Posture Detection of Individual Pigs Based on Lightweight Convolution Neural Networks and Efficient Channel-Wise Attention

Abstract

In this paper, a lightweight channel-wise attention model is proposed for the real-time detection of five representative pig postures: standing, lying on the belly, lying on the side, sitting, and mounting. An optimized compressed block with symmetrical structure is proposed based on model structure and parameter statistics, and the efficient channel attention modules are considered as a channel-wise mechanism to improve the model architecture.The results show that the algorithm’s average precision in detecting standing, lying on the belly, lying on the side, sitting, and mounting is 97.7%, 95.2%, 95.7%, 87.5%, and 84.1%, respectively, and the speed of inference is around 63 ms (CPU = i7, RAM = 8G) per postures image. Compared with state-of-the-art models (ResNet50, Darknet53, CSPDarknet53, MobileNetV3-Large, and MobileNetV3-Small), the proposed model has fewer model parameters and lower computation complexity. The statistical results of the postures (with continuous 24 h monitoring) show that some pigs will eat in the early morning, and the peak of the pig’s feeding appears after the input of new feed, which reflects the health of the pig herd for farmers.

Machine Learning-Based Sensor Data Fusion for Animal Monitoring: Scoping Review

“…This review includes articles with Qualsyst score percentages ≥60%. As a result, 23 articles were included for in-depth analysis [ 7 , 13 , 14 , 15 , 16 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 ]; the remaining 5 articles were excluded since their score was below the acceptance percentage [ 45 , 46 , 47 , 48 , 49 ]. The flow diagram of the review phases’ is shown in Figure 2 .…”

“…The first study identified dates back to 2016 [ 39 ], and 95.7% (22/23) of the studies were conducted in the last five years (2018–2022). Most of the 23 studies were conducted in Europe (11/23, 47.8%) [ 7 , 15 , 16 , 29 , 30 , 32 , 33 , 38 , 39 , 40 , 41 ] followed by Asia (8/23, 34.7%) [ 13 , 27 , 34 , 35 , 36 , 42 , 43 , 44 ], and Oceania (3/23, 13%) [ 31 , 37 , 44 ]. An overview of the results is presented in Table 2 , and a detailed analysis of the selected studies are displayed in Table 3 , Table 4 and Table 5 , according to sensor fusion level.…”

“…Among the articles, a subset of them (2/23, 8.6%) employed multimodal switching as a method for fusion, while another subset (2/23, 8.6%) utilized mixing. Additionally, specific fusion methods were identified, including Cross-modality interaction [ 36 ], Dual-Stream Convolutional Neural Networks [ 43 ], Path aggregation network [ 35 ], Cascade and Feedback Fusion [ 34 ], KNN-RF Weighted Fusion Model [ 42 ], and EKF [ 44 ]. Each method was mentioned once, representing 4.35% of the total.…”

Recent Advances in Artificial Intelligence Sensors

“…With the significant advancement of Internet of things (IoT) and artificial intelligence (AI), Fourth Industrial Revolution DOI: 10.1002/adsr.202200072 (Industry 4.0) is revolutionizing the way that companies upgrade and transform manufacturing technologies to realize smart digital factories. [1][2][3][4][5] Automatic machines and robotics play a vital role in our daily lives and are essential components for manufacturers, which leverage AI to finish cloud computing and data analytics in their production facilities and throughout their operations. [6][7][8][9] The fast development of AI started from 2012 benefiting from the improvement of computation power and speed, in which graphics processing unit (GPU) accelerates the design of various deep learning algorithms.…”

Sow Farrowing Early Warning and Supervision for Embedded Board Implementations

“…Although deep-learning algorithms [ 11 , 12 , 13 ] have developed rapidly, they require a large number of calculations and numerous parameters, and models can normally only run on high-performance workstations equipped with graphics processing units (GPUs). A computer-vision technology based on lightweight deep learning [ 14 , 15 , 16 ] has emerged owing to cost considerations. This paper proposes a lightweight deep learning-based approach for the early warning and supervision of sow behaviors preceding and during farrowing.…”