Drone-based land-cover mapping using a fuzzy unordered rule induction algorithm integrated into object-based image analysis

Kalantar, Bahareh; Mansor, Shattri; Sameen, Maher Ibrahim; Pradhan, Biswajeet; Shafri, Helmi Zulhaidi Mohd

doi:10.1080/01431161.2016.1277043

Cited by 64 publications

(56 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference [28] evaluated classifications after applying an advanced feature selection model to SVM and RF classifiers. A novel method was developed in [6] where the fuzzy unordered rule algorithm and OBIA were integrated to extract land cover from UAV images. Their method first segments the images based on multi-resolution segmentation, then optimises them based on feature selection (integrating feature space optimisation into the plateau objective function) and finally classifies them using a decision tree and an SVM.…”

Section: Related Studiesmentioning

confidence: 99%

“…Ease-of-use and affordability are two catalysing factors for the widespread use of UAVs in civilian and military applications [1,4]. Images captured using UAVs are used for geographical information system databases, datasets for automated decision-making, agricultural mapping, urban planning, land use and land cover detection and environmental monitoring and assessment [1,[5][6][7]. Such images are commonly used in supervised machine learning-based classification tasks as training data [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

“…Such images are commonly used in supervised machine learning-based classification tasks as training data [8][9][10]. One reason for this is that these images have high resolution and a good range of spectral bands [6]. This is an advantage since training and validating a supervised classifier for a remote sensing task demands reliable features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Land Cover Classification from fused DSM and UAV Images Using Convolutional Neural Networks

et al. 2019

Self Cite

View full text Add to dashboard Cite

In recent years, remote sensing researchers have investigated the use of different modalities (or combinations of modalities) for classification tasks. Such modalities can be extracted via a diverse range of sensors and images. Currently, there are no (or only a few) studies that have been done to increase the land cover classification accuracy via unmanned aerial vehicle (UAV)-digital surface model (DSM) fused datasets. Therefore, this study looks at improving the accuracy of these datasets by exploiting convolutional neural networks (CNNs). In this work, we focus on the fusion of DSM and UAV images for land use/land cover mapping via classification into seven classes: bare land, buildings, dense vegetation/trees, grassland, paved roads, shadows, and water bodies. Specifically, we investigated the effectiveness of the two datasets with the aim of inspecting whether the fused DSM yields remarkable outcomes for land cover classification. The datasets were: (i) only orthomosaic image data (Red, Green and Blue channel data), and (ii) a fusion of the orthomosaic image and DSM data, where the final classification was performed using a CNN. CNN, as a classification method, is promising due to hierarchical learning structure, regulating and weight sharing with respect to training data, generalization, optimization and parameters reduction, automatic feature extraction and robust discrimination ability with high performance. The experimental results show that a CNN trained on the fused dataset obtains better results with Kappa index of~0.98, an average accuracy of 0.97 and final overall accuracy of 0.98. Comparing accuracies between the CNN with DSM result and the CNN without DSM result for the overall accuracy, average accuracy and Kappa index revealed an improvement of 1.2%, 1.8% and 1.5%, respectively. Accordingly, adding the heights of features such as buildings and trees improved the differentiation between vegetation specifically where plants were dense.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Land Cover Classification from fused DSM and UAV Images Using Convolutional Neural Networks

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…), land cover classification (Kalantar et al. ), species reintroduction (Puttock et al. ) or forest monitoring (Paneque‐Gálvez et al.…”

Section: Introductionmentioning

confidence: 99%

“…UAVs or drones) capable of collecting high-resolution imagery, several fields of research are using this technology to gather relevant information. Drones have been implemented for many different purposes, such as wildlife detection (Koh and Wich 2012), vegetation mapping (Cruzan et al 2016;Cunliffe et al 2016), land cover classification (Kalantar et al 2017), species reintroduction (Puttock et al 2015) or forest monitoring (Paneque-G alvez et al 2014). These studies show that with little economic investment and easy operability, consumer-level drones can provide high-quality data and time series for effective monitoring and management of medium-sized areas.…”

Section: Introductionmentioning

confidence: 99%

Drones as a tool to monitor human impacts and vegetation changes in parks and protected areas

Ancin‐Murguzur

Muñoz

Monz

et al. 2019

Remote Sens Ecol Conserv

View full text Add to dashboard Cite

Increased visitation to protected areas could have adverse impacts on the conservation values in the protected areas, and therefore effective visitor monitoring methods are needed to meet the complex management challenges that arise. Collecting data on human impacts is highly time consuming, thus requiring more effective tools that allow for high‐quality and long‐term measurements. In this study, we show how unmanned aerial vehicles (i.e. UAV or drones) could be used to monitor tourism impacts in protected areas. Tourism has boomed in national parks in Norway in recent years, such as in Jotunheimen National Park for which this study applies. We test the use of drones on a site where new tourist facilities will be established to set a baseline to identify future changes. We demonstrate how drones could help protected area management by monitoring visitor use patterns and commonly associated impacts such as trail condition (width and depth), vegetation structure and disturbances, informal trail proliferation, trampling, and trash and other impacts along the trails. We assessed accuracy and reliability compared with intensive field measurements of impacts and found low‐cost drones to be effective in mapping the study area with a resolution of 0.5 cm/pixel: drone derived trail measurements were comparable to traditional measurements with a negligible divergence on trail width measurements and a consistent 1.05 cm divergence on trail depth measurements that can be corrected with a few validation points. In addition, we created a high‐resolution vegetation classification map that could be used as a baseline for monitoring impacts. We conclude that drones can effectively contribute to visitor monitoring by reducing time spent in the field and by providing high‐resolution time series that could be used as baseline to measure tourism impacts on conservation values in protected areas.

show abstract

Progress in Urban Remote Sensing

Yang

2021

Urban Remote Sensing

View full text Add to dashboard Cite

Drone-based land-cover mapping using a fuzzy unordered rule induction algorithm integrated into object-based image analysis

Cited by 64 publications

References 21 publications

Land Cover Classification from fused DSM and UAV Images Using Convolutional Neural Networks

Land Cover Classification from fused DSM and UAV Images Using Convolutional Neural Networks

Drones as a tool to monitor human impacts and vegetation changes in parks and protected areas

Progress in Urban Remote Sensing

Contact Info

Product

Resources

About