Method for key point detection and detection network training, electronic device and storage medium
A technology of network training and detection method, applied in the field of neural network, can solve the problems of abnormal shape of key points, out of shape range, inaccurate detection of key points, etc., to achieve the effect of improving accuracy, reducing difficulty and improving stability
Active Publication Date: 2021-08-17
合肥的卢深视科技有限公司
View PDF6 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] However, the inventor found that the traditional way of directly extracting mechanical key points from the image may lead to abnormal shapes of key points, which exceed the original shape range of the object to be detected, resulting in inaccurate key point detection
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
[0023] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, various implementation modes of the present invention will be described in detail below in conjunction with the accompanying drawings. However, those of ordinary skill in the art can understand that, in each implementation manner of the present invention, many technical details are provided for readers to better understand the present application. However, even without these technical details and various changes and modifications based on the following implementation modes, the technical solution claimed in this application can also be realized.
[0024] The division of the following embodiments is for the convenience of description, and should not constitute any limitation to the specific implementation of the present invention, and the various embodiments can be combined and referred to each other on the premise of no contradiction.
[0025] Embodim...
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 relates to the field of neural networks, and discloses a method for key point detection and detection network training, electronic equipment and a storage medium. In the present invention, a preset key point template, a training sample image, and a sample key point corresponding to the training sample image are obtained, and the key point template is the shape standard of the output result of the pre-built initial key point detection network; through the An initial key point detection network, combining the training sample image and the key point template to obtain a training detection key point; according to the training detection key point and the sample key point, iteratively train the initial key point detection network, and The initial key point detection network satisfying the preset iteration condition is used as the key point detection network after training. The key point template is provided as a priori to ensure the normal shape of key points and improve the accuracy of key point detection.
Description
technical field [0001] The embodiments of the present invention relate to the field of neural networks, and in particular to key point detection and detection network training methods, electronic equipment and storage media. Background technique [0002] The traditional method of detecting key points of an image usually uses a convolutional neural network to combine the image with a heat map (HeatMap) to obtain the key points corresponding to the image. Among them, HeatMap can use color changes to reflect the data information in the two-dimensional matrix or table, and it can intuitively express the size of the data value with the defined color depth. The data is often clustered according to the abundance similarity between species or samples, and the clustered data is displayed on the HeatMap map, and high-abundance and low-abundance species can be aggregated in blocks, and the color gradient and similarity can be used to identify Reflect the similarity and difference of t...
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 Patents(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/171G06V40/172G06V10/44G06N3/047G06N3/045G06F18/23G06F18/241G06F18/2415
Inventor 保长存朱海涛陈智超江坤户磊
Owner 合肥的卢深视科技有限公司