An adaptive object detection method based on spcnn

A target detection and self-adaptive technology, applied in the field of computer vision, can solve problems such as time-consuming, complex calculation, and poor robustness, and achieve the effect of high efficiency, simple calculation, and improved robustness

Active Publication Date: 2021-06-15
北京博睿维讯科技有限公司 +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For SPCNN, it is necessary to manually set parameters, manually select the optimal output, and the existing methods are complex in calculation, time-consuming and poor in robustness.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An adaptive object detection method based on spcnn
  • An adaptive object detection method based on spcnn
  • An adaptive object detection method based on spcnn

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] A kind of adaptive target detection method based on SPCNN disclosed in this embodiment, its overall process is as attached figure 1 As shown, the specific implementation steps are as follows:

[0051] Step 1: Calculate the image static attribute parameters and some parameters in the SPCNN model.

[0052] After the grayscale preprocessing of the image, the overall grayscale average of the image is calculated, which will be used as the calculation factor of the threshold decay time constant in the SPCNN model.

[0053] Then normalize the image grayscale matrix, calculate the maximum grayscale value of the target pixel area, and use the Otsu method to find the best histogram threshold, and calculate the standard deviation of the normalized grayscale image.

[0054] The above three parameter values ​​will be used as the calculation factors of the parameters in the SPCNN model.

[0055] According to the existing method, the parameter values ​​obtained by preprocessing are ...

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

No PUM Login to view more

Abstract

The invention discloses an adaptive target detection method based on SPCNN, which belongs to the technical field of computer vision. The realization method of the present invention is: calculate image static property parameter; Deduce theoretical formula according to Stevens's law, calculate threshold value attenuation time constant α e , making the threshold decay time constant α e It can be adaptively set according to the overall grayscale characteristics of the target image; based on the adaptive side suppression mechanism, the hyperbolic tangent function is used to improve the suppression coefficient calculation model, and the suppression coefficient calculation model is used to calculate the link weight matrix of each pixel; In the SPCNN with the image input parameters adaptively set, iteratively generates binarized segmentation results and extracts candidate targets; based on the fast connection mechanism in neuron synchronization, combined with gray image criteria, by calculating the segmentation results of adjacent iterations Similarity and find the maximum value of similarity to achieve automatic output of the best segmentation results, while automatically controlling iterations to improve the efficiency and intelligence of the target detection method.

Description

technical field [0001] The invention relates to an adaptive target detection method, in particular to an adaptive target detection method based on a Simplified Pulse Coupled Neural Network (SPCNN, Simplified Pulse Coupled Neural Network), and belongs to the technical field of computer vision. Background technique [0002] Pulse coupled neural network (PCNN) belongs to the new neural network model of the third generation artificial neural network. Pulse-coupled neural network (PCNN) is inspired by the neuron activity in the main visual area V1 of the human neocortex. It has translation, rotation, scale invariance, good noise resistance and no need to process digital images. training and other advantages. The properties of PCNN for image processing mechanisms are divided into a new three-dimensional, the first dimension specifies the time matrix of PCNN, the second dimension captures the firing rate of PCNN, and the third dimension is the synchronization of PCNN. [0003] At...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/136G06T7/194G06N3/04
CPCG06T7/136G06T7/194G06N3/049G06T2207/20016G06V2201/07
Inventor 周肃宋勇郭拯坤张大勇赵宇飞
Owner 北京博睿维讯科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap