High Speed and Accuracy of Animation 3D Pose Recognition Based on an Improved Deep Convolution Neural Network

Abstract

Pose recognition in character animations is an important avenue of research in computer graphics. However, the current use of traditional artificial intelligence algorithms to recognize animation gestures faces hurdles such as low accuracy and speed. Therefore, to overcome the above problems, this paper proposes a real-time 3D pose recognition system, which includes both facial and body poses, based on deep convolutional neural networks and further designs a single-purpose 3D pose estimation system. First, we transformed the human pose extracted from the input image to an abstract pose data structure. Subsequently, we generated the required character animation at runtime based on the transformed dataset. This challenges the conventional concept of monocular 3D pose estimation, which is extremely difficult to achieve. It can also achieve real-time running speed at a resolution of 384 fps. The proposed method was used to identify multiple-character animation using multiple datasets (Microsoft COCO 2014, CMU Panoptic, Human3.6M, and JTA). The results indicated that the improved algorithm improved the recognition accuracy and performance by approximately 3.5% and 8–10 times, respectively, which is significantly superior to other classic algorithms. Furthermore, we tested the proposed system on multiple pose-recognition datasets. The 3D attitude estimation system speed can reach 24 fps with an error of 100 mm, which is considerably less than that of the 2D attitude estimation system with a speed of 60 fps. The pose recognition based on deep learning proposed in this study yielded surprisingly superior performance, proving that the use of deep-learning technology for image recognition has great potential.

Object detection in optical imaging of the Internet of Things based on deep learning

“… Zhong et al (2023) advocated the fusion of real-time monocular 3D detection networks and CNNs to overcome temporal dependencies, resulting in improved accuracy for target detection. Ding & Li (2023) highlighted the advantages of DL-based target recognition, who demonstrateed superior performance compared to traditional AI algorithms. Their findings underscore DL technology’s potential for enhancing image recognition.…”

Application of Graph Neural Network and Virtual Reality Based on the Concept of Sustainable Design

“…Character animation plays a crucial role in animation scene design, and character pose recognition is an indispensable part of animators in constructing vivid and realistic animation scenes. Ding and Li [6] proposed a real-time 3D pose recognition system based on deep convolutional neural networks. This data structure not only includes the body posture of the character but also details such as facial expressions, providing rich materials for subsequent animation generation.…”