Development of a Parcel-Level Land Boundary Extraction Algorithm for Aerial Imagery of Regularly Arranged Agricultural Areas

Hong, Rokgi; Park, Jinseok; Jang, Seongju; Shin, Hyung-Jin; Kim, Hakkwan; Song, Inhong

doi:10.3390/rs13061167

Cited by 30 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The steps described here share some similarities with the workflow presented in Ref. [52], but there are two key differences: no assumption that land parcel boundaries are straight lines and no use of the Hough transform during the process.…”

Section: Boundary Detectionmentioning

confidence: 99%

The SmartLandMaps Approach for Participatory Land Rights Mapping

Lindner,

Degbelo,

Vassányi

et al. 2023

Land

View full text Add to dashboard Cite

Millions of formal and informal land rights are still undocumented worldwide and there is a need for scalable techniques to facilitate that documentation. In this context, sketch mapping based on printed high-resolution satellite or aerial imagery is being promoted as a fit-for-purpose land administration method and can be seen as a promising way to collect cadastral and land use information with the community in a rapid and cost-effective manner. The main disadvantage of paper-based mapping is the need for digitization to facilitate the integration with existing land administration information systems and the sustainable use of the data. Currently, this digitization is mostly done manually, which is time-consuming and error-prone. This article presents the SmartLandMaps approach to land rights mapping and digitization to address this gap. The recording involves the use of sketches during participatory mapping activities to delineate parcel boundaries, and the use of mobile phones to collect attribute information about spatial units and land rights holders. The digitization involves the use of photogrammetric techniques to derive a digital representation from the annotated paper maps, and the use of computer vision techniques to automate the extraction of parcel boundaries and stickers from raster maps. The approach was deployed in four scenarios across Africa, revealing its simplicity, versatility, efficiency, and cost-effectiveness. It can be regarded as a scalable alternative to traditional paper-based participatory land rights mapping.

show abstract

Section: Boundary Detectionmentioning

confidence: 99%

The SmartLandMaps Approach for Participatory Land Rights Mapping

Lindner,

Degbelo,

Vassányi

et al. 2023

Land

View full text Add to dashboard Cite

show abstract

“…The Hough transform extracts straight lines or curves from images and can be used for digitising cadastral maps [46], or for the extraction of land boundaries [47]. The feature extraction technique was implemented in Matlab.…”

Section: Vectorisation Of Predicted Boundary Maps-hough Transformmentioning

confidence: 99%

Revising Cadastral Data on Land Boundaries Using Deep Learning in Image-Based Mapping

Fetai

Grigillo

Lisec

2022

IJGI

View full text Add to dashboard Cite

One of the main concerns of land administration in developed countries is to keep the cadastral system up to date. The goal of this research was to develop an approach to detect visible land boundaries and revise existing cadastral data using deep learning. The convolutional neural network (CNN), based on a modified architecture, was trained using the Berkeley segmentation data set 500 (BSDS500) available online. This dataset is known for edge and boundary detection. The model was tested in two rural areas in Slovenia. The results were evaluated using recall, precision, and the F1 score—as a more appropriate method for unbalanced classes. In terms of detection quality, balanced recall and precision resulted in F1 scores of 0.60 and 0.54 for Ponova vas and Odranci, respectively. With lower recall (completeness), the model was able to predict the boundaries with a precision (correctness) of 0.71 and 0.61. When the cadastral data were revised, the low values were interpreted to mean that the lower the recall, the greater the need to update the existing cadastral data. In the case of Ponova vas, the recall value was less than 0.1, which means that the boundaries did not overlap. In Odranci, 21% of the predicted and cadastral boundaries overlapped. Since the direction of the lines was not a problem, the low recall value (0.21) was mainly due to overly fragmented plots. Overall, the automatic methods are faster (once the model is trained) but less accurate than the manual methods. For a rapid revision of existing cadastral boundaries, an automatic approach is certainly desirable for many national mapping and cadastral agencies, especially in developed countries.

show abstract

“…Segmentation is related to the final quality of the ultimate thematic map, and is, therefore, a key aspect of GEOBIA. The best method is to segment the scene into objects that map features of interest in the real world [44,45]. Various image segmentation algorithms have been developed, some of which can be implemented in the form of tools or software, for instance, the multiscale segmentation algorithm provided by the eCognition platform.…”

Section: Image Segmentationmentioning

confidence: 99%

“…The dependence on parcel boundary data limits the application of the proposed methodological framework in large regions. Automatic extraction of parcel boundary information has always been a challenge in the field of agricultural RS [45,71]. Although there are many automatic and semiautomatic object-oriented image segmentation methods [30], it remains difficult to use these methods to segment images to extract homogeneous and complete parcels [44].…”

Section: Benefits/drawbacks Of Our Approachmentioning

confidence: 99%

Improving Parcel-Level Mapping of Smallholder Crops from VHSR Imagery: An Ensemble Machine-Learning-Based Framework

Zhang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Explicit spatial information about crop types on smallholder farms is important for the development of local precision agriculture. However, due to highly fragmented and heterogeneous cropland landscapes, fine-scale mapping of smallholder crops, based on low- and medium-resolution satellite images and relying on a single machine learning (ML) classifier, generally fails to achieve satisfactory performance. This paper develops an ensemble ML-based framework to improve the accuracy of parcel-level smallholder crop mapping from very high spatial resolution (VHSR) images. A typical smallholder agricultural area in central China covered by WorldView-2 images is selected to demonstrate our approach. This approach involves the task of distinguishing eight crop-level agricultural land use types. To this end, six widely used individual ML classifiers are evaluated. We further improved their performance by independently implementing bagging and stacking ensemble learning (EL) techniques. The results show that the bagging models improved the performance of unstable classifiers, but these improvements are limited. In contrast, the stacking models perform better, and the Stacking #2 model (overall accuracy = 83.91%, kappa = 0.812), which integrates the three best-performing individual classifiers, performs the best of all of the built models and improves the classwise accuracy of almost all of the land use types. Since classification performance can be significantly improved without adding costly data collection, stacking-ensemble mapping approaches are valuable for the spatial management of complex agricultural areas. We also demonstrate that using geometric and textural features extracted from VHSR images can improve the accuracy of parcel-level smallholder crop mapping. The proposed framework shows the great potential of combining EL technology with VHSR imagery for accurate mapping of smallholder crops, which could facilitate the development of parcel-level crop identification systems in countries dominated by smallholder agriculture.

show abstract

Development of a Parcel-Level Land Boundary Extraction Algorithm for Aerial Imagery of Regularly Arranged Agricultural Areas

Cited by 30 publications

References 37 publications

The SmartLandMaps Approach for Participatory Land Rights Mapping

The SmartLandMaps Approach for Participatory Land Rights Mapping

Revising Cadastral Data on Land Boundaries Using Deep Learning in Image-Based Mapping

Improving Parcel-Level Mapping of Smallholder Crops from VHSR Imagery: An Ensemble Machine-Learning-Based Framework

Contact Info

Product

Resources

About