ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis)

Abstract The Indo‐Pacific humpback dolphin ( Sousa chinensis ) is a small‐toothed whale species that inhabits estuaries and shallow coastal waters from the eastern Indian Ocean to the western Pacific, and faces significant negative impacts from anthropogenic activities. The noninvasive Photo‐identif...

Full description

Bibliographic Details
Published in:Marine Mammal Science
Main Authors: Yang, Minghao, Wu, Zhongrui, Zang, Xiqing, Jin, Changlong, Zhu, Qian
Other Authors: Ministry of Agriculture and Rural Affairs of the People's Republic of China, Ocean Park Conservation Foundation, Hong Kong
Format: Article in Journal/Newspaper
Language:English
Published: Wiley 2024
Subjects:
Online Access:http://dx.doi.org/10.1111/mms.13154
https://onlinelibrary.wiley.com/doi/pdf/10.1111/mms.13154
id crwiley:10.1111/mms.13154
record_format openpolar
spelling crwiley:10.1111/mms.13154 2024-09-15T18:39:10+00:00 ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis) Yang, Minghao Wu, Zhongrui Zang, Xiqing Jin, Changlong Zhu, Qian Ministry of Agriculture and Rural Affairs of the People's Republic of China Ocean Park Conservation Foundation, Hong Kong 2024 http://dx.doi.org/10.1111/mms.13154 https://onlinelibrary.wiley.com/doi/pdf/10.1111/mms.13154 en eng Wiley http://onlinelibrary.wiley.com/termsAndConditions#vor Marine Mammal Science ISSN 0824-0469 1748-7692 journal-article 2024 crwiley https://doi.org/10.1111/mms.13154 2024-07-23T04:11:59Z Abstract The Indo‐Pacific humpback dolphin ( Sousa chinensis ) is a small‐toothed whale species that inhabits estuaries and shallow coastal waters from the eastern Indian Ocean to the western Pacific, and faces significant negative impacts from anthropogenic activities. The noninvasive Photo‐identification method enables individual identification and abundance estimation based on natural markings of cetaceans without disrupting their natural behaviors. Currently, the identification of S. chinensis using photographs relies primarily on time‐intensive visual recognition by experienced researchers. Through field surveys conducted in the west Huangmao Sea area from 2012 to 2021, we compiled the Zhu‐Ming data set focusing on S. chinensis (ZMSC), consisting of 479 individuals and 5,196 photos. Utilizing the ZMSC, we proposed a Few‐Shot Identification method for S. chinensis (FISC), which achieved 85.93% identification Top‐1 accuracy. The implementation of proper preprocessing steps and data augmentation techniques has significantly enhanced the performance of FISC, while visualizing network weights has improved its interpretability. Despite the remaining challenges of data imbalance and the inability to automatically allocate new labels, ZMFISC alleviates the challenge of the current heavy reliance on time‐intensive visual recognition methods by researchers for individual identification of S. chinensis and provide a valuable tool to enhance future conservation efforts for S. chinensis . Article in Journal/Newspaper toothed whale Wiley Online Library Marine Mammal Science
institution Open Polar
collection Wiley Online Library
op_collection_id crwiley
language English
description Abstract The Indo‐Pacific humpback dolphin ( Sousa chinensis ) is a small‐toothed whale species that inhabits estuaries and shallow coastal waters from the eastern Indian Ocean to the western Pacific, and faces significant negative impacts from anthropogenic activities. The noninvasive Photo‐identification method enables individual identification and abundance estimation based on natural markings of cetaceans without disrupting their natural behaviors. Currently, the identification of S. chinensis using photographs relies primarily on time‐intensive visual recognition by experienced researchers. Through field surveys conducted in the west Huangmao Sea area from 2012 to 2021, we compiled the Zhu‐Ming data set focusing on S. chinensis (ZMSC), consisting of 479 individuals and 5,196 photos. Utilizing the ZMSC, we proposed a Few‐Shot Identification method for S. chinensis (FISC), which achieved 85.93% identification Top‐1 accuracy. The implementation of proper preprocessing steps and data augmentation techniques has significantly enhanced the performance of FISC, while visualizing network weights has improved its interpretability. Despite the remaining challenges of data imbalance and the inability to automatically allocate new labels, ZMFISC alleviates the challenge of the current heavy reliance on time‐intensive visual recognition methods by researchers for individual identification of S. chinensis and provide a valuable tool to enhance future conservation efforts for S. chinensis .
author2 Ministry of Agriculture and Rural Affairs of the People's Republic of China
Ocean Park Conservation Foundation, Hong Kong
format Article in Journal/Newspaper
author Yang, Minghao
Wu, Zhongrui
Zang, Xiqing
Jin, Changlong
Zhu, Qian
spellingShingle Yang, Minghao
Wu, Zhongrui
Zang, Xiqing
Jin, Changlong
Zhu, Qian
ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis)
author_facet Yang, Minghao
Wu, Zhongrui
Zang, Xiqing
Jin, Changlong
Zhu, Qian
author_sort Yang, Minghao
title ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis)
title_short ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis)
title_full ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis)
title_fullStr ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis)
title_full_unstemmed ZMFISC: Zhu‐Ming data set with a convolutional neural network for identifying Indo‐Pacific humpback dolphins ( Sousa chinensis)
title_sort zmfisc: zhu‐ming data set with a convolutional neural network for identifying indo‐pacific humpback dolphins ( sousa chinensis)
publisher Wiley
publishDate 2024
url http://dx.doi.org/10.1111/mms.13154
https://onlinelibrary.wiley.com/doi/pdf/10.1111/mms.13154
genre toothed whale
genre_facet toothed whale
op_source Marine Mammal Science
ISSN 0824-0469 1748-7692
op_rights http://onlinelibrary.wiley.com/termsAndConditions#vor
op_doi https://doi.org/10.1111/mms.13154
container_title Marine Mammal Science
_version_ 1810483577620529152