Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild
Visual identification of cattle in the wild provides an essential way for real-time cattle monitoring applicable to precision livestock farming. Chinese Simmental exhibit a yellow or brown coat with individually characteristic white stripes or spots, which makes a biometric identifier for identifica...
Published in: | Animals |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/ani12040459 https://doaj.org/article/3f70697c7f69413f9902acfb465092ef |
id |
ftdoajarticles:oai:doaj.org/article:3f70697c7f69413f9902acfb465092ef |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:3f70697c7f69413f9902acfb465092ef 2023-05-15T16:02:02+02:00 Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild Jianmin Zhao Qiusheng Lian Neal N. Xiong 2022-02-01T00:00:00Z https://doi.org/10.3390/ani12040459 https://doaj.org/article/3f70697c7f69413f9902acfb465092ef EN eng MDPI AG https://www.mdpi.com/2076-2615/12/4/459 https://doaj.org/toc/2076-2615 doi:10.3390/ani12040459 2076-2615 https://doaj.org/article/3f70697c7f69413f9902acfb465092ef Animals, Vol 12, Iss 459, p 459 (2022) cattle identification deep convolutional neural networks (DCNNs) deep metric learning (DML) open-set recognition precision livestock farming Veterinary medicine SF600-1100 Zoology QL1-991 article 2022 ftdoajarticles https://doi.org/10.3390/ani12040459 2022-12-31T09:45:27Z Visual identification of cattle in the wild provides an essential way for real-time cattle monitoring applicable to precision livestock farming. Chinese Simmental exhibit a yellow or brown coat with individually characteristic white stripes or spots, which makes a biometric identifier for identification possible. This work employed the observable biometric characteristics to perform cattle identification with an image from any viewpoint. We propose multi-center agent loss to jointly supervise the learning of DCNNs by SoftMax with multiple centers and the agent triplet. We reformulated SoftMax with multiple centers to reduce intra-class variance by offering more centers for feature clustering. Then, we utilized the agent triplet, which consisted of the features and the agents, to enforce separation among different classes. As there are no datasets for the identification of cattle with multi-view images, we created CNSID100, consisting of 11,635 images from 100 Chinese Simmental identities. Our proposed loss was comprehensively compared with several well-known losses on CNSID100 and OpenCows2020 and analyzed in an engineering application in the farming environment. It was encouraging to find that our approach outperformed the state-of-the-art models on the datasets above. The engineering application demonstrated that our pipeline with detection and recognition is promising for continuous cattle identification in real livestock farming scenarios. Article in Journal/Newspaper DML Directory of Open Access Journals: DOAJ Articles Animals 12 4 459 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
cattle identification deep convolutional neural networks (DCNNs) deep metric learning (DML) open-set recognition precision livestock farming Veterinary medicine SF600-1100 Zoology QL1-991 |
spellingShingle |
cattle identification deep convolutional neural networks (DCNNs) deep metric learning (DML) open-set recognition precision livestock farming Veterinary medicine SF600-1100 Zoology QL1-991 Jianmin Zhao Qiusheng Lian Neal N. Xiong Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild |
topic_facet |
cattle identification deep convolutional neural networks (DCNNs) deep metric learning (DML) open-set recognition precision livestock farming Veterinary medicine SF600-1100 Zoology QL1-991 |
description |
Visual identification of cattle in the wild provides an essential way for real-time cattle monitoring applicable to precision livestock farming. Chinese Simmental exhibit a yellow or brown coat with individually characteristic white stripes or spots, which makes a biometric identifier for identification possible. This work employed the observable biometric characteristics to perform cattle identification with an image from any viewpoint. We propose multi-center agent loss to jointly supervise the learning of DCNNs by SoftMax with multiple centers and the agent triplet. We reformulated SoftMax with multiple centers to reduce intra-class variance by offering more centers for feature clustering. Then, we utilized the agent triplet, which consisted of the features and the agents, to enforce separation among different classes. As there are no datasets for the identification of cattle with multi-view images, we created CNSID100, consisting of 11,635 images from 100 Chinese Simmental identities. Our proposed loss was comprehensively compared with several well-known losses on CNSID100 and OpenCows2020 and analyzed in an engineering application in the farming environment. It was encouraging to find that our approach outperformed the state-of-the-art models on the datasets above. The engineering application demonstrated that our pipeline with detection and recognition is promising for continuous cattle identification in real livestock farming scenarios. |
format |
Article in Journal/Newspaper |
author |
Jianmin Zhao Qiusheng Lian Neal N. Xiong |
author_facet |
Jianmin Zhao Qiusheng Lian Neal N. Xiong |
author_sort |
Jianmin Zhao |
title |
Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild |
title_short |
Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild |
title_full |
Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild |
title_fullStr |
Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild |
title_full_unstemmed |
Multi-Center Agent Loss for Visual Identification of Chinese Simmental in the Wild |
title_sort |
multi-center agent loss for visual identification of chinese simmental in the wild |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/ani12040459 https://doaj.org/article/3f70697c7f69413f9902acfb465092ef |
genre |
DML |
genre_facet |
DML |
op_source |
Animals, Vol 12, Iss 459, p 459 (2022) |
op_relation |
https://www.mdpi.com/2076-2615/12/4/459 https://doaj.org/toc/2076-2615 doi:10.3390/ani12040459 2076-2615 https://doaj.org/article/3f70697c7f69413f9902acfb465092ef |
op_doi |
https://doi.org/10.3390/ani12040459 |
container_title |
Animals |
container_volume |
12 |
container_issue |
4 |
container_start_page |
459 |
_version_ |
1766397675238850560 |