Unlock instant, AI-driven research and patent intelligence for your innovation.

Human body image detection method

A human body image and detection method technology, applied in the field of image processing, can solve the problems of running speed and accuracy, reduce uncertainty and other problems, and achieve the effect of good effect, large receptive field and strong generalization ability

Pending Publication Date: 2020-08-11
天津中科智能识别有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to propose a human body image detection method to solve the problems of running speed and accuracy in the existing detection methods, so as to improve the quality of human body image bounding box generation and reduce uncertainty

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
  • Human body image detection method
  • Human body image detection method
  • Human body image detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other if there is no conflict.

[0036] Such as Figure 1-Figure 6 As shown,

[0037] The human body image detection method of the present invention includes the following steps:

[0038] Step S1, first perform specific data enhancement on the image training set data. First, we define all possible data enhancements that can be applied to the image, as shown in the following table (the parameters correspond to the corresponding function parameters of TensorFlow):

[0039]

[0040] Take the following specific actions:

[0041]

[0042] The enhanced strategy is defined as a set of disordered K sub-strategies. During training, one of K sub-strategies will be randomly selected and then applied to the current image. Each sub-strategy has 2 image enhancement operations, where P is the probability value of each operation (range 0-1), M is the parameter amplitude, an...

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 human body image detection method, which comprises the following steps of: preprocessing an input training image, augmenting and expanding data by using automatic data, and using a pyramid-like network of a feature region based on hole convolution bottleneck; cutting a boundary frame formed by the detected human body, and only reserving an image in the frame; and inputting the cut image into a designed model for training to obtain a pedestrian detection model. According to the invention, two-dimensional space detection can be carried out on the input image containingthe human body, the human body space information in the generated image is accurate, and the calculation cost is low.

Description

Technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for detecting human body images. Background technique [0002] Human body image detection refers to marking the spatial geometric position of the human body from an image containing the human body. Human body detection is a computer technology related to computer vision and image processing, used to detect specific categories of semantic objects in digital images and videos. The subject detection areas for in-depth research on the human body include face detection and pedestrian detection. Human detection has applications in many areas of computer vision, including image retrieval and video surveillance. [0003] Since the human body is quite flexible, there are various postures and shapes, and its appearance is greatly affected by wearing, posture, and viewing angle. In addition, it is also affected by factors such as occlusion and illumination. This makes p...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/20G06V10/44G06N3/045G06F18/2415
Inventor 侯峦轩马鑫赫然孙哲南
Owner 天津中科智能识别有限公司