Identifying the Mating Posture of Cattle Using Deep Learning-Based Object Detection with Networks of Various Settings

Chae, Jung-woo; Cho, Hyun-chong

doi:10.1007/s42835-021-00701-z

Cited by 10 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original activation function was the leaky ReLU function, which leads to poor connectivity to the output because there is a distortion at the point where the input is zero. In contrast, the Mish function yields a smooth curve where the input is zero, so it is possible to deliver a stable value to the next layer input [ 23 ]. Fig.…”

Section: Methodsmentioning

confidence: 99%

A deep learning-based approach for feeding behavior recognition of weanling pigs

Kim¹,

Choi²,

Lee³

et al. 2021

J Anim Sci Technol

Self Cite

View full text Add to dashboard Cite

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-leaning-based 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.

show abstract

Section: Methodsmentioning

confidence: 99%

A deep learning-based approach for feeding behavior recognition of weanling pigs

Kim¹,

Choi²,

Lee³

et al. 2021

J Anim Sci Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…The aim of this study was to identify five distinct cattle behaviors: rumination, lactation, calf interaction, cow interaction, and the normal state. However, these behaviors lack specific, conspicuous postures, such as mounting [23]. Some involve actions that cannot be assessed from a single image, such as rumination observable through mouth movement while standing or lying [24].…”

Section: B Video-based Classification Of Cattle Behaviormentioning

confidence: 99%

Video-Based Analysis of Cattle Behaviors: Improved Classification Using FlowEQ Transform

Chae,

Sim,

Lee

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Cattle management plays a crucial role in determining the productivity of livestock farms. With the expansion of large-scale livestock operations, it has become increasingly impractical for livestock managers to rely solely on traditional visual observations to monitor cattle behavior and health. Consequently, the incorporation of automation technology in livestock management is needed. The objective of this study is the automated identification of cattle behavior using deep learning-based algorithms. The study specifically focused on identifying five distinct cattle behaviors closely associated with their management, employing action classification instead of the commonly used object detection. This approach enabled the classification of intricate, repetitive, and slow behaviors that were challenging to detect using previous methods. Additionally, a novel method named FlowEQ transform was introduced, incorporating temporal information into the input data. This enhancement proved instrumental in providing valuable insights for inferring cattle behavior, resulting in an impressive 8% improvement in classification performance and achieving a high accuracy rate of 91.5%. The utilization of action classification and the introduction of the innovative FlowEQ transform mark a significant advancement in automated cattle management. This approach is poised to enhance the efficiency of behavior monitoring on livestock farms.

show abstract

“…Chae et al [9] addressed the challenge of detecting cattle mating postures. Building upon the YOLOv3 framework, they introduced specific upper convolution and upper sampling layers, resulting in a network architecture characterized by enhanced detection accuracy, thereby accomplishing the task of cattle mating posture detection.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Sheep Head Detection and Dynamic Counting Method Based on Neural Network

Wang,

Hu,

Hou

et al. 2023

Animals

View full text Add to dashboard Cite

To achieve rapid and precise target counting, the quality of target detection serves as a pivotal factor. This study introduces the Sheep’s Head-Single Shot MultiBox Detector (SH-SSD) as a solution. Within the network’s backbone, the Triple Attention mechanism is incorporated to enhance the MobileNetV3 backbone, resulting in a significant reduction in network parameters and an improvement in detection speed. The network’s neck is constructed using a combination of the Spatial Pyramid Pooling module and the Triple Attention Bottleneck module. This combination enhances the extraction of semantic information and the preservation of detailed feature map information, with a slight increase in network parameters. The network’s head is established through the Decoupled Head module, optimizing the network’s prediction capabilities. Experimental findings demonstrate that the SH-SSD model attains an impressive average detection accuracy of 96.11%, effectively detecting sheep’s heads within the sample. Notably, SH-SSD exhibits enhancements across various detection metrics, accompanied by a significant reduction in model parameters. Furthermore, when combined with the DeepSort tracking algorithm, it achieves high-precision quantitative statistics. The SH-SSD model, introduced in this paper, showcases commendable performance in sheep’s head detection and offers deployment simplicity, thereby furnishing essential technical support for the advancement of intelligent animal husbandry practices.

show abstract

Identifying the Mating Posture of Cattle Using Deep Learning-Based Object Detection with Networks of Various Settings

Cited by 10 publications

References 13 publications

A deep learning-based approach for feeding behavior recognition of weanling pigs

A deep learning-based approach for feeding behavior recognition of weanling pigs

Video-Based Analysis of Cattle Behaviors: Improved Classification Using FlowEQ Transform

Lightweight Sheep Head Detection and Dynamic Counting Method Based on Neural Network

Contact Info

Product

Resources

About