DWEC-YOLO: A Multi-Behavior Detection Model for Group-Housed Pigs.
- 1College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China.
Abstract
In large-scale pig farming systems, high visual similarity among pigs, complex posture variations, and frequent interactions between individuals pose significant challenges to vision-based multi-behavior detection. To overcome these limitations, this study proposes an improved YOLO11-based pig behavior detection model, termed DWEC-YOLO, for recognizing normal behaviors (standing, lying, sitting, and feeding) and aggressive behaviors (fighting, ear biting, and tail biting). First, the C3k2-DySnake module is embedded within the backbone architecture, enabling more effective extraction of fine-grained visual details. Second, an EUCB-SC module is employed during feature aggregation and works jointly with the CoordAtt mechanism to strengthen multi-scale feature representations, thereby enhancing the network's sensitivity toward critical interaction areas. In addition, Wise-ShapeIoU is adopted as the bounding-box regression loss to refine localization optimization and produce more accurate object predictions. Comprehensive experiments show that DWEC-YOLO surpasses several representative lightweight detectors, including YOLOv5n, YOLOv7-Tiny, YOLOv8n, YOLOv10n, and YOLOv12n, in detection effectiveness. Relative to the original YOLO11 architecture, DWEC-YOLO improves precision, recall, and [email protected] by 4.28, 4.46, and 2.65 percentage points, respectively, achieving 96.17%, 95.25%, and 97.57%. These outcomes demonstrate that DWEC-YOLO substantially enhances multi-behavior detection in group-housed environments, serving as a dependable tool for automated monitoring in smart livestock farming.
Related
- A modular open-source computer vision pipeline enables individual-level behavior analysis of group-housed pigs
- eeeHive: a new HF RFID-based automated behavioral monitoring system enabling high spatiotemporal resolution tracking of group-housed animals.
- Data paper: Cross-species datasets on individual associative learning to regulate access to shared resources in group-housed gestating sows and lactating dairy cows
- Exploring piling behavior in aviary-housed laying hens in response to age, management practices, and social influences
- An exploratory animal-economics study to evaluate the motivation of group-housed rabbit does to access different secluded areas
BibTeX
@article{chen2026dwecyolo,
title = {{DWEC-YOLO: A Multi-Behavior Detection Model for Group-Housed Pigs.}},
author = {Yan Chen and Jiehao Wu and Yingjie Kuang and Qiumei Yang},
journal = {Animals : an open access journal from MDPI},
year = {2026},
month = oct,
doi = {10.3390/ani16193125},
url = {https://europepmc.org/article/MED/42883094},
note = {CC BY},
}
RIS
TY - JOUR
TI - DWEC-YOLO: A Multi-Behavior Detection Model for Group-Housed Pigs.
AU - Yan Chen
AU - Jiehao Wu
AU - Yingjie Kuang
AU - Qiumei Yang
PY - 2026
DA - 2026/10/05
JO - Animals : an open access journal from MDPI
DO - 10.3390/ani16193125
UR - https://europepmc.org/article/MED/42883094
AB - In large-scale pig farming systems, high visual similarity among pigs, complex posture variations, and frequent interactions between individuals pose significant challenges to vision-based multi-behavior detection. To overcome these limitations, this study proposes an improved YOLO11-based pig behavior detection model, termed DWEC-YOLO, for recognizing normal behaviors (standing, lying, sitting, and feeding) and aggressive behaviors (fighting, ear biting, and tail biting). First, the C3k2-DySnake module is embedded within the backbone architecture, enabling more effective extraction of fine-grained visual details. Second, an EUCB-SC module is employed during feature aggregation and works jointly with the CoordAtt mechanism to strengthen multi-scale feature representations, thereby enhancing the network's sensitivity toward critical interaction areas. In addition, Wise-ShapeIoU is adopted as the bounding-box regression loss to refine localization optimization and produce more accurate object predictions. Comprehensive experiments show that DWEC-YOLO surpasses several representative lightweight detectors, including YOLOv5n, YOLOv7-Tiny, YOLOv8n, YOLOv10n, and YOLOv12n, in detection effectiveness. Relative to the original YOLO11 architecture, DWEC-YOLO improves precision, recall, and [email protected] by 4.28, 4.46, and 2.65 percentage points, respectively, achieving 96.17%, 95.25%, and 97.57%. These outcomes demonstrate that DWEC-YOLO substantially enhances multi-behavior detection in group-housed environments, serving as a dependable tool for automated monitoring in smart livestock farming.
SN - 2076-2615
ER -