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

Target object ranging method based on deep learning under truck environment

A technology of deep learning and target objects, applied in the interpretation of photos, biological neural network models, neural architectures, etc., can solve problems such as inability to remind

Inactive Publication Date: 2019-03-22
NORTHEASTERN UNIV
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method cannot alert the driver to the existence of other objects such as pedestrians and auxiliary vehicles.

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
  • Target object ranging method based on deep learning under truck environment
  • Target object ranging method based on deep learning under truck environment
  • Target object ranging method based on deep learning under truck environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] Such as figure 1 Shown: the present embodiment discloses a method for measuring distance of objects in a truck environment based on deep learning, including the following steps:

[0081] S1. Acquiring target image data.

[0082] It should be noted that the target object image data described in this step is the target object image acquisition data acquired by the image acquisition device located on the mining truck, wherein the target object can be other targets such as mining trucks, people, etc. The image data of the target object here is the image data of other mining trucks; of course, there can be multiple image acquisition devices on the mining truck in this embodiment.

[0083] S2. Preprocessing the acquired image data of the target object.

[0084] The preprocessing in this step mainly includes: randomly intercepting a part of the target image and distorting it, randomly flipping the image left and right, randomly distorting the color (such as brightness, satur...

Embodiment 2

[0146] This embodiment discloses a method for measuring the distance of an object in a truck environment based on deep learning, which specifically includes the following steps:

[0147] (1) For a truck transporting ore in an open-pit mine, each image acquisition device on the truck collects image information of a corresponding area.

[0148] (2) The image processing center connected to all image acquisition devices on the truck processes the image information in real time to determine the pixel position of the target to be identified in the acquired image.

[0149] (3) According to the pixel position of the recognized target in the image, the distance between the target and the image acquisition device is calculated by the method of image ranging.

[0150] Wherein, step (2) specifically includes:

[0151] (2.1) Perform preprocessing on the images collected by each image acquisition device, and obtain preprocessed images.

[0152] (2.2) The compressed SSD model is trained us...

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 relates to a target object ranging method based on deep learning under a truck environment. The target object ranging method comprises the following steps of S1: obtaining target objectimage data; S2: preprocessing the obtained target object image data; S3: inputting the preprocessed target object image data into an SSD (Steady-State Distribution) model, and processing by the SSD model to obtain the pixel position coordinate of a target object in an image; S4: according to the identified pixel position coordinate of the target object in the image, through the image ranging method, calculating a distance between the target object and an image collection device, thus obtaining the distance between the target object and the image collection device, wherein the SSD model is a compressed and improved model, and the target object image data is target object image data obtained under an overlooking condition. For the target object which needs to be identified by a mine area truck, the ranging method provided by the invention has the advantages of high identification speed, high identification efficiency, high ranging speed since a monocular ranging method is used and the like.

Description

technical field [0001] The invention belongs to the technical field of computer vision and truck anti-collision, and in particular relates to a deep learning-based object ranging method in a truck environment. Background technique [0002] With the advancement and development of science and technology, a large amount of human labor is gradually completed by computers. Machine vision can complete various tasks better and faster than humans. On the one hand, due to human nature, long-term work is prone to fatigue and cannot guarantee a high detection accuracy rate. On the other hand, due to the physiological limit of the human eye, it is difficult to improve in terms of speed and accuracy. Therefore, modern industry and production urgently need a new machine technology to replace human vision. At the same time, with the continuous development and improvement of computer technology, electromechanical control technology, intelligent detection technology and digital image proce...

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): G01C11/04G06N3/04
CPCG01C11/04G06N3/045
Inventor 肖冬单丰王宝华刘燨文李雪娆孙效玉
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