Neural Network Based Methodology for Automatic Detection of Whale Blows in Infrared Video

Santhaseelan, Varun; Arigela, Saibabu; Asari, Vijayan K.

doi:10.1007/978-3-642-33179-4_23

Cited by 7 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Perryman et al, 1999) and provide greater coverage of the entire migration during acceptable weather conditions; automated blow detectors (e.g. Santhaseelan et al, 2012) can be developed to eliminate observer effects and standardise detectability to provide counts with minimal (and quantifiable) bias. These extensions would further serve to build a more robust and automated observation model to combine with the flexible abundance model for the migration process described in this paper.…”

Section: Discussionmentioning

confidence: 99%

Estimating gray whale abundance from shore-based counts using a multilevel Bayesian model

Durban¹,

Weller²,

Lang³

et al. 2023

JCRM

View full text Add to dashboard Cite

Counts of southbound migrating whales off California form the basis of abundance estimation for the eastern North Pacific stock of gray whales (Eschrichtius robustus). Previous assessments (1967–2007) have estimated detection probability (p) from the detection-non detection of pods by two independent observers. However, tracking distinct pods in the field can be difficult for single observers; resulting in biased estimates of pod sizes that needed correcting, and matching observations of the same pod by both observers involved key assumptions. Due to these limitations, a new observation approach has been adopted wherein a paired team of observers work together and use a computerised mapping application to better track and enumerate distinct pods and tally the number of whales passing during watch periods. This approach has produced consistent counts over four recently monitored migrations (2006/7, 2007/8, 2009/10 and 2010/11), with an apparent increase in p compared to the previous method. To evaluate p and estimate abundance in these four years, counts from two independent stations of paired observers operating simultaneously were compared using a hierarchical Bayesian ‘N-mixture’ model to jointly estimate p and abundance without the challenge of matching pods between stations. The baseline detectability po was estimated as 0.80 (95% Highest Posterior Density Interval [HPDI] = 0.75–0.85), which varied with observation conditions, observer effects and changes in whale abundance during the migration. Abundance changes were described using Bayesian model selection between a parametric model for a normally distributed common migration trend and a semi-parametric model that estimated the time trends independently for each year; the resultant migration curve was a weighted compromise between models, allowing for key departures from the common trend. The summed estimates of migration abundance ranged from 17,820 (95% HPDI = 16,150–19,920) in 2007/08 to 21,210 (95% HPDI = 19,420–23,230) in 2009/10, consistent with previous estimates and indicative of a stable population.

show abstract

Section: Discussionmentioning

confidence: 99%

Estimating gray whale abundance from shore-based counts using a multilevel Bayesian model

Durban¹,

Weller²,

Lang³

et al. 2023

JCRM

View full text Add to dashboard Cite

show abstract

“…Work by Graber (2011) demonstrates that infrared video can be used to detect the dorsal fins of mammals from far distances. These methods can also be used to detect blows, as the breath expelled from whales as they surface is warmer than the surrounding water (Graber, 2011;Santhaseelan, Arigela, & Asari, 2012;Santhaseelan & Asari, 2015). Most of this work, however, is focused on larger, migrating whale species.…”

Section: Boat and Shoreline Based Methodsmentioning

confidence: 99%

Automated Video Surveillance for the Study of Marine Mammal Behavior and Cognition

Karnowski¹,

Johnson²,

Hutchins³

2016

AB&C

View full text Add to dashboard Cite

Systems for detecting and tracking social marine mammals, including dolphins, can provide data to help explain their social dynamics, predict their behavior, and measure the impact of human interference. Data collected from video surveillance methods can be consistently and systematically sampled for studies of behavior, and frameby-frame analyses can uncover insights impossible to observe from real-time, freely occurring natural behavior. Advances in boat-based, aerial, and underwater recording platforms provide opportunities to document the behavior of marine mammals and create massive datasets. The use of human experts to detect, track, identify individuals, and recognize activity in video demands significant time and financial investment. This paper examines automated methods designed to analyze large video corpora containing marine mammals. While research is converging on best solutions for some automated tasks, particularly detection and classification, many research domains are ripe for exploration.

show abstract

“…PAM is only effective when marine mammals vocalize frequently, and when vocalizations are not masked by vessel or other background noise. With the goal of improving marine mammal detections beyond using these traditional methods, studies in recent years have evaluated the use of thermal imaging cameras to detect marine mammals at the ocean's surface (Verfuss et al 2018) and to make such detections automatically (Santhaseelan et al 2012;Zitterbart et al 2013). Thermal imaging systems have been used to detect marine mammals during nighttime hours for a few decades (Perryman et al 1999;Schoonmaker et al 2008), and an automatic detection system has been described and used in recent years (Zitterbart et al 2013;Smith et al 2020), but methods have not yet been standardized.…”

Section: Introductionmentioning

confidence: 99%

Scaling the Laws of Thermal Imaging–Based Whale Detection

Zitterbart

Smith

Flau

et al. 2020

Journal of Atmospheric and Oceanic Technology

View full text Add to dashboard Cite

Marine mammals are under growing pressure as anthropogenic use of the ocean increases. Ship strikes of large whales and loud underwater sound sources including air guns for marine geophysical prospecting and naval midfrequency sonar are criticized for their possible negative effects on marine mammals. Competent authorities regularly require the implementation of mitigation measures, including vessel speed reductions or shutdown of acoustic sources if marine mammals are sighted in sensitive areas or in predefined exclusion zones around a vessel. To ensure successful mitigation, reliable at-sea detection of animals is crucial. To date, ship-based marine mammal observers are the most commonly implemented detection method; however, thermal (IR) imaging–based automatic detection systems have been used in recent years. This study evaluates thermal imaging–based automatic whale detection technology for its use across different oceans. The performance of this technology is characterized with respect to environmental conditions, and an automatic detection algorithm for whale blows is presented. The technology can detect whales in polar, temperate, and subtropical ocean regimes over distances of up to several kilometers and outperforms marine mammal observers in the number of whales detected. These results show that thermal imaging technology can be used to assist in providing protection for marine mammals against ship strike and acoustic impact across the world’s oceans.

show abstract

Neural Network Based Methodology for Automatic Detection of Whale Blows in Infrared Video

Cited by 7 publications

References 8 publications

Estimating gray whale abundance from shore-based counts using a multilevel Bayesian model

Estimating gray whale abundance from shore-based counts using a multilevel Bayesian model

Automated Video Surveillance for the Study of Marine Mammal Behavior and Cognition

Scaling the Laws of Thermal Imaging–Based Whale Detection

Contact Info

Product

Resources

About