Counting sheep: human experience vs. Yolo algorithm with drone to determine population
This study assessed the efficiency of traditional human counting methods and the YOLOv7 algorithm in sheep population management at SAIS Pachacutec S.A.C., Peru. Human counters with varying experience levels (M1-M4) and the YOLOv7 algorithm (M5) were evaluated across six sheep flocks of differe...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Veterinary Medicine, Chiang Mai University
2024-07-01
|
| Series: | Veterinary Integrative Sciences |
| Online Access: | https://he02.tci-thaijo.org/index.php/vis/article/view/269700 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850062320720412672 |
|---|---|
| author | Jordan Ninahuanca Carhuas Luigüi Andre Cerna Grados Ide Unchupaico Payano Edgar Garcia-Olarte Yakelin Mauricio-Ramos Carlos Quispe Eulogio Mohamed M. Hadi Mohamed |
| author_facet | Jordan Ninahuanca Carhuas Luigüi Andre Cerna Grados Ide Unchupaico Payano Edgar Garcia-Olarte Yakelin Mauricio-Ramos Carlos Quispe Eulogio Mohamed M. Hadi Mohamed |
| author_sort | Jordan Ninahuanca Carhuas |
| collection | DOAJ |
| description |
This study assessed the efficiency of traditional human counting methods and the YOLOv7 algorithm in sheep population management at SAIS Pachacutec S.A.C., Peru. Human counters with varying experience levels (M1-M4) and the YOLOv7 algorithm (M5) were evaluated across six sheep flocks of different sizes. Traditional counting involved "linear pair counting" with human assistants, while the YOLOv7 algorithm utilized drone-captured images for automated counting. Using ANOVA and post-hoc tests, data analysis indicated that 24 months of human experience achieved 100% accuracy, highlighting the importance of expertise in accurate population management. The YOLOv7 algorithm achieved 85% accuracy, affected by factors such as the number of training images, hardware limitations, and training parameters. Despite its lower accuracy, YOLOv7 significantly reduced counting time compared to manual methods, making it a viable option for rapid object counting tasks. Further improvements in algorithm training and computational resources could enhance the algorithm's accuracy. These findings suggest that while human expertise remains critical for precise sheep counting, advancements in computer vision algorithms like YOLOv7 offer promising support, particularly for reducing counting time. |
| format | Article |
| id | doaj-art-e8044faf891347948699f30e41a6abaf |
| institution | DOAJ |
| issn | 2629-9968 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | Faculty of Veterinary Medicine, Chiang Mai University |
| record_format | Article |
| series | Veterinary Integrative Sciences |
| spelling | doaj-art-e8044faf891347948699f30e41a6abaf2025-08-20T02:49:58ZengFaculty of Veterinary Medicine, Chiang Mai UniversityVeterinary Integrative Sciences2629-99682024-07-0123210.12982/VIS.2025.032Counting sheep: human experience vs. Yolo algorithm with drone to determine populationJordan Ninahuanca Carhuashttps://orcid.org/0000-0002-0137-0631Luigüi Andre Cerna Gradoshttps://orcid.org/0009-0008-1079-607XIde Unchupaico Payanohttps://orcid.org/0000-0002-6441-5016Edgar Garcia-Olartehttps://orcid.org/0000-0003-1643-288XYakelin Mauricio-Ramoshttps://orcid.org/0009-0008-1518-6238Carlos Quispe Eulogiohttps://orcid.org/0000-0002-2316-1646Mohamed M. Hadi Mohamedhttps://orcid.org/0000-0003-1940-8383 This study assessed the efficiency of traditional human counting methods and the YOLOv7 algorithm in sheep population management at SAIS Pachacutec S.A.C., Peru. Human counters with varying experience levels (M1-M4) and the YOLOv7 algorithm (M5) were evaluated across six sheep flocks of different sizes. Traditional counting involved "linear pair counting" with human assistants, while the YOLOv7 algorithm utilized drone-captured images for automated counting. Using ANOVA and post-hoc tests, data analysis indicated that 24 months of human experience achieved 100% accuracy, highlighting the importance of expertise in accurate population management. The YOLOv7 algorithm achieved 85% accuracy, affected by factors such as the number of training images, hardware limitations, and training parameters. Despite its lower accuracy, YOLOv7 significantly reduced counting time compared to manual methods, making it a viable option for rapid object counting tasks. Further improvements in algorithm training and computational resources could enhance the algorithm's accuracy. These findings suggest that while human expertise remains critical for precise sheep counting, advancements in computer vision algorithms like YOLOv7 offer promising support, particularly for reducing counting time.https://he02.tci-thaijo.org/index.php/vis/article/view/269700 |
| spellingShingle | Jordan Ninahuanca Carhuas Luigüi Andre Cerna Grados Ide Unchupaico Payano Edgar Garcia-Olarte Yakelin Mauricio-Ramos Carlos Quispe Eulogio Mohamed M. Hadi Mohamed Counting sheep: human experience vs. Yolo algorithm with drone to determine population Veterinary Integrative Sciences |
| title | Counting sheep: human experience vs. Yolo algorithm with drone to determine population |
| title_full | Counting sheep: human experience vs. Yolo algorithm with drone to determine population |
| title_fullStr | Counting sheep: human experience vs. Yolo algorithm with drone to determine population |
| title_full_unstemmed | Counting sheep: human experience vs. Yolo algorithm with drone to determine population |
| title_short | Counting sheep: human experience vs. Yolo algorithm with drone to determine population |
| title_sort | counting sheep human experience vs yolo algorithm with drone to determine population |
| url | https://he02.tci-thaijo.org/index.php/vis/article/view/269700 |
| work_keys_str_mv | AT jordanninahuancacarhuas countingsheephumanexperiencevsyoloalgorithmwithdronetodeterminepopulation AT luiguiandrecernagrados countingsheephumanexperiencevsyoloalgorithmwithdronetodeterminepopulation AT ideunchupaicopayano countingsheephumanexperiencevsyoloalgorithmwithdronetodeterminepopulation AT edgargarciaolarte countingsheephumanexperiencevsyoloalgorithmwithdronetodeterminepopulation AT yakelinmauricioramos countingsheephumanexperiencevsyoloalgorithmwithdronetodeterminepopulation AT carlosquispeeulogio countingsheephumanexperiencevsyoloalgorithmwithdronetodeterminepopulation AT mohamedmhadimohamed countingsheephumanexperiencevsyoloalgorithmwithdronetodeterminepopulation |