Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Training method of target detection model for multi-category junk scene recognition

A target detection and detection model technology, applied in the field of image processing, can solve problems such as low detection accuracy of garbage targets, ineffective recognition of multi-point garbage, and small range of receptive fields, so as to prevent excessive receptive fields, high discrimination accuracy, and receptive The effect of wild lifting

Active Publication Date: 2022-01-28
BEIJING WENAN INTELLIGENT TECH CO LTD
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a training method for a target detection model for multi-category garbage scene recognition, to solve the problem that the target detection model in the prior art has a small receptive field range, so that there is garbage in the scene image with a wide field of view. The problem of low target detection accuracy, if such scene images are used as model input for garbage recognition detection, the detection results obtained often have the phenomenon of invalid multi-point garbage recognition or false positives of garbage 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Training method of target detection model for multi-category junk scene recognition
  • Training method of target detection model for multi-category junk scene recognition
  • Training method of target detection model for multi-category junk scene recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] 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 invention will be described in detail below with reference to the accompanying drawings and examples.

[0034]In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is an embodiment of a part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0035] It should be noted that the terms "firs...

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 provides a training method of a target detection model for multi-category junk scene recognition. The training method comprises the following steps: constructing a basic target detection model; in the p convolution layers, selecting m continuous convolution layers, and replacing each selected convolution layer by a cavity convolution; sequentially setting the void ratios of the m hole convolutions to meet the condition that the largest common divisor of the void ratios of any two adjacent hole convolutions is 1 so as to obtain an optimized target detection model; and training the optimized target detection model by using the sample image training set to obtain a target detection model for multi-category junk scene recognition. According to the invention, the problem of low garbage target detection precision of a scene image with a wide visual field due to a small receptive field range of a target detection model in the prior art is solved, the scene image is used as a model input for garbage recognition detection, and the obtained detection result often has the phenomenon of invalid multi-point garbage identification or false alarm of garbage detection.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a training method for a target detection model used for multi-category garbage scene recognition. Background technique [0002] Target detection is an image understanding algorithm based on the geometric and statistical characteristics of the target. Target detection combines the positioning and recognition of target objects. For example, based on computer vision algorithms, the image is detected by using the target detection model obtained through machine learning. Different categories of target objects in the target object, that is, the position of the target is marked with a rectangular frame, and the category of the target object is identified. [0003] Target detection is widely used in garbage recognition and classification. In related technologies, the target detection model can only recognize a limited number of garbage types due to a small amount of artificial c...

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
IPC IPC(8): G06V10/25G06V10/774G06V10/82G06K9/62G06N3/04
CPCG06N3/045G06F18/214
Inventor 张志嵩张帆陈映曹松任必为
Owner BEIJING WENAN INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products