Forklift anti-collision system based on binocular vision

A binocular vision, collision avoidance system technology, applied in scene recognition, combustion engine, internal combustion piston engine and other directions, to achieve the effect of all-round power consumption, all-round recognition and ranging, low recognition and ranging

Inactive Publication Date: 2022-05-27
江苏自然数智能科技有限公司
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a forklift anti-collision system based on binocular vision, which is used to solve the problem that the forklift cannot accurately identify the obstacles encountered in the existing solution and adjust the operation adaptively Technical Problems of Realizing Dynamic Collision Avoidance

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
  • Forklift anti-collision system based on binocular vision
  • Forklift anti-collision system based on binocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] If the feature analysis set includes the first type of instruction and the feature state set includes the second distance instruction, a first control signal is generated, and the moving direction of the forklift is adjusted through a preset first adjustment angle according to the first control signal to avoid object obstacles;

[0086] If the feature analysis set contains the first type of instruction and the feature state set contains the third distance instruction, a second control signal is generated, and the moving direction of the forklift is adjusted through a preset second adjustment angle according to the second control signal to avoid object obstacles; Wherein, the second adjustment angle is greater than the first adjustment angle;

[0087] The specific steps for adjusting the moving direction of the forklift according to different adjustment angles include:

[0088] Obtain the monitoring coordinates of obstacles on the three-dimensional coordinate system esta...

Embodiment 2

[0094] If the feature analysis set contains the second type of command and the feature state set contains the first distance command, a third control signal is generated, and the forklift is controlled to decelerate according to the third control signal and the bell will prompt;

[0095] If the feature analysis set contains the second type command and the feature state set contains the second distance command, a fourth control signal is generated, and the forklift is controlled to stop moving according to the fourth control signal and a voice prompt is performed to avoid obstacles.

[0096] It should be noted that this embodiment can adaptively make different operation controls according to the type and distance of the obstacle. When the obstacle is an object, different degrees of offset are made according to the distance and position between the forklift and the object. to actively avoid the object; when the obstacle is a person, different prompts are made according to the dis...

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 forklift anti-collision system based on binocular vision, and belongs to the technical field of image recognition and safe ranging, a binocular vision module comprises a plurality of binocular camera devices distributed at the front, back, left and right positions of the top of a forklift, and the binocular camera devices are used for collecting images in different directions in the moving process of the forklift; arranging and combining a plurality of images in different directions according to a direction sequence to obtain an image set; preprocessing a plurality of images in different directions collected in the image set to obtain an image processing set; the identification module analyzes types and states of obstacles in the image processing set to obtain an obstacle analysis set; the control module automatically controls the forklift to perform voice prompt and automatic steering and parking to avoid different types of obstacles according to the obstacle analysis set; the method is used for solving the technical problem that in an existing scheme, a forklift cannot accurately recognize encountered obstacles and cannot adaptively adjust the operation mode to achieve dynamic anti-collision.

Description

technical field [0001] The invention relates to the technical field of image recognition and safe ranging, and more particularly to a forklift collision avoidance system based on binocular vision. Background technique [0002] In recent years, with the rapid development of warehousing and logistics enterprises, the demand for forklift trucks is also increasing, and forklift accidents are also increasing. Forklifts are large-scale heavy-tonnage transportation machinery in warehouses. Because the goods block the front line of sight, there are many blind spots. Because the forklifts and the goods are too heavy, once a collision occurs, it is easy to smash people or cause people to be injured due to knocking down items, so give personal safety belts. great danger. [0003] After retrieval, the invention with the publication number CN105303345A, titled an RFID-based forklift collision avoidance system and method, discloses a forklift module arranged in a forklift and a warehouse...

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): G06V20/58
CPCY02T10/40
Inventor 董海川刘辉
Owner 江苏自然数智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap