Efficient Aggressive Behavior Recognition of Pigs Based on Temporal Shift Module

Ji, Hengyi; Teng, Guanghui; Yu, Jionghua; Wen, Yi; Deng, Hong‐Wen; Zhuang, Yanrong

doi:10.3390/ani13132078

Cited by 5 publications

(4 citation statements)

References 29 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is evident from the charts that our statistical results differ very little from the manually observed results. The data were preprocessed according to the following procedure: (a) Grouping the tracking results by pig ID (1,2,3,4). (b) Calculating the center-point positions of the bounding boxes for each pig.…”

Section: Discussion On the Application Of Long-term Pig Tracking Algo...mentioning

confidence: 99%

“…Pig tracking is of significant importance in pig farm management. Through the individual localization and tracking of pigs, it is possible to collect data on pig movements, analyze pig behavior, and monitor various pig-related information, to find the abnormal pigs in a timely manner [1,2]. At the same time, the automatic tracking and monitoring of pigs can avoid labor-intensive and error-prone manual management, thereby improving management efficiency [3][4][5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Long-Term Video Tracking Method for Group-Housed Pigs

Yang,

Hui,

Huang

et al. 2024

Animals

View full text Add to dashboard Cite

Pig tracking provides strong support for refined management in pig farms. However, long and continuous multi-pig tracking is still extremely challenging due to occlusion, distortion, and motion blurring in real farming scenarios. This study proposes a long-term video tracking method for group-housed pigs based on improved StrongSORT, which can significantly improve the performance of pig tracking in production scenarios. In addition, this research constructs a 24 h pig tracking video dataset, providing a basis for exploring the effectiveness of long-term tracking algorithms. For object detection, a lightweight pig detection network, YOLO v7-tiny_Pig, improved based on YOLO v7-tiny, is proposed to reduce model parameters and improve detection speed. To address the target association problem, the trajectory management method of StrongSORT is optimized according to the characteristics of the pig tracking task to reduce the tracking identity (ID) switching and improve the stability of the algorithm. The experimental results show that YOLO v7-tiny_Pig ensures detection applicability while reducing parameters by 36.7% compared to YOLO v7-tiny and achieving an average video detection speed of 435 frames per second. In terms of pig tracking, Higher-Order Tracking Accuracy (HOTA), Multi-Object Tracking Accuracy (MOTP), and Identification F1 (IDF1) scores reach 83.16%, 97.6%, and 91.42%, respectively. Compared with the original StrongSORT algorithm, HOTA and IDF1 are improved by 6.19% and 10.89%, respectively, and Identity Switch (IDSW) is reduced by 69%. Our algorithm can achieve the continuous tracking of pigs in real scenarios for up to 24 h. This method provides technical support for non-contact pig automatic monitoring.

show abstract

Section: Discussion On the Application Of Long-term Pig Tracking Algo...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Long-Term Video Tracking Method for Group-Housed Pigs

Yang,

Hui,

Huang

et al. 2024

Animals

View full text Add to dashboard Cite

show abstract

“…To recognize the aggressive behavior of group-housed pigs, Gao et al [12] presented a hybrid model combining CNN and Gated Recurrent Unit (GRU) to extract behavior features, and a specific spatiotemporal attention mechanism was added into the model to better classify the behaviors. Ji et al [28] utilized a temporal shift module inserted into four different CNN networks to automatically recognize pig behaviors. The whole model was efficient, without extra parameters and complexity.…”

Section: Applications Of Computer Vision Technologies In Pig Farmingmentioning

confidence: 99%

Pig Movement Estimation by Integrating Optical Flow with a Multi-Object Tracking Model

Zhou,

Chung,

Kakar

et al. 2023

Sensors

View full text Add to dashboard Cite

Pig husbandry constitutes a significant segment within the broader framework of livestock farming, with porcine well-being emerging as a paramount concern due to its direct implications on pig breeding and production. An easily observable proxy for assessing the health of pigs lies in their daily patterns of movement. The daily movement patterns of pigs can be used as an indicator of their health, in which more active pigs are usually healthier than those who are not active, providing farmers with knowledge of identifying pigs’ health state before they become sick or their condition becomes life-threatening. However, the conventional means of estimating pig mobility largely rely on manual observations by farmers, which is impractical in the context of contemporary centralized and extensive pig farming operations. In response to these challenges, multi-object tracking and pig behavior methods are adopted to monitor pig health and welfare closely. Regrettably, these existing methods frequently fall short of providing precise and quantified measurements of movement distance, thereby yielding a rudimentary metric for assessing pig health. This paper proposes a novel approach that integrates optical flow and a multi-object tracking algorithm to more accurately gauge pig movement based on both qualitative and quantitative analyses of the shortcomings of solely relying on tracking algorithms. The optical flow records accurate movement between two consecutive frames and the multi-object tracking algorithm offers individual tracks for each pig. By combining optical flow and the tracking algorithm, our approach can accurately estimate each pig’s movement. Moreover, the incorporation of optical flow affords the capacity to discern partial movements, such as instances where only the pig’s head is in motion while the remainder of its body remains stationary. The experimental results show that the proposed method has superiority over the method of solely using tracking results, i.e., bounding boxes. The reason is that the movement calculated based on bounding boxes is easily affected by the size fluctuation while the optical flow data can avoid these drawbacks and even provide more fine-grained motion information. The virtues inherent in the proposed method culminate in the provision of more accurate and comprehensive information, thus enhancing the efficacy of decision-making and management processes within the realm of pig farming.

show abstract

“…Such behavior typically occurs after mixing, with the most frequent instances of aggression occurring during the first few hours after mixing [ 1 ]. Aggressive behavior in pigs commonly results in physical injuries and skin lesions, and in extreme cases, a bacterial infection of the wound could cause the death of the pigs and increase treatment costs [ 2 , 3 ]. Studies on pig aggressive behavior indicate that such behavior has a heritability of 0.3 to 0.4 [ 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

A Functional Single Nucleotide Polymorphism in the 3′ Untranslated Region of the Porcine JARID2 Gene Is Associated with Aggressive Behavior of Weaned Pigs after Mixing

Yang,

Zhang,

Chao

et al. 2023

IJMS

View full text Add to dashboard Cite

In pig production, pigs often show more aggressive behavior after mixing, which adversely affects animal welfare and growth performance. The Jumonji and structural domain-rich AT interaction domain 2 (JARID2) gene plays an important role in neurodevelopment in mice and various psychiatric disorders in humans. The JARID2 gene may impact the aggressive behavior of pigs. By observing the behavior of 500 weaned pigs during the first 72 h after mixing, the ear tissue samples of the 12 most aggressive and 12 least aggressive pigs were selected for DNA resequencing based on the intensity of their aggressive behavior. Large group correlation analysis indicated that the rs3262221458 site located in the 3′-UTR region of the porcine JARID2 gene has a strong relationship with the aggressive behavior of weaned pigs. Pigs with the mutant TT genotype of rs3262221458 have more aggressive behavior than those pigs with the GG and GT genotypes. The dual luciferase assay indicated that the luciferase activity of the plasmids containing the G allele of rs326221458 was significantly less than that of plasmids containing the T allele of rs326221458 and control groups. The binding ability of miR-9828-3p to sequences containing the T allele was less than that of sequences containing the G allele. The overexpression of miR-9828-3p in porcine neuroglial cells (PNGCs) and PK15 cells significantly decreased the mRNA and protein levels of the JARID2 gene. In addition, miR-9828-3p inhibited the proliferation of PNGCs. After inhibiting miR-9828-3p, the mRNA and protein expression levels of JARID2 increased, and the proliferation of PNGCs showed an opposite trend to the cells that forced the expression of miR-9828-3p. In addition, interference with the JARID2 gene by siRNA can effectively inhibit the proliferation of PNGCs. In summary, we found that the rs326221458 locus regulates the expression of the JARID2 gene by affecting the binding of miR-9828-3p and the JARID2 gene, thereby affecting the aggressive behavior of weaned pigs after mixing.

show abstract

Efficient Aggressive Behavior Recognition of Pigs Based on Temporal Shift Module

Cited by 5 publications

References 29 publications

A Long-Term Video Tracking Method for Group-Housed Pigs

A Long-Term Video Tracking Method for Group-Housed Pigs

Pig Movement Estimation by Integrating Optical Flow with a Multi-Object Tracking Model

A Functional Single Nucleotide Polymorphism in the 3′ Untranslated Region of the Porcine JARID2 Gene Is Associated with Aggressive Behavior of Weaned Pigs after Mixing

Contact Info

Product

Resources

About