Human body key point detection method based on deep learning

Abstract

The invention discloses a human body key point detection method based on deep learning. The method comprises the steps of data acquisition, network construction, model training and evaluation, optimal model prediction and the like. According to the method, the ResNet50 network is improved, an expanded convolution residual network is provided, and a two-stage expanded convolution residual network is adopted to construct a human body key point detection network. During model training, feature extraction is performed on training data by the first-stage network, prediction is performed by using four channels, loss of all key points in a prediction result are calculated, and the loss is returned to adjust network parameters; the input feature map, the output feature map and the prediction result of the first-stage network are added by adopting an intermediate stage, and are transmitted to a second stage; and feature extraction is performed by the second-level network, prediction is performed on the finally obtained feature map after two-layer transposition, key point loss of a prediction result is calculated, the key point loss is sorted according to a descending order, and the first K * B losses are selected to return and adjust network parameters. An optimal training model is selected to predict human body key points of the to-be-detected image, the precision is high, and the practicability is good.

Description

technical field [0001] The invention belongs to the field of computer vision technology, and has wide application requirements in the fields of public security, somatosensory game entertainment, human-computer interaction, standard action analysis, etc., and is precisely a human body key point detection method based on deep learning. Background technique [0002] Human body key point detection is an important topic in the field of computer vision. The main task is to detect human body key points (usually some joint points or parts) in a given image, input an image containing pedestrians, and output the image Including all key point coordinates of all people, the current pose can be obtained from these coordinate information. Due to the different scales of each pedestrian, the interaction between pedestrians is also very complicated, such as mutual occlusion or occlusion by other objects, as well as background and clothing interference, complex and variable human body movemen...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the shortcomings of traditional detection methods that are difficult to balance accuracy and complexity, the present invention proposes a human body key point detection method based on deep learning, and designs a new expanded convolution residual network to build a human body key point detection network. High detection accuracy can be achieved without using a large network, and the mechanism is robust, so this method has high practical value

Images