Attitude estimation model training method, attitude estimation method, attitude estimation device and electronic equipment
A pose estimation and model training technology, applied in the computer field, can solve the problem of low accuracy of pose estimation results, and achieve the effect of avoiding semantic confusion, improving accuracy, and ensuring processing efficiency.
Pending Publication Date: 2021-07-09
MEGVII BEIJINGTECH CO LTD
View PDF0 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The embodiment of the present application proposes an attitude estimation model training method, an attitude estimation method, a device, and electronic equipment to solve the technical problem in the prior art that the accuracy of the attitude estimation result is low in order to ensure processing efficiency
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
[0021] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.
[0022] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.
[0023] Please refer to figure 1 , which shows a process 100 of an embodiment of a pose estimation model training method according to the present application. The execution subject of the attitude estimation model training method may be various electronic devices or processo...
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 embodiment of the invention discloses an attitude estimation model training method, an attitude estimation method, an attitude estimation device and electronic equipment. The method comprises the following steps: acquiring a sample image and an initial thermodynamic diagram of joint points in the sample image; inputting the sample image into a to-be-trained attitude estimation model to obtain a scale feature map, a prediction thermodynamic diagram and an embedded label of a joint point in the sample image; adjusting the initial thermodynamic diagram based on the scale feature map to obtain a target thermodynamic diagram; and on the basis of the target thermodynamic diagram, the prediction thermodynamic diagram and the embedded tag, updating parameters of a to-be-trained attitude estimation model. According to the embodiment, the precision of the attitude estimation result is improved while the processing efficiency is ensured.
Description
technical field [0001] The embodiments of the present application relate to the field of computer technology, and in particular to a pose estimation model training method, pose estimation method, device, and electronic equipment. Background technique [0002] Pose estimation is an important branch of computer vision, which is used to locate various joint points of objects, such as elbows, wrists, knees, etc. [0003] In the prior art, by detecting each object in an image, scaling each object to a fixed size, and then performing joint point detection, so as to obtain the pose of each object. This method needs to detect the object, and the calculation amount is large, so the processing efficiency is low. Another method in the prior art can detect all joint points through the same function or algorithm, and determine the object to which each joint point belongs, so as to obtain the pose of each object. This method cannot distinguish between objects of different scales, so the...
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): G06K9/00G06K9/46G06K9/62
CPCG06V40/10G06V10/40G06F18/214
Inventor 罗正雄王志成周而进
Owner MEGVII BEIJINGTECH CO LTD