Body part detection method and device based on artificial intelligence, and electronic equipment
A technology of body parts and artificial intelligence, applied in the field of computer vision and artificial intelligence, can solve the problems of poor generalization and robustness, high cost, time-consuming and laborious, etc., to achieve good robustness, save labor costs, and accurate detection results Effect
Active Publication Date: 2022-01-11
北京医准智能科技有限公司
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The images taken by different models of the same object have different image data. Traditional computer vision detection methods need to manually set specific parameters for different data when detecting, and the generalization and robustness are poor.
[0004] (2) Before using the machine learning method for detection, a large number of training labels need to be manually marked in advance, which is time-consuming, laborious and costly
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] In order to make the purpose, features, and advantages of the application more obvious and understandable, the technical solutions in the embodiments of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the application. Obviously, the described The embodiments are only some of the embodiments of the present application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.
[0040] The body part detection method of the embodiment of the present application uses computer vision methods to obtain the first body part sample and the second body part sample in the target image sample, uses the target image sample as a training label to train the body detection model, and finally uses the training to complete A body detection model detects ...
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
Login to View More Abstract
The invention discloses a body part detection method and device based on artificial intelligence and electronic equipment, and the method comprises the steps: carrying out the image segmentation of an initial image, and obtaining a target image; processing the target image to obtain a mask for indicating the body part; determining a first body part in the target image by using the mask; and processing the image of the first body part to obtain a second body part in the target image, wherein the first body part and the second body part are determined based on a body detection model. According to the method, the body detection model is trained through the sample marked with the body part label, and finally the body part in the medical image is detected by using the trained body detection model.
Description
technical field [0001] The present application relates to the technical fields of computer vision and artificial intelligence, and in particular to an artificial intelligence-based body part detection method, device and electronic equipment. Background technique [0002] At present, the position of a certain part of the body in the image is mainly detected by traditional computer vision and machine learning methods, but these two methods have the following defects: [0003] (1) Generalization mainly describes the prediction ability of the model for unknown data, that is, it can also give appropriate output for data other than data with the same law; robustness refers to the perturbation of the control system under certain (structure, size) parameters , while maintaining certain other performance characteristics. The images taken by different models of the same object have different image data. Traditional computer vision detection methods need to manually set specific param...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/12G06T7/194
CPCG06T7/0012G06T7/12G06T7/194G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30068G06T2207/30096
Inventor 王雅倩王子腾胡阳王立威丁佳吕晨翀
Owner 北京医准智能科技有限公司