A deep learning-based approach for feeding behavior recognition of weanling pigs
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaningbased method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.
Abstract
Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaningbased method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.
참고문헌 (24)
- K.H. Kim, "Effects of Gestational Housing on Reproductive Performance and Behavior of Sows with Different Backfat Thickness", Animal Bioscience, 29(1), pp.142~148 (2016), 아세아·태평양축산학회[DOI]
- 최요한, "Night feeding in lactating sows is an essential management approach to decrease the detrimental impacts of heat stress", 한국축산학회지, 61(6), pp.333~339 (2019), 한국축산학회[DOI]
- A. R. Hosseindoust, "Productive performance of weanling piglets was improved by administration of a mixture of bacteriophages, targeted to control Coliforms and Clostridium spp. shedding in a challenging environment", Journal of Animal Physiology and Animal Nutrition, 101(5), pp.e98~e107 (2017), Wiley[DOI]
- Amy L Miller, "How many pigs within a group need to be sick to lead to a diagnostic change in the group’s behavior?", Journal of Animal Science, 97(5), pp.1956~1966 (2019), Oxford University Press (OUP)[DOI]
- AR Hosseindoust, "Dietary bacteriophages as an alternative for zinc oxide or organic acids to control diarrhoea and improve the performance of weanling piglets", Veterinární Medicína, 62(2), pp.53~61 (2017), Czech Academy of Agricultural Sciences[DOI]
- Choi YH, "An overview of hourly rhythm of demand-feeding pattern by a controlled feeding system on productive performance of lactating sows during summer", Ital J Anim Sci, 17, pp.1001~1009 (2018)
- J. Ghassemi Nejad, "Effects of water restriction after feeding during heat stress on nutrient digestibility, nitrogen balance, blood profile and characteristics in Corriedale ewes", Animal Feed Science and Technology, 193, pp.1~8 (2014), Elsevier BV[DOI]
- "Monitor water for health" (2007)[URL]
- Chen Chen, "Behaviour recognition of pigs and cattle: Journey from computer vision to deep learning", Computers and Electronics in Agriculture, 187, pp.106255~ (2021), Elsevier BV[DOI]
- Wei-xing Zhu, "Recognition and drinking behaviour analysis of individual pigs based on machine vision", Livestock Science, 205, pp.129~136 (2017), Elsevier BV[DOI]
- Qiumei Yang, "Feeding behavior recognition for group-housed pigs with the Faster R-CNN", Computers and Electronics in Agriculture, 155, pp.453~460 (2018), Elsevier BV[DOI]
- Weijia Huang, "Identification of group-housed pigs based on Gabor and Local Binary Pattern features", Biosystems Engineering, 166, pp.90~100 (2018), Elsevier BV[DOI]
- Mathieu Marsot, "An adaptive pig face recognition approach using Convolutional Neural Networks", Computers and Electronics in Agriculture, 173, pp.105386~ (2020), Elsevier BV[DOI]
- Mark F. Hansen, "Towards on-farm pig face recognition using convolutional neural networks", Computers in Industry, 98, pp.145~152 (2018), Elsevier BV[DOI]
- Abozar Nasirahmadi, "Automatic scoring of lateral and sternal lying posture in grouped pigs using image processing and Support Vector Machine", Computers and Electronics in Agriculture, 156, pp.475~481 (2019), Elsevier BV[DOI]
- Peter Ahrendt, "Development of a real-time computer vision system for tracking loose-housed pigs", Computers and Electronics in Agriculture, 76(2), pp.169~174 (2011), Elsevier BV[DOI]
- Mohammadamin Kashiha, "The automatic monitoring of pigs water use by cameras", Computers and Electronics in Agriculture, 90, pp.164~169 (2013), Elsevier BV[DOI]
- Ali Alameer, "Automatic recognition of feeding and foraging behaviour in pigs using deep learning", Biosystems Engineering, 197, pp.91~104 (2020), Elsevier BV[DOI]
- Chen Chen, "Recognition of feeding behaviour of pigs and determination of feeding time of each pig by a video-based deep learning method", Computers and Electronics in Agriculture, 176, pp.105642~ (2020), Elsevier BV[DOI]
- "Yolov3: an incremental improvement" (2018)[URL]
- "Real-time object detection method based on improved YOLOv4-tiny" (2020)[URL]
- "Yolov4: optimal speed and accuracy of object detection" (2020)[URL]
- Chae Jung-woo, "Identifying the Mating Posture of Cattle Using Deep Learning-Based Object Detection with Networks of Various Settings", Journal of Electrical Engineering & Technology, 16(3), pp.1685~1692 (2021), 대한전기학회[DOI]
- Kaiming He, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), pp.1904~1916 (2015), Institute of Electrical and Electronics Engineers (IEEE)[DOI]