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

A kind of truck danger reminding method

A truck and dangerous technology, applied in the field of truck safety early warning, can solve the problem of frequent accidents in blind areas of vision, and achieve the effects of fast recognition speed, fast early warning speed and high recognition efficiency

Active Publication Date: 2021-12-14
NORTHEASTERN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of frequent accidents caused by the existence of blind spots in trucks in mining areas in the prior art, the present invention provides a truck danger reminder method

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 kind of truck danger reminding method
  • A kind of truck danger reminding method
  • A kind of truck danger reminding method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] Such as figure 1 Shown is a truck danger warning method according to an embodiment of the present invention, comprising the following steps:

[0076] S1. For a truck located in a mine area, each image acquisition device on the truck collects image information of a corresponding area.

[0077] S2. The image processing center connected to all image acquisition devices on the truck processes the image information in real time to determine whether there is a target to be identified within the preset range of the current truck;

[0078] Wherein, step S2 specifically includes:

[0079] S21. Perform preprocessing on the images collected by each image collection device, and obtain preprocessed images;

[0080] S22. Using the trained lightweight SSD model to process the preprocessed image in real time;

[0081] Wherein, the lightweight SSD model after training is obtained by training the lightweight SSD model with training images related to the current truck in advance.

[0...

Embodiment 2

[0098] When running for the first time the program carrying a truck danger reminder method of the present invention, it is necessary to train the lightweight SSD model, and the training of the lightweight SSD model specifically includes the following steps:

[0099] L01: Input the preprocessed training image into the lightweight SSD model to obtain the first feature map;

[0100] It should be noted that, in order to perform detection on multiple scales, the first feature maps of the new module, the seventh module and the eighth module are extracted here. Each first feature map contains a certain number of default bounding boxes, i.e., default boxes, which have a certain scale and aspect ratio, and two different types of filters (i.e., position and score) are applied to each first feature Graph to predict the location offset and target score of the default box.

[0101] L02: Calculate the first default frame of each first feature map;

[0102] First, the first feature map is ...

Embodiment 3

[0133] The trained lightweight SSD model structure is:

[0134] The input of the lightweight SSD model is a 300×300×3 image, the number of channels of the image is 3, and it is an RGB (three primary colors of image color: red, green, blue) image. The first module: first there are two convolution layers, the size of the convolution kernel is 3×3, the number of convolution kernels is 64, the step size is 1, and the padding method is 'SAME' (zero padding makes the input and output images the same size ), the activation function is a linear rectification function (Rectified Linear Unit, ReLU), and then the maximum pooling layer, the sampling kernel size is 2×2, the step size is 2, and the output is 64 feature maps of 150×150;

[0135] The second module: first there are two convolutional layers, the convolution kernel size is 3×3, the number of convolution kernels is 128, and then the maximum pooling layer, the sampling kernel size is 2×2, and the output is 128 75×75 feature map; ...

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 belongs to the field of truck safety early warning, and in particular relates to a truck danger warning method. The method includes: for the truck located in the mine area, each image acquisition device on the truck collects the image information of the corresponding area; the image processing center connected to all the image acquisition devices on the truck processes the image information in real time to determine the current truck's forecast Whether there is a target to be identified within the preset range; if there is a target to be identified within the preset range, a danger signal will be sent to the driver of the current truck. The truck danger warning method of the present invention does not use network communication, all image information is processed in real time, and the early warning speed is fast. The truck danger warning method of the present invention uses a lightweight SSD model to process image information in real time, and the model has a high recognition speed and high recognition efficiency for people and vehicle targets that trucks in mining areas need to be specially recognized.

Description

technical field [0001] The invention belongs to the field of truck safety early warning, and in particular relates to a truck danger warning method. Background technique [0002] With the continuous improvement of mining technology and the continuous increase of mining intensity, the large-scale equipment is also constantly developing. Large-scale truck transportation is one of the most important forms of production and transportation in large-scale mines. [0003] The safety warning system of mining trucks is different from the safety warning system of ordinary cars. There are two main reasons: first, the driving road of mining vehicles is completely different from that of ordinary cars. Composed of steps and steps, the complexity of the road is much higher than that of ordinary cars; second, mining vehicles are bulky, and their length, width and height are several times that of ordinary cars, so there are blind spots in the field of vision, and the risk factor is relative...

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): G06K9/00G06K9/62
CPCG06V40/10G06V20/584G06V20/58G06F18/214
Inventor 肖冬杨丰华单丰孙效玉柳小波毛亚纯
Owner NORTHEASTERN UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com