Comparative Assessment Between Per-Pixel and Object-Oriented for Mapping Land Cover and Use

Prudente, Victor Hugo Rohden; Silva, Bruno B. da; Johann, Jerry Adriani; Mercante, Erivelto; Oldoni, Lucas Volochen

doi:10.1590/1809-4430-eng.agric.v37n5p1015-1027/2017

Cited by 7 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OBIA (Object Based Image Analysisi) merupakan salah satu teknik yang banyak diterapkan untuk menderivasi informasi tutupan lahan melalui citra penginderaan jauh. Prinsip dasar dalam teknik tersebut adalah segmentasi dan klasifikasi dimana melibatkan aspek spektral (nilai piksel) juga aspek geometris dan topologis dari citra yang digunakan (Prudente, et al, 2017). Segmentasi dalam konteks OBIA merujuk pada pengelompokan nilai piksel yang saling bertetangga dalam area atau segmen tertentu berdasarkan similarity atas nilai spektral atau kenampakan tekstural (Meinel & Nuebert, 2004;dalam Hussein, 2016).…”

Section: Pendahuluanunclassified

Pemetaan Tutupan Lahan Sebagian Wilayah Kabupaten Kulonprogo Menggunakan Citra Resolusi Spasial Tinggi Dengan Pendekatan Obia (Object Based Image Analysis)

Waspadi,

Lestariningsih,

Ariasari

et al. 2023

JHL

View full text Add to dashboard Cite

The importance of land cover information in various planning circumstances results in high demand for such up-to-date information continuously. Remote sensing is a time and cost-effective technology that could provide such information. Remote sensing can be employed to derive numerous information from a distance without requiring direct contact with the object. The remote sensing data analysis simply demands field verification to produce scientifically admissible land cover maps. In the process, the analysis can be done with visual as well as digital analysis. In terms of digital analysis, the OBIA (Object-Based Image Analysis) technique could be deployed to synthesize land cover information in the form of maps. OBIA is a digital interpretation technique consisting of two processes named segmentation and classification which require a dominant role of interpreter. The study aims is apply OBIA in Pleiades imagery to produce land cover maps in parts of the Kulonprogo region. The accuracy of the produced map then be evaluated using the confusion matrix method and Kappa Index. The analysis reveals that OBIA is adequate in terms of providing accurate land cover maps using high spatial remote sensing imagery. The Overall accuracy and Kappa Index values of the resulting map reached 91.07% and 0.92. The results exhibit that the technique applied has a high level of confidence and could be scientifically accepted.Keywords: Accuracy Assessments, Land cover, OBIA, Pleiades.AbstrakPentingnya informasi tutupan lahan dalam berbagai bidang perencanaan mengakibatkan tingginya kebutuhan dan keterbaharuan informasi tersebut secara berkelanjutan. Penginderaan jauh merupakan salah satu teknologi yang dapat digunakan untuk menyediakan informasi tutupan lahan secara time and cost effective. Penginderaan jauh dapat digunakan untuk menderivasi berbagai informasi tanpa harus ada kontak langsung dengan objek tersebut. Analisa data penginderaan jauh hanya memerlukan verifikasi lapangan untuk menghasilkan peta tutupan lahan yang dapat dipertanggungjawabkan secara ilmiah. Pada prosesnya, analisa tersebut dapat dilakukan dengan berbagai macam teknik; baik secara digital maupun visual. Secara digital, derivasi informasi tutupan lahan dapat dilakukan dengan teknik OBIA (Object Based Image Analysis). OBIA merupakan teknik interpretasi digital yang terdiri atas segmentasi dan klasifikasi dimana dalam prosesnya, memerlukan peran interpreter yang cukup dominan. Penelitian ini bertujuan untuk memetakan tutupan lahan pada sebagian wilayah Kulonprogo menggunakan citra Pleiades dengan teknik OBIA. Terhadap peta hasil analisis OBIA, dilakukan perhitungan akurasi dengan metode confusion matrix dan perhitungan Kappa Index untuk mengetahui akurasi dari penerapan OBIA pada citra Pleiades. Berdasarkan analisa dan perhitungan yang dilakukan, diketahui bahwa OBIA mampu memberikan hasil yang akurat untuk interpretasi informasi tutupan lahan menggunakan citra penginderaan jauh resolusi spasial tinggi. Nilai overall accuracy dan Kappa Index yang mencapai 91.07% dan 0.92 menunjukkan bahwa hasil analisis tersebut memiliki tingkat konfidensi yang tinggi dan dapat diterima juga dipertanggungjawabkan secara ilmiah. Kata kunci: Uji Akurasi, Tutupan Lahan, OBIA, Pleiades

show abstract

Section: Pendahuluanunclassified

Pemetaan Tutupan Lahan Sebagian Wilayah Kabupaten Kulonprogo Menggunakan Citra Resolusi Spasial Tinggi Dengan Pendekatan Obia (Object Based Image Analysis)

Waspadi,

Lestariningsih,

Ariasari

et al. 2023

JHL

View full text Add to dashboard Cite

show abstract

“…Object-oriented classification, as a novel classification approach, can extract features, such as texture, shape and spatial information, after image segmentation which would suppress noise and improve the classification accuracy [30] . Some statistical models and segmentation methods for SAR data have been studied [31][32][33] .…”

Section: Introduction mentioning

confidence: 99%

Integration of optical and SAR remote sensing images for crop-type mapping based on a novel object-oriented feature selection method

Cui

Zhang

Wang

et al. 2020

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Remote sensing is an important technical means to investigate land resources. Optical imagery has been widely used in crop classification and can show changes in moisture and chlorophyll content in crop leaves, whereas synthetic aperture radar (SAR) imagery is sensitive to changes in growth states and morphological structures. Crop-type mapping with a single type of imagery sometimes has unsatisfactory precision, so providing precise spatiotemporal information on crop type at a local scale for agricultural applications is difficult. To explore the abilities of combining optical and SAR images and to solve the problem of inaccurate spatial information for land parcels, a new method is proposed in this paper to improve crop-type identification accuracy. Multifeatures were derived from the full polarimetric SAR data (GaoFen-3) and a high-resolution optical image (GaoFen-2), and the farmland parcels used as the basic for object-oriented classification were obtained from the GaoFen-2 image using optimal scale segmentation. A novel feature subset selection method based on within-class aggregation and between-class scatter (WA-BS) is proposed to extract the optimal feature subset. Finally, crop-type mapping was produced by a support vector machine (SVM) classifier. The results showed that the proposed method achieved good classification results with an overall accuracy of 89.50%, which is better than the crop classification results derived from SAR-based segmentation. Compared with the ReliefF, mRMR and LeastC feature selection algorithms, the WA-BS algorithm can effectively remove redundant features that are strongly correlated and obtain a high classification accuracy via the obtained optimal feature subset. This study shows that the accuracy of crop-type mapping in an area with multiple cropping patterns can be improved by the combination of optical and SAR remote sensing images.

show abstract

Ovipositional Reproduction of the Dengue Vector for Identifying High-Risk Urban Areas

Lage

Barbosa²,

Andrade³

et al. 2022

EcoHealth

View full text Add to dashboard Cite

Comparative Assessment Between Per-Pixel and Object-Oriented for Mapping Land Cover and Use

Cited by 7 publications

References 35 publications

Pemetaan Tutupan Lahan Sebagian Wilayah Kabupaten Kulonprogo Menggunakan Citra Resolusi Spasial Tinggi Dengan Pendekatan Obia (Object Based Image Analysis)

Pemetaan Tutupan Lahan Sebagian Wilayah Kabupaten Kulonprogo Menggunakan Citra Resolusi Spasial Tinggi Dengan Pendekatan Obia (Object Based Image Analysis)

Integration of optical and SAR remote sensing images for crop-type mapping based on a novel object-oriented feature selection method

Ovipositional Reproduction of the Dengue Vector for Identifying High-Risk Urban Areas

Contact Info

Product

Resources

About