modern, postholes were found across the site. The postholes may have been the result of an extensive network of Second World War temporary timber structures known as tactical obstacles (including barbed wire entanglements and tank proof obstacles) erected during anti-invasion defence works. These structures were likely to have been part of the important Stop Line Defence network, Line A of the GHQ (General Headquarters) line of defences, which were planned to slow down a ground invasion.

Iron Age and Roman Enclosed Settlement at Winchester Road, Basingstoke

2019 ◽  
Vol 74 (1) ◽  
pp. 36-97
Author(s):  
Richard Massey ◽  
Matt Nichol ◽  
Dana Challinor ◽  
Sharon Clough ◽  
Matilda Holmes ◽  
...  
Keyword(s):  
Iron Age ◽  
Roman Period ◽  
Field Boundary ◽  
Crop Processing ◽  
Late Iron Age ◽  
Middle Iron Age ◽  
Grave Goods

Excavation in Area 1 identified an enclosed settlement of Middle–Late Iron Age and Early Roman date, which included a roundhouse gully and deep storage pits with complex fills. A group of undated four-post structures, situated in the east of Area 1, appeared to represent a specialised area of storage or crop processing of probable Middle Iron Age date. A sequence of re-cutting and reorganisation of ditches and boundaries in the Late Iron Age/Early Roman period was followed, possibly after a considerable hiatus, by a phase of later Roman activity, Late Iron Age reorganisation appeared to be associated with the abandonment of a roundhouse, and a number of structured pit deposits may also relate to this period of change. Seven Late Iron Age cremation burials were associated with a contemporary boundary ditch which crossed Area 1. Two partly-exposed, L-shaped ditches may represent a later Roman phase of enclosed settlement and a slight shift in settlement focus. An isolated inhumation burial within the northern margins of Area 1 was tentatively dated by grave goods to the Early Saxon period.<br/> Area 2 contained a possible trackway and field boundary ditches, of which one was of confirmed Late Iron Age/Early Roman date. A short posthole alignment in Area 2 was undated, and may be an earlier prehistoric feature.

Upper Palaeolithic, Mesolithic and Later Finds from Oxlease Farm, Romsey, Hampshire: Summary Report

2018 ◽  
Vol 73 (1) ◽  
pp. 1-10
Author(s):  
Chris Ellis ◽  
Jacky Sommerville
Keyword(s):  
Upper Palaeolithic ◽  
Summary Report ◽  
Archaeological Excavation ◽  
Field Boundary ◽  
Lithic Assemblage ◽  
Late Roman

In March 2016, archaeological excavation was undertaken at four areas of land at Oxlease Farm, Cupernham Lane, Romsey, Hampshire. The fieldwork recovered a lithic assemblage from all four excavation areas, although the majority was recorded from a single flint-bearing deposit in Area 1. The assemblage included several elements that may belong to the Terminal Upper Palaeolithic Long Blade industry, as well as three flints of Mesolithic date. A small number of undated features were also uncovered, including pits and possible postholes, which may have been of a prehistoric date. A small and residual assemblage of Late Roman (3rd – 4th century AD) pottery was also recovered from probable medieval/post-medieval field boundary ditches or plough furrows.

Sign in / Sign up

Export Citation Format

Share Document