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

Deep learning-based van door state recognition device and system

A state recognition and deep learning technology, applied in character and pattern recognition, neural learning methods, instruments, etc., can solve problems such as the inability to achieve external supervision, and achieve the effect of eliminating hidden dangers

Inactive Publication Date: 2020-09-29
HANGZHOU GUDEWEI ROBOT CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above schemes all detect the state of the door from the inside of the car, and cannot achieve external supervision

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
  • Deep learning-based van door state recognition device and system
  • Deep learning-based van door state recognition device and system
  • Deep learning-based van door state recognition device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] At present, the rapid development of my country's logistics parks has also spawned a lot of technical requirements, such as logistics park management and service capabilities, and the level of informatization needs to be improved. In order to improve the data collection and automatic management capabilities in all aspects of logistics and transportation, in view of the current lack of identification and monitoring of the closed doors of vans in logistics parks, combined with the needs of logistics and transportation services and the characteristics of the embedded Raspberry Pi processing platform, This embodiment provides a system, device and controller for identifying the state of a van compartment door based on deep learning.

[0095] Such as figure 1 As shown, a deep learning-based van door state recognition system 10000 includes a recognition controller 100, a user interface unit 200, an acousto-optic unit 300, a distance sensing unit 600, an image acquisition unit...

Embodiment 2

[0144] Different from Embodiment 1, this embodiment also uses the image recognition module to recognize the truck model information. In order to record and compare vehicle model information in the management of freight yard entry and exit, combined with figure 1 with image 3 As shown, the present invention also extracts the type of the vehicle based on the collected images after being processed by the image recognition module.

[0145] The composition of transport vehicles in the logistics park is relatively complex, including individual transport and cooperative transport vehicles. For this reason, in the ERP system of the logistics park, it is necessary to update and maintain the vehicle information, and enter the vehicle information into the vehicle management subsystem, including the vehicle model, rated load capacity, license plate number, color, empty weight, owner, driver personnel, contacts, phone numbers, etc. Among them, the reason why the car model information i...

Embodiment 3

[0153] Different from other embodiments, in this embodiment, in the offline processing of samples, the recognition controller 100 also automatically marks the anchor frame of the car door area in the sample image through image difference processing, and obtains preliminary data of the training set and the test set.

[0154] Specifically, combined with Figure 5 , Figure 9 As shown, for the three viewing angle images of the truck collected in the image acquisition unit, the road surface images of the three viewing angles are used as the background image for differential calculation to obtain three differential images, and each differential image is processed:

[0155] Searching for the first and second horizontal lines whose length exceeds a set value and whose row numbers are the smallest and largest respectively in the differential image, and searching for the second column line whose length exceeds a set value and whose column number is the largest in the differential image...

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 provides a deep learning-based van door state recognition device and system. Side-looking, side-looking and overlooking multi-view images acquired by the image acquisition unit are fusedinto an image sample input into the deep learning network; a deep learning network is established in the identification controller; the feature convolution extraction depth is increased, a feature sharing layer is added in front of an output layer to achieve voting judgment of the state of the compartment door, multi-view compartment door area feature map fusion and sharing layer multi-feature fusion are matched with one another, and the robustness and accuracy of the network for compartment door state recognition are improved. According to the invention, automatic identification of the stateof the cargo compartment door is achieved, hidden dangers caused by opening of the compartment door during transportation can be effectively prevented, and the logistics transportation management level is improved. The license plate area and the vehicle type are recognized in the same network, so that the number of recognition networks is reduced, and the recognition efficiency is improved; and through automatic preliminary frame selection of the compartment door area in the training sample image, the annotation workload is saved.

Description

technical field [0001] The patent of the present invention belongs to the field of logistics transportation, and specifically relates to a device and system for identifying the state of a van compartment door based on deep learning. Background technique [0002] Logistics transportation is an important pillar industry for economic and social development. For enterprises, the establishment and improvement of their logistics capabilities is an important driving force for their development. At present, due to the obvious scale advantages and aggregation effects of logistics parks in terms of economic scale, geographical distribution, and construction and operation methods, my country has formed a national logistics park construction and development situation from south to north and from east to west. The logistics park covers a relatively large area, in addition to warehousing, transportation, processing, etc., it also includes some supporting businesses such as information, co...

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
IPC IPC(8): G06K9/00G06K9/20G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06V20/52G06V10/22G06V30/153G06N3/045G06F18/25
Inventor 邹细勇黄昌清花江峰
Owner HANGZHOU GUDEWEI ROBOT CO LTD
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