Target detection method and device based on cascade regression
A target detection and cascade regression technology, applied in the field of image processing, can solve the problems of poor detection accuracy and inconspicuous small target features, and achieve the effect of improving accuracy
Pending Publication Date: 2022-03-01
际络科技(上海)有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention provides a target detection method and device based on cascaded regression, which is used to solve the defect that the characteristics of small targets are not obvious in the prior art so that the detection accuracy is poor. Accuracy of object 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
[0022] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention , but not all examples. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0023] figure 1 A schematic flow chart of a cascaded regression-based target detection method is shown, the method comprising:
[0024] S11, acquiring a picture to be detected, the picture to be detected includes a target picture and a target frame corresponding to the target picture, and the target frame includes a first target frame and a second target frame whose number of pixels is great...
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 provides a target detection method and device based on cascade regression, and the method comprises the steps: obtaining a to-be-detected picture, the to-be-detected picture comprises a target picture and a target frame corresponding to the target picture, and the target frame comprises a first target frame and a second target frame of which the number of pixel points is greater than that of the first target frame; performing scale transformation on the first target frame according to a preset proportion to obtain a third target frame with the scale size of the second target frame; and obtaining a candidate target frame according to the third target frame and the second target frame, and inputting the to-be-detected picture and the candidate target frame into a specific target detection model to obtain a target prediction result output by the specific target detection model. Scale transformation is carried out on the first target frame according to the size of the second target frame so as to amplify the feature expression ability of the first target; and the amplified first target is detected by using a specific target detection model, and a target frame regression mode from large to small is adopted, so that the small target detection precision is greatly improved.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to a cascade regression-based target detection method and device. Background technique [0002] In the target detection task based on deep learning, especially in the face detection task widely used in actual scenes, it is very difficult to detect small targets and small faces, and it faces many technical challenges. Insufficient learning ability, so that small target detection and recognition tasks have not been greatly improved in recent years. [0003] At present, most small target detection methods use methods such as increasing input, feature fusion of deep and shallow featuremaps, attention mechanisms, and small target data oversampling to improve small target detection accuracy. However, due to the low sample hits of small targets in detection tasks, and fewer pixels, the features are not obvious. Therefore, it is easy to cause small target features to be lo...
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): G06V10/25G06V10/766G06V10/774G06V10/771G06V10/82G06N3/08G06K9/62
CPCG06N3/08G06F18/211G06F18/2148
Inventor 李梦宇程新景杨睿刚
Owner 际络科技(上海)有限公司