Spectral Reflectance of Indian Ocean Surface to Detect Blue Whales Using VHRS Images.

Protecting blue whales is a core principle of the One-earth Initiative. Accurate detection and classification in oceanic environments are crucial for marine conservation, particularly to avoid mis-classification with other marine objects. Building on our earlier work using Transformer-based models for Detection and tracking of blue whales in the Indian Ocean, this study refines classification accuracy through the application of spectral indices. High-resolution data, obtained from NSIL Bangalore(ISRO) and Planet.com with resolutions of 1.6m and 3m, respectively, is utilized to tackle the complex task of distinguishing blue whales from other marine objects. Statistical Machine learning model are used to validate the detection output accurately by means of whale reflectance data. Mean square error(MSE) is used to check the performance of the prediction. The combined use of these technologies outperformed traditional methods, offering an accuracy of 0.85 and reliability for real-time whale monitoring.

Authors

Institutions

Publication Details

Published
2025-02-07
DOI
https://doi.org/10.1109/icccit62592.2025.10927940
Primary Topic
Marine animal studies overview
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Spectral Reflectance of Indian Ocean Surface to Detect Blue Whales Using VHRS Images.

Prudhvi Narayana Bandaru, Vasavi Sanikommu, Balasai Sigreddy
Marine animal studies overview
article

Spectral Reflectance of Indian Ocean Surface to Detect Blue Whales Using VHRS Images.

Prudhvi Narayana Bandaru, Vasavi Sanikommu, Balasai Sigreddy
article en

Abstract

Protecting blue whales is a core principle of the One-earth Initiative. Accurate detection and classification in oceanic environments are crucial for marine conservation, particularly to avoid mis-classification with other marine objects. Building on our earlier work using Transformer-based models for Detection and tracking of blue whales in the Indian Ocean, this study refines classification accuracy through the application of spectral indices. High-resolution data, obtained from NSIL Bangalore(ISRO) and Planet.com with resolutions of 1.6m and 3m, respectively, is utilized to tackle the complex task of distinguishing blue whales from other marine objects. Statistical Machine learning model are used to validate the detection output accurately by means of whale reflectance data. Mean square error(MSE) is used to check the performance of the prediction. The combined use of these technologies outperformed traditional methods, offering an accuracy of 0.85 and reliability for real-time whale monitoring.

Siddhartha Medical College (IN)
Life below water
Openalex Percentile: Top 94%
Marine animal studies overview
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.