Oil spill detection from RISAT-1 imagery using texture analysis

Joseph, Manoj; Dutta, Sujay Kumar; Kumari, E. V. S. Sita; Prasad, A. V. V.

doi:10.1109/apmc.2016.7931359

Cited by 5 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Various kernel functions, including linear, polynomial, sigmoid, and radial basis function (RBF) kernels, are used to reduce the computational cost of dealing with high-dimensional feature spaces [248]. RBF [22,112,114,115,155,185,198] and polynomial kernel [194] are commonly used kernels in oil spill studies. However, the selection of the appropriate kernel type and its parameter configuration should be considered when adopting SVM for oil spill classification.…”

Section: Support Vector Machinementioning

confidence: 99%

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

et al. 2020

View full text Add to dashboard Cite

Remote sensing technologies and machine learning (ML) algorithms play an increasingly important role in accurate detection and monitoring of oil spill slicks, assisting scientists in forecasting their trajectories, developing clean-up plans, taking timely and urgent actions, and applying effective treatments to contain and alleviate adverse effects. Review and analysis of different sources of remotely sensed data and various components of ML classification systems for oil spill detection and monitoring are presented in this study. More than 100 publications in the field of oil spill remote sensing, published in the past 10 years, are reviewed in this paper. The first part of this review discusses the strengths and weaknesses of different sources of remotely sensed data used for oil spill detection. Necessary preprocessing and preparation of data for developing classification models are then highlighted. Feature extraction, feature selection, and widely used handcrafted features for oil spill detection are subsequently introduced and analyzed. The second part of this review explains the use and capabilities of different classical and developed state-of-the-art ML techniques for oil spill detection. Finally, an in-depth discussion on limitations, open challenges, considerations of oil spill classification systems using remote sensing, and state-of-the-art ML algorithms are highlighted along with conclusions and insights into future directions.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Misra & Balaji (2017) melakukan kajian deteksi dengan data Radarsat 2 menggunakan metode adaptive threshold dan analisis tekstur, dan menujukkan bahwa analisis tekstur meningkatkan hasil estimasi sebaran tumpahan minyak. Joseph, Jayasri, Dutta, Kumari, & Prasad (2017) Tahap awal dilakukan koreksi data meliputi koreksi atau kalibrasi radiometrik dengan mengkonversi nilai digital menjadi nilai backscatter, dan koreksi geometrik dilakukan dengan algoritma Range-Dopler Terain Corection dan menggunakan referensi data DEM (Digital Elevation Model) SRTM resolusi 30 m. Selanjutnya dilakukan proses filtering untuk menghilangkan speckle noise menggunakan filter Lee. Menurut Marghany & Van Genderen (2014) algoritma Lee dapat beroperasi dengan baik pada lapisan minyak yang linier.…”

Section: Pendahuluanunclassified

Deteksi Tumpahan Minyak Menggunakan Metode Adaptive Threshold Dan Analisis Tekstur Pada Data Sar

Sulma

Rahmi²,

Febrianti³

et al. 2019

MIG

View full text Add to dashboard Cite

Metode untuk deteksi tumpahan minyak menggunakan data SAR telah berkembang dari metode manual hingga metode otomatis. Penelitian ini bertujuan untuk membandingkan metode analisis tekstur dan adaptive threshold untuk deteksi tumpahan minyak menggunakan citra SAR Sentinel 1. Wilayah kajian meliputi perairan utara Bintan yang hampir rutin terjadi kasus tumpahan minyak khususnya pada musim barat/utara, serta perairan Teluk Balikpapan yang mengalami kejadian tumpahan minyak yang cukup besar pada akhir Maret 2018. Tahap awal dilakukan koreksi data meliputi koreksi atau kalibrasi radiometrik, filtering dan land masking. Tahap selanjutnya adalah deteksi dark spot yang dilakukan menggunakan dua pendekatan dan dibandingkan metode yang memberikan hasil terbaik. Metode pertama adalah analisis tekstur menggunakan Grey Level cooccurrence matrix (GLCM) dengan perhitungan homogenity, entropi dan Angular Second Moment (ASM), kemudian dilakukan klasifikasi menggunakan Maximum Likelihood, sedangkan pendekatan kedua adalah menggunakan adaptive threshold. Hasil kajian menunjukkan bahwa metode tekstur analisis GLCM dan adaptive threshold pada citra SAR Sentinel 1 memberikan hasil yang cukup baik untuk area tumpahan minyak yang cukup tebal. Namun untuk area tumpahan minyak yang tipis atau pada wilayah pencampuran air, metode adaptive threshold memberikan hasil yang lebih baik. Modifikasi berupa masking kapal (atau objek dengan backscatter tinggi) sebelum diterapkan metode adaptive threshold dapat mengurangi kesalahan seperti terdeteksinya objek minyak di sekitar kapal.

show abstract

“…Nesse contexto o presente trabalho tem como objetivo avaliar o desempenho de métodos de aprendizado profundo para a classificação de eventos no mar usando imagens de radar de abertura sintética (SAR). Os métodos de aprendizado profundo [6,8] destacam-se por seu ótimo desempenho em cenários de alta complexidade superando os métodos tradicionais baseados em algoritmos de classificação como Máquinas de Vetores de Suporte (SVM) [10,11] ou Random Forest [7], que requerem um processo de extração de atributos desenhado por um especialista. Por outro lado, no aprendizado profundo é feito um aprendizado end-to-end, onde os atributos mais representativos são aprendidos e extraídos pelo modelo, apresentando um grande benefício na automatização do estudo de atributos, havendo uma menor intervenção de especialistas.…”

Section: Motivaçãounclassified

“…Várias abordagens têm sido propostas para o estudo de eventos no mar: tendo abordagens baseados em algoritmos de aprendizado de máquina [7,9,10,11,12] (e.g. Support Vector Machines -SVM, Random Forest, Clustering) e aprendizado profundo [13,14,15,16,17,18,19] (e.g.…”

Section: Organização Dos Capítulos Restantes Da Dissertaçãounclassified

“…Baseado nos algoritmos de aprendizado de máquina, Joseph et al [11] propõe uma abordagem para segmentação de imagens SAR usando SVM, realizando uma extração de atributos usando múltiplas polarizações. Neste cenário SVM mostrou um desempenho bom no estudo de imagens com variação no ângulo de incidência, tendo em contrapartida a necessidade de definir um critério de contexto e extração de atributos.…”

Section: Organização Dos Capítulos Restantes Da Dissertaçãounclassified

See 1 more Smart Citation

Aplicação E Avaliação Do Desempenho De Métodos De Aprendizado Profundo Para Classificação De Imagens De Radar Sar (Synthetic Aperture Radar) Para Monitoramento De Áreas Marinhas Na Detecção De Feições De Interesse Para a Área De Óleo E Gás

RUIZ¹

View full text Add to dashboard Cite

show abstract

Oil spill detection from RISAT-1 imagery using texture analysis

Cited by 5 publications

References 4 publications

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

Deteksi Tumpahan Minyak Menggunakan Metode Adaptive Threshold Dan Analisis Tekstur Pada Data Sar

Aplicação E Avaliação Do Desempenho De Métodos De Aprendizado Profundo Para Classificação De Imagens De Radar Sar (Synthetic Aperture Radar) Para Monitoramento De Áreas Marinhas Na Detecção De Feições De Interesse Para a Área De Óleo E Gás

Contact Info

Product

Resources

About