scholarly journals Comparison of pixel-based and object-based image classification techniques in extracting information from UAV imagery data

2018 ◽  
Vol 169 ◽  
pp. 012098 ◽  
Author(s):  
H I Sibaruddin ◽  
H Z M Shafri ◽  
B Pradhan ◽  
N A Haron
Keyword(s):  
Image Classification ◽  
Classification Techniques ◽  
Object Based ◽  
Imagery Data

scholarly journals Remote sensing techniques: mapping and monitoring of mangrove ecosystem—a review

2021 ◽  
Author(s):  
Khushbu Maurya ◽  
Seema Mahajan ◽  
Nilima Chaube
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Image Classification ◽  
Digital Image ◽  
Mangrove Ecosystem ◽  
Mangrove Forests ◽  
Classification Techniques ◽  
Knowledge Based ◽  
Object Based ◽  
Remote Sensing Techniques

AbstractMangrove forests are considered to be the most productive ecosystem yet vanishing rapidly over the world. They are mostly found in the intertidal zone and sheltered by the seacoast. Mangroves have potential socio-economic benefits such as protecting the shoreline from storm and soil erosion, flood and flow control, acting as a carbon sink, provides a fertile breeding ground for marine species and fauna. It also acts as a source of income by providing various forest products. Restoration and conservation of mangrove forests remain a big challenge due to the large and inaccessible areas covered by mangroves forests which makes field assessment difficult and time-consuming. Remote sensing along with various digital image classification approaches seem to be promising in providing better and accurate results in mapping and monitoring the mangroves ecosystem. This review paper aims to provide a comprehensive summary of the work undertaken, and addresses various remote sensing techniques applied for mapping and monitoring of the mangrove ecosystem, and summarize their potential and limitation. For that various digital image classification techniques are analyzed and compared based on the type of image used with its spectral resolution, spatial resolution, and other related image features along with the accuracy of the classification to derive specific class information related to mangroves. The digital image classification techniques used for mangrove mapping and monitoring in various studies can be classified into pixel-based, object-based, and knowledge-based classifiers. The various satellite image data analyzed are ranged from light detection and ranging (LiDAR), hyperspectral and multispectral optical imagery, synthetic aperture radar (SAR), and aerial imagery. Supervised state of the art machine learning/deep machine learning algorithms which use both pixel-based and object-based approaches and can be combined with the knowledge-based approach are widely used for classification purpose, due to the recent development and evolution in these techniques. There is a huge future scope to study the performance of these classification techniques in combination with various high spatial and spectral resolution optical imageries, SAR and LiDAR, and also with multi-sensor, multiresolution, and temporal data.

Evaluation of various image classification techniques on Landsat to identify coral reefs

2013 ◽  
Vol 5 (2) ◽  
pp. 173-184 ◽  
Author(s):  
Tarun Teja Kondraju ◽  
Venkata Ravi Babu Mandla ◽  
R.S. Mahendra ◽  
T. Srinivas Kumar
Keyword(s):  
Coral Reefs ◽  
Image Classification ◽  
Classification Techniques

scholarly journals Identifikasi Gosong Karang Mengggunakan Citra Satelit Sentinel 2A (Studi Kasus: Perairan Pesisir Nias Utara)

2020 ◽  
Vol 21 (1) ◽  
pp. 95-108
Author(s):  
Anang Dwi Purwanto ◽  
Teguh Prayogo ◽  
Sartono Marpaung
Keyword(s):  
Coral Reefs ◽  
Image Classification ◽  
Classification Method ◽  
Fishing Ground ◽  
Field Observations ◽  
Geometric Correction ◽  
Radiometric Correction ◽  
Object Based ◽  
Sentinel 2A ◽  
North Sumatra

ABSTRACTThe waters of Northern Nias, North Sumatra Province have a great potential for natural resources, one of which is the reef which is often used as a fishing ground. This study aims to identify and monitor the distribution of coral reefs around the waters of Northern Nias. The location of study is limited by coordinates 97° 0'31'' - 97° 16'54'' E and 1° 29'2'' LU - 1° 6'24'' N. The study locations were grouped in 6 (six) areas including Mardika reef, Wunga reef, Mausi1 reef, Mausi2 reef, Tureloto reef and Senau reef. The data used were Sentinel 2A imagery acquisition on 19 September 2018 and field observations made on 6-12 September 2018. Data processing includes geometric correction, radiometric correction, water column correction and classification using pixel-based and object-based methods as well as by delineating on the image. One classification method will be chosen that is most suitable for the location of the reef. The results show Sentinel 2A was very helpful in mapping the distribution of coral reefs compared to direct observation in the field. The use of image classification method rightly is very helpful in distinguishing coral reef objects from surrounding objects. The estimated area of coral reefs was 1,793.20 ha with details of the Mardika reef 143.27 ha, Wunga reef 627.06 ha, Mausi1 reef 299.84 ha, Mausi2 reef 141.873 ha, Tureloto reef 244.73 ha, Senau reef 336.44 ha. The existence of coral reefs have a high potential as a fishing ground and a natural tourist attraction.Keywords: coral reefs, sentinel 2A, lyzenga 1978, image classification, Northern NiasABSTRAKPerairan Nias Utara yang terletak di Provinsi Sumatra Utara memiliki potensi kekayaan alam yang besar dimana salah satunya adalah gosong karang yang sering dijadikan lokasi penangkapan ikan oleh nelayan. Penelitian ini bertujuan untuk mengidentifikasi dan monitoring sebaran gosong karang di sekitar perairan Nias Utara. Lokasi penelitian dibatasi dengan koordinat 97°0’31’’ - 97°16’54’’ BT dan 1°29’2’’LU – 1°6’24’’  LU. Untuk mempermudah dalam pengolahan data maka lokasi kajian dikelompokkan dalam 6 (enam) kawasan diantaranya gosong Mardika, gosong Wunga, gosong Mausi1, gosong Mausi2, gosong Tureloto dan gosong Senau. Data yang digunakan adalah citra satelit Sentinel 2A hasil perekaman tanggal 19 September 2018 dan hasil pengamatan lapangan yang telah dilakukan pada tanggal 6 - 12 September 2018. Pengolahan data meliputi koreksi geometrik, koreksi radiometrik, koreksi kolom air dan klasifikasi menggunakan metode klasifikasi berbasis piksel dan berbasis objek serta deliniasi citra. Dari ketiga metode klasifikasi tersebut akan dipilih satu metode klasifikasi yang sesuai dengan lokasi gosong karang. Hasil penelitian menunjukkan citra Sentinel 2A sangat membantu dalam memetakan sebaran gosong karang dibandingkan dengan pengamatan langsung di lapangan. Pemilihan metode klasifikasi citra satelit yang tepat sangat membantu dalam membedakan objek gosong karang dengan objek di sekitarnya. Estimasi total luasan gosong karang di perairan Nias Utara adalah 1,793.20 ha dengan rincian luasan gosong karang Mardika 143.27 ha, gosong Wunga 627.06 ha, gosong Mausi1 299.84 ha, gosong Mausi2 141.873 ha, gosong Tureloto 244.73 ha, gosong Senau 336.44 ha. Keberadaan gosong karang memiliki potensi yang tinggi sebagai lokasi penangkapan ikan dan memiliki daya tarik sebagai tempat wisata alam.Kata kunci: gosong karang, sentinel 2A, lyzenga 1978, klasifikasi citra, Nias Utara

Sign in / Sign up

Export Citation Format

Share Document