Super-resolution fusion optimization for poultry detection: a multi-object chicken detection method
Journal of Animal Science · 03.01.2023 · 101
DOI: 10.1093/jas/skad249 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Animal Science, online erschienen am 25.07.2023. Verfasst von Zhenlong Wu und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering, South China Agricultural University, Guangzhou 510642, PR China. Hauptthemen laut MEDLINE: Chickens, Poultry. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Guangdong Province Special Fund for Modern Agricultural Industry Common Key Technology R&D Innovation Team, Guangdong Chaozhou Science and Technology Planning Project.
Abstract (Originalsprache)
Accurate poultry detection is crucial for studying poultry behavior using computer vision and video surveillance. However, in free-range farming environments, detecting chickens can often be challenging due to their small size and mutual occlusion. The current detection algorithms exhibit a low level of accuracy, with a high probability of false and missed detections. To address this, we proposed a multi-object chicken detection method named Super-resolution Chicken Detection, which utilizes super-resolution fusion optimization. The algorithm employs the residual–residual dense block to extract image features and used a generative adversarial network to compensate for the loss of details during deep convolution, producing high-resolution images for detection. The proposed algorithm was validated with the B1 data set and the MC1 multi-object data set, demonstrating that the reconstructed images possessed richer pixel features compared to original images, specifically it improved detection accuracy and reduced the number of missed detections. The structural similarity of the reconstructed images was 99.9%, and the peak signal-to-noise ratio was above 30. The algorithm improved the Average Precision50:95 of all You Only Look Once Version X (YOLOX) models, with the largest improvement for the B1 data set with YOLOX-Large (+6.3%) and for the MC1 data set with YOLOX-Small (+4.1%). This was the first time a super-resolution reconstruction technique was applied to multi-object poultry detection. Our method will provide a fresh approach for future poultry researchers to improve the accuracy of object detection using computer vision and video surveillance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Engineering, South China Agricultural University, Guangzhou 510642, PR China.
- State Key Laboratory of Swine and Poultry Breeding Industry, Guangzhou 510642, PR China.
- National Engineering Research Center for Breeding Swine Industry, Guangzhou 510642, PR China.
Förderung
- Guangdong Province Special Fund for Modern Agricultural Industry Common Key Technology R&D Innovation Team
- Guangdong Chaozhou Science and Technology Planning Project
Zitieren
APA
Wu, Z., Zhang, T., Fang, C., Yang, J., Ma, C., Zheng, H., & Zhao, H. (2023). Super-resolution fusion optimization for poultry detection: a multi-object chicken detection method. Journal of Animal Science, 101. https://doi.org/10.1093/jas/skad249
Vancouver
Wu Z, Zhang T, Fang C, Yang J, Ma C, Zheng H, et al. Super-resolution fusion optimization for poultry detection: a multi-object chicken detection method. Journal of Animal Science. 2023;101. doi:10.1093/jas/skad249
BibTeX
@article{Wu2023,
author = {Wu, Zhenlong and Zhang, Tiemin and Fang, Cheng and Yang, Jikang and Ma, Chuang and Zheng, Haikun and Zhao, Hongzhi},
title = {Super-resolution fusion optimization for poultry detection: a multi-object chicken detection method},
journal = {Journal of Animal Science},
year = {2023},
volume = {101},
doi = {10.1093/jas/skad249}
}
EUVIMED