Human body gesture identification method based on depth convolution neural network

Abstract

The invention discloses a human body gesture identification method based on a depth convolution neural network, belongs to the technical filed of mode identification and information processing, relates to behavior identification tasks in the aspect of computer vision, and in particular relates to a human body gesture estimation system research and implementation scheme based on the depth convolution neural network. The neural network comprises independent output layers and independent loss functions, wherein the independent output layers and the independent loss functions are designed for positioning human body joints. ILPN consists of an input layer, seven hidden layers and two independent output layers. The hidden layers from the first to the sixth are convolution layers, and are used for feature extraction. The seventh hidden layer (fc7) is a full connection layer. The output layers consist of two independent parts of fc8-x and fc8-y. The fc8-x is used for predicting the x coordinate of a joint. The fc8-y is used for predicting the y coordinate of the joint. When model training is carried out, each output is provided with an independent softmax loss function to guide the learning of a model. The human body gesture identification method has the advantages of simple and fast training, small computation amount and high accuracy.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and information processing, and relates to the behavior recognition task of computer vision, in particular to the research and realization scheme of a human body pose estimation system based on a deep convolutional neural network. Background technique [0002] Human pose estimation refers to the process of locating the positions of human joints or parts of the human body in images. It is a key problem in computer vision and a fundamental technique for image-based action recognition. Human pose estimation can be used in visual surveillance systems, human body segmentation, robot control, somatosensory games and other fields. The difficulty of human pose estimation lies in: the body joints are small and difficult to detect; the body itself is seriously occluded, the appearance changes greatly, and in-plane and out-plane rotations cause large visual changes. The mainstream methods of po...

AI Technical Summary

Problems solved by technology

[0013] In order to overcome the lack of pose estimation accuracy caused by artificial design of image features and spatial models in traditional pose estimation methods, the present invention studies how to obtain higher pose accuracy on the premise of ensuring pose estimation speed

Images