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

A method of generating object detection model

An object detection and model technology, applied in the field of computer vision, can solve problems such as low accuracy, and achieve the effect of improving accuracy, reducing size, and improving feature receptive field

Inactive Publication Date: 2019-07-30
XIAMEN MEITUZHIJIA TECH
View PDF15 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is fast to detect, but the accuracy is low

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
  • A method of generating object detection model
  • A method of generating object detection model
  • A method of generating object detection model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0041] Generally, the SSD object detection model includes a VGG basic network and a pyramid network. Since VGG has a deep network structure with 16 or 19 layers, the model has a large number of parameters and cannot meet the requirements of the mobile terminal. In order to achieve real-time object detection and make the model meet the requirements of mobile memory and computing speed, this solution improves the network structure of ...

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 a method for generating an object detection model, and the method comprises the steps: obtaining a training image containing annotation data, and enabling the annotation data to be the position and category of a target object in the training image; inputting the training image into a pre-trained object detection model for processing, the object detection model comprising afeature extraction module, a fusion module and a prediction module which are mutually coupled, the feature extraction module being suitable for performing convolution processing on the training imageto generate at least one initial feature map; the fusion module is suitable for performing up-sampling processing on the initial feature map to obtain a feature map after feature fusion; the prediction module is suitable for predicting the category and the position of the target object from the feature map; and on the basis of the annotation data and the predicted object category and position, training a pre-trained object detection model to obtain a trained object detection model as a generated object detection model.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for generating an object detection model, an object detection method, a computing device and a storage medium. Background technique [0002] Object detection is the basis of many computer vision tasks. It is suitable for locating and identifying one or more known targets in the input image. It is usually applied to scene content understanding, video surveillance, content-based image retrieval, robot navigation and augmented reality, etc. field. [0003] The traditional object detection method is generally divided into three stages: first, extract the candidate frame area, and use the sliding window to traverse the entire image to obtain the possible position of the object; then, extract features from these extracted candidate frame areas. The commonly used method is SIFT (Scale-invariant feature transformation), HOG (Histogram of Oriented Gradients), etc.; final...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/00G06V10/454G06F18/214
Inventor 齐子铭李启东陈裕潮张伟李志阳
Owner XIAMEN MEITUZHIJIA TECH
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