Head posture estimation method combined with YOLO-MobilenetV3 face detection

A technology for head posture and face detection, applied in neural learning methods, computing, computer parts, etc., can solve the problems of large memory occupation, long training time, large amount of calculation, etc., to achieve easy practical application, improve detection Accurate, Fast and Accurate Estimation of Effects

Pending Publication Date: 2021-11-26
JILIN UNIV FIRST HOSPITAL
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, YOLOV3 has a faster detection speed. It mainly uses darknet53 as the basic backbone network structure for feature extraction. This structure has too many parameters and a large amount of calculation, resulting in a long training time and a large memory during the training process.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Head posture estimation method combined with YOLO-MobilenetV3 face detection
  • Head posture estimation method combined with YOLO-MobilenetV3 face detection
  • Head posture estimation method combined with YOLO-MobilenetV3 face detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Include the following steps:

[0055] (1) Improve the network structure of YOLOV3.

[0056] The overall structure of the model is shown in Figure 2(a). In step 1.1, the original image is processed to obtain an input image with a resolution of 416*416, and then the input image is passed through the backbone feature extraction network. This part will use the MobileNetV3 structure to replace the original YOLOV3. The darknet53 structure realizes the light weight of the model; step 1.2, in order to ensure the detection accuracy, the final segment of the backbone feature extraction network is fused with the spatial pyramid pooling module, so that the model can obtain richer global context feature information; step 1.3, the prediction part is included in the feature Extract the backbone network part to lead to three different scales, perform multi-layer feature learning and prediction, and finally connect to the output part to output the prediction result; step 1.4, modify the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a head posture estimation method combined with YOLO-MobilenetV3 face detection, belonging to the field of machine vision image processing. The method comprises the following steps: constructing a face and face key feature point detection module, improving an original YOLOV3 loss function, preprocessing an image containing a head posture, training an improved YOLOV3 detection model, inputting a test image into the trained model, and calculating an Euler angle and estimating the head posture through combination with a PnP algorithm. The method has the beneficial effects that the MobileNetV3 structure is used for replacing the darknet53 structure in an original YOLOV3 to realize light weight of the model; a spatial pyramid pooling module is adopted to improve the acquisition of global semantics of the image by the model, and the spatial position information of a target is processed more effectively, so detection precision is improved; and a YOLOV3 output layer and the loss function are improved, so the model can detect key points of face, practical application is easy, and the head posture can be estimated more quickly and accurately.

Description

technical field [0001] The invention belongs to the field of machine vision image processing, relates to a single frame detection technology, in particular to a head posture estimation method based on YOLO-MobilenetV3 detection. Background technique [0002] In recent years, artificial intelligence technology has developed rapidly, and people's demand for information security and intelligence has gradually increased. Head pose estimation, as a part of biometric analysis, is an intersecting field between pose analysis and face recognition. research value and significance. Head posture recognition can be used in the driving system to detect whether there is fatigue driving by estimating the driver's head posture; Remotely operate mechanical work in the environment; it can also be used in smart classrooms and virtual games. [0003] For humans, it is a common ability to directly observe and estimate the posture of the human head. However, it is not easy to use a computer to o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 冯俊燕贾飞勇董涵宇陈小林万园园
Owner JILIN UNIV FIRST HOSPITAL
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap