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

Pedestrian detection method and device, electronic equipment and storage medium

A technology for pedestrian detection and images to be detected is applied in the fields of pedestrian detection methods, electronic equipment and storage media, and devices, and can solve the problems of lack of analysis and reduced accuracy of pedestrian detection by algorithms, so as to improve the accuracy, reduce the possibility, Enhance the effect of feature angles

Pending Publication Date: 2022-05-10
CHINA FIRST AUTOMOBILE
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for different algorithms, the extracted feature angles usually match the structure and characteristics of the algorithm model, but for the feature angles that the model does not care about, the extracted features will not express the feature angles, which will make the algorithm lack correctness. The analysis of the characteristic angles that should not be concerned, and sometimes these characteristic angles may best express the characteristics of pedestrians, which will lead to a decrease in the accuracy of the algorithm for pedestrian 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
  • Pedestrian detection method and device, electronic equipment and storage medium
  • Pedestrian detection method and device, electronic equipment and storage medium
  • Pedestrian detection method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] figure 1 A schematic flowchart of the pedestrian detection method provided in the first embodiment of the present application, this embodiment can be applied to the scene of pedestrian detection, the method can be executed by a pedestrian detection device, the device can be implemented in hardware and / or software, and Generally, it can be integrated into electronic devices such as computers with data computing capabilities, and specifically includes the following steps:

[0026] Step 101: Acquire image data to be detected, and use multiple convolution kernels to perform feature extraction on the image data to be detected to obtain multiple feature maps.

[0027] In this step, the image data to be detected may be image data captured by a vehicle-mounted camera, and the captured image data may be video data or photo data. If it is video data, each frame of data in the video data may be used as this The image data to be detected in the step; if it is photo data, it can be...

Embodiment 2

[0047] see figure 2 , figure 2 It is a schematic flow chart of obtaining gradient histogram features provided by Embodiment 2 of the present application, specifically including the following steps:

[0048] Step 201, for any feature map, normalize the feature map, and calculate the gradient magnitude and gradient direction of each pixel in the feature map.

[0049] In this step, normalization can reduce the impact of image shadows and illumination changes on subsequent detection agents. Specifically, normalization can be performed in units of pixels, and the calculation formula for normalization can be I(x, y)=I(x, y) gamma , where gamma is usually 0.5.

[0050] In addition, when calculating the gradient magnitude and gradient direction of each pixel in the feature map, for any pixel, the gradient components of the pixel in the first preset direction and the second preset direction can be determined first; then based on the first The gradient component of a preset direct...

Embodiment 3

[0063] see image 3 , image 3 It is a schematic structural diagram of a pedestrian detection device provided in Embodiment 3 of the present application. The pedestrian detection device provided in the embodiment of the present application can execute the pedestrian detection method provided in any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the method. The device can be implemented in software and / or hardware, such as image 3 As shown, the pedestrian detection device specifically includes: a feature map extraction module 301 , a gradient histogram feature acquisition module 302 , and a classification module 303 .

[0064] Wherein, the feature map extraction module is used to obtain the image data to be detected, and utilize multiple convolution kernels to perform feature extraction on the image data to be detected to obtain multiple feature maps;

[0065] The gradient histogram feature acquisition mo...

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 embodiment of the invention discloses a pedestrian detection method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring to-be-detected image data, and performing feature extraction on the to-be-detected image data by using a plurality of convolution kernels to obtain a plurality of feature maps; for any feature map, inputting the feature map into a preset gradient histogram feature acquisition algorithm, and acquiring a gradient histogram feature corresponding to the feature map output by the gradient histogram feature acquisition algorithm; and inputting the gradient histogram features corresponding to the feature maps into a preset classifier, obtaining a classification result of the preset classifier, and detecting pedestrians in the to-be-detected image data based on the classification result. On the basis, the possibility of missing features capable of expressing pedestrian features can be reduced, and the accuracy of pedestrian detection is improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of automatic driving, and in particular, to a pedestrian detection method, device, electronic device, and storage medium. Background technique [0002] With the development of science and technology, autonomous driving technology is continuously developing to the L3 level, that is, conditional autonomous network, the system can sense environmental changes in real time, dynamically optimize and adjust based on the external environment in a specific field, and realize closed-loop management based on intent. Among them, the detection of pedestrians is an important part in the perception of environmental changes. [0003] Traditional pedestrian detection algorithms generally perform feature extraction first, and then detect pedestrians based on the extracted features. However, for different algorithms, the extracted feature angle is usually matched with the structure and characterist...

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): G06V40/10G06V10/50G06V10/774G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2411G06F18/214
Inventor 曹燕
Owner CHINA FIRST AUTOMOBILE