Action Recognition Using a Spatial-Temporal Network for Wild Felines

SIMPLE SUMMARY: Many wild felines are on the verge of extinction, and the monitoring of wildlife diversity is particularly important. Using surveillance videos of wild felines to monitor their behaviors has an auxiliary effect on the protection of wild felines. Through the actions of wild felines, such as standing, galloping, ambling, etc., their behaviors can be inferred and judged. Therefore, research on the action recognition of wild felines is of great significance to wildlife protection. The currently available methods are all aimed at experimental animals and design-specific feature descriptors for specific animals (such as color, texture, shape, edge, etc.), thus lacking flexibility and versatility. The proposed state-of-the-art algorithm using spatial-temporal networks combines skeleton features with outline features to automatically recognize the actions of wild felines. This model will be suitable for researchers of wild felines. ABSTRACT: Behavior analysis of wild felines has significance for the protection of a grassland ecological environment. Compared with human action recognition, fewer researchers have focused on feline behavior analysis. This paper proposes a novel two-stream architecture that incorporates spatial and temporal networks for wild feline action recognition. The spatial portion outlines the object region extracted by Mask region-based convolutional neural network (R-CNN) and builds a Tiny Visual Geometry Group (VGG) network for static action recognition. Compared with VGG16, the Tiny VGG network can reduce the number of network parameters and avoid overfitting. The temporal part presents a novel skeleton-based action recognition model based on the bending angle fluctuation amplitude of the knee joints in a video clip. Due to its temporal features, the model can effectively distinguish between different upright actions, such as standing, ambling, and galloping, particularly when the felines are occluded by objects such as plants, fallen trees, and so on. The experimental results showed that the proposed two-stream network model can effectively outline the wild feline targets in captured images and can significantly improve the performance of wild feline action recognition due to its spatial and temporal features.