Target detection method based on semantic feature consistency supervision pyramid network
A semantic feature and target detection technology, applied in the field of computer vision, can solve the problems of inconsistent semantic feature fusion and low detection accuracy, and achieve the effect of improving detection accuracy, improving semantic information, and enhancing consistency
Active Publication Date: 2021-03-19
XIDIAN UNIV
View PDF13 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose an image target detection method based on a semantic feature consistency pyramid network, which is used to solve the problems existing in the prior art due to the multi-scale semantics of the target in the process of image or video target detection. The technical problem of low detection accuracy caused by inconsistency in feature fusion
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
[0028] Below in conjunction with accompanying drawing and specific embodiment, the present invention is described in further detail:
[0029] refer to figure 1 , the present invention comprises the following steps:
[0030] Step 1) Obtain training sample set K and test sample set V:
[0031] Obtain multiple RGB three-channel images with a size of W×H in the target detection data set, and use N RGB three-channel images with target category labels and target position coordinates as the training sample set K={k 1 ,k 2 ,...,k n ,...,k N}, Take M pieces of RGB three-channel images with target category labels and target position coordinates as the test sample set V={v 1 ,v 2 ,...,v m ,...,v M}, Among them, N≥100000, M≥5000, k n Indicates that the nth target category label is The coordinates of the target location are The training samples of v m Indicates that the mth target category label is The coordinates of the target location are The test samples, the train...
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 an image target detection method based on a semantic feature consistency pyramid network, which is used for solving the technical problem of relatively low detection precision caused by inconsistency of target multi-scale semantic features in an image or video target detection process in the prior art. The method comprises the steps of acquiring a training sample set K and atest sample set V; constructing an image target detection network S based on a semantic feature consistency pyramid network P; performing iterative training on the image target detection network S based on the semantic feature consistency pyramid network P; obtaining target detection recognition results. The method is plug-and-play in a mainstream RCNN target detection network, solves the technical problem of low detection precision caused by inconsistent semantic feature fusion of different layers, and improves the detection precision.
Description
technical field [0001] The invention belongs to the technical field of computer vision in image processing, and relates to a target detection method based on deep learning, in particular to a target detection method based on semantic feature consistency supervision pyramid network, which can be used for targets in RGB optical images and videos detection. Background technique [0002] With the development of computer technology and the advent of the era of artificial intelligence, the technology in the field of computer vision has advanced by leaps and bounds, and the target detection technology has also achieved breakthrough results. Object detection is one of the core problems in the field of computer vision. Its task is to find out all the objects of interest in the image and determine their position and size. The detection of important targets such as face detection, pedestrian detection, and vehicle detection has been widely studied. Not only that, target detection in s...
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 IPC IPC(8): G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V10/267G06N3/045G06F18/253G06F18/214
Inventor 何立火柯俊杰甘海林韩博高新波唐杰浩路文蔡虹霞
Owner XIDIAN UNIV