RESUMO
Optimizing the breeding techniques and increasing the hatching rate of Andrias davidianus offspring necessitates a thorough understanding of its parental care behaviors. However, A. davidianus' nocturnal and cave-dwelling tendencies pose significant challenges for direct observation. To address this problem, this study constructed a dataset for the parental care behavior of A. davidianus, applied the target detection method to this behavior for the first time, and proposed a detection model for A. davidianus' parental care behavior based on the YOLOv8s algorithm. Firstly, a multi-scale feature fusion convolution (MSConv) is proposed and combined with a C2f module, which significantly enhances the feature extraction capability of the model. Secondly, the large separable kernel attention is introduced into the spatial pyramid pooling fast (SPPF) layer to effectively reduce the interference factors in the complex environment. Thirdly, to address the problem of low quality of captured images, Wise-IoU (WIoU) is used to replace CIoU in the original YOLOv8 to optimize the loss function and improve the model's robustness. The experimental results show that the model achieves 85.7% in the mAP50-95, surpassing the YOLOv8s model by 2.1%. Compared with other mainstream models, the overall performance of our model is much better and can effectively detect the parental care behavior of A. davidianus. Our research method not only offers a reference for the behavior recognition of A. davidianus and other amphibians but also provides a new strategy for the smart breeding of A. davidianus.
RESUMO
The PAE (Posture-Act-Environment) coding system is a behavior coding system that divides the study of animal behavior into postures, actions, and the corresponding environmental factors, and they are coded correspondingly. It determines the analysis dimension to standardize the study of behavior. To investigate the behavior of A. davidianus during the breeding period, as well as their related postures, actions, and required environmental conditions, this study monitored the behavior of four pairs of A. davidianus in a simulated natural breeding pool using an infrared image monitoring system and recorded the changes in water quality during this process using a water quality monitoring system. The process of reproductive behaviors was observed and recorded with the random sampling method and the focal animal sampling method to classify and code the behaviors, and the ethogram of A. davidianus during the breeding period was constructed based on the PAE coding system. The result showed that 10 postures, 33 actions, 11 environments, and 45 behavioral patterns were differentiated and defined, which were classified into 9 categories of behaviors according to the behavioral function. Among these categories, five were distinguished as behaviors unique to the reproductive period, which include sand pushing, showering, courtship, oviposition, and parental care. The remaining four categories were daily behaviors: exercise, feeding, rest, and miscellaneous behaviors. The quantitative data on water quality and habitat factors that had a significant impact on the behavior of A. davidianus, such as water temperature (WT), pH, and dissolved oxygen (DO), were included in the coding framework, which more accurately expresses the environmental conditions and thresholds required for the breeding behavior.