Lock station connection lock detection system and method based on deep learning

A technology of deep learning and detection methods, which is applied in closed-circuit television systems, televisions, instruments, etc., to achieve the effect of reducing the false alarm rate of the model and improving the accuracy of the model

Active Publication Date: 2021-09-21
TIANJIN PORT SECOND CONTAINER TERMINAL CO LTD +2
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Lack of an automatic means to automatically detect the correct installation and removal of the attachment lock

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
  • Lock station connection lock detection system and method based on deep learning
  • Lock station connection lock detection system and method based on deep learning
  • Lock station connection lock detection system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0109] Install 6 cameras (network dome cameras) at the lock station, including 3 cameras on both sides of the lock station, corresponding to the head of the double 20-foot container, the middle of the double container, and the tail of the tail box to detect the corresponding position of the container. Attachment and detachment of the connection lock on the side.

[0110] Install a set of visual analysis system (including server and network transmission equipment) in the general control room of the port for real-time analysis of the front-end camera screen and provide corresponding early warning data output. At the same time, the visual analysis system has the ability to interface with the port business system or the main control system of the lock station, and can send the recognition results to the corresponding third-party system.

[0111] Install a power distribution box (2 sides in total) in the guard box on the same side of the lock station for the convergence and transmi...

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 lock station connection lock detection system and method based on deep learning. The system comprises a camera which is disposed at a lock station and is used for detecting a video image of the loading and unloading of a connection lock on a container in the lock station; a distribution box is shot in a sentry box in the lock station and is used for gathering and transmitting the video images; a visual analysis system is arranged in the control room and is used for analyzing the video images in real time and providing corresponding early warning data output; and the network connection equipment is used for transmitting the video images and the early warning data. According to the invention, the monitoring camera is installed at the lock station, and the installation and disassembly states of the connection lock are automatically detected by using the video-based deep learning technology.

Description

technical field [0001] The present invention relates to a technology for disassembling connecting locks on containers, and more specifically, to a detection system and method for connecting locks at lock stations based on deep learning. Background technique [0002] Deep learning refers to a collection of algorithms that use various machine learning algorithms on multi-layer convolutional neural networks to solve various problems such as videos and images. Deep learning can be classified into neural networks in a broad category. The core is special learning, which aims to obtain hierarchical feature information through layered networks, so as to solve important problems that required manual design of features in the past. [0003] The vision-based deep learning algorithm is to simulate the human visual principle, which is as follows: [0004] Starting from the original signal intake (pupil intake pixel, based on the image is the pixel pixel), then do preliminary processing ...

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): G06K9/00G06K9/62G06N3/04H04N7/18
CPCH04N7/181G06N3/045G06F18/214Y02T10/40
Inventor 杨荣杨雷忠范柘高延辉陈培张凯武彬彭云辉王学迁尹兆鑫
Owner TIANJIN PORT SECOND CONTAINER TERMINAL CO LTD
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