CN115083211B - Distributed ship height detection system based on multi-view stereoscopic vision - Google Patents

Distributed ship height detection system based on multi-view stereoscopic vision Download PDF

Info

Publication number
CN115083211B
CN115083211B CN202210772947.9A CN202210772947A CN115083211B CN 115083211 B CN115083211 B CN 115083211B CN 202210772947 A CN202210772947 A CN 202210772947A CN 115083211 B CN115083211 B CN 115083211B
Authority
CN
China
Prior art keywords
ship
bridge
distributed
assembly
absolute elevation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210772947.9A
Other languages
Chinese (zh)
Other versions
CN115083211A (en
Inventor
顾振雄
王达磊
董一庆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongji University
Original Assignee
Tongji University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tongji University filed Critical Tongji University
Priority to CN202210772947.9A priority Critical patent/CN115083211B/en
Publication of CN115083211A publication Critical patent/CN115083211A/en
Application granted granted Critical
Publication of CN115083211B publication Critical patent/CN115083211B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G3/00Traffic control systems for marine craft
    • G08G3/02Anti-collision systems
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18Status alarms
    • G08B21/182Level alarms, e.g. alarms responsive to variables exceeding a threshold
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18Status alarms
    • G08B21/24Reminder alarms, e.g. anti-loss alarms
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/04Synchronising

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Ocean & Marine Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to a distributed ship height detection system based on multi-view stereoscopic vision, which comprises a distributed video acquisition assembly, a video transmission and synchronization assembly and a data summarizing and processing assembly, wherein the distributed video acquisition assembly is arranged at the upstream and downstream positions of a bridge, and the distributed video acquisition assembly acquires the video information of the ship from the upstream and downstream positions of the bridge; the video transmission and synchronization component performs time synchronization on the ship video information and performs upper output; the data summarizing and processing assembly is used for carrying out three-dimensional reconstruction on the ship based on the video information of the ship from the beginning to the end, obtaining the absolute elevation of the top structure of the ship, comparing the absolute elevation of the top of the ship with the absolute elevation of the bottom of the bridge, and judging the possibility of scraping or collision between the ship and the bottom of the bridge. Compared with the prior art, the invention realizes the three-dimensional reconstruction and the real-time monitoring and early warning of the height relation between the ship height and the bridge height, and realizes the real-time notification of the user side through the wireless communication technology.

Description

Distributed ship height detection system based on multi-view stereoscopic vision
Technical Field
The invention relates to the technical field of shipping, in particular to a distributed ship height detection system based on multi-view stereoscopic vision.
Background
When a ship runs on a channel, the relative heights of the ship and a bridge through which the ship passes can be changed due to the change of the water level of a river and the cargo loading of the ship. If the absolute elevation of the highest point of the ship is greater than the absolute elevation of the bottom of the pathway bridge, the ship may scrape or even collide with the bottom of the bridge, thereby posing a threat to the bridge and the ship.
CN106530837a discloses a method for actively preventing a ship from collision on a bridge based on machine vision, which utilizes actual measurement data such as distance, navigational speed, heading, latest meeting point, time reaching the latest meeting point, etc., actively reminds a ship of illegal operation, evaluates the risk of ship collision in real time, actively pre-warns the risk of ship collision, and automatically alarms the accident of ship collision.
CN 109949616A discloses a bridge active ship collision prevention monitoring and early warning system, which comprises a plurality of monitoring video acquisition devices and a track tracking device, wherein the monitoring video acquisition devices have: a video acquisition part and an acquisition side communication part; the track following device has: a neural network storage unit in which a neural network model is stored; a target ship acquisition unit for acquiring a ship position of the target ship; a coordinate acquisition unit that acquires a ship coordinate value from a ship position; a ship track acquisition unit that acquires a ship track and a ship navigation speed from the ship coordinate values; a ship track prediction unit for acquiring a predicted track, a predicted speed, a bridge-abutting time, and a probability distribution of a passing position from a ship track and a sailing speed; and the ship collision early warning part acquires the ship collision probability according to the bridge abutment time and the passing position and gives an alarm.
The two schemes mainly focus on the relationship between the navigation track of the ship and the bridge pier on a plane coordinate system, and cannot solve the technical problem of channel early warning faced by the scheme.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a distributed ship height detection system based on multi-view stereoscopic vision, which can realize detection of ship height, so as to pre-judge whether the height of the ship exceeds the height of the bottom of a bridge or not and further judge whether the ship is likely to scrape or even collide with the bottom of the bridge or not.
The aim of the invention can be achieved by the following technical scheme:
the invention aims to provide a distributed ship height detection system based on multi-view stereoscopic vision, which comprises a distributed video acquisition component, a video transmission and synchronization component and a data summarizing and processing component, wherein the distributed ship height detection system specifically comprises the following components:
the distributed video acquisition assembly is arranged at the upstream and downstream positions of the bridge, and acquires the video information of the ship from the upstream and downstream positions of the bridge;
the video transmission and synchronization assembly is in communication connection with the distributed video acquisition assembly, and the video transmission and synchronization assembly performs time synchronization on the video information coming to the ship and performs upper output;
the data summarizing and processing assembly is in communication connection with the video transmission and synchronization assembly, three-dimensional reconstruction is carried out on the ship based on the video information of the ship from the beginning to the end, the absolute elevation of the top structure of the ship is obtained, the absolute elevation of the top of the ship is compared with the absolute elevation of the bottom of the bridge, the possibility of scraping or collision between the ship and the bottom of the bridge is judged, and if scraping or collision risks exist, an early warning message is sent to a user side.
Further, the distributed video acquisition assembly comprises a plurality of camera devices arranged along the upstream and downstream river banks of the bridge.
Further, the video transmission and synchronization assembly includes a first processing unit and a first output unit electrically connected to each other.
Further, the first processing unit is respectively in communication connection with each image pickup device, and performs frame-by-frame synchronous correction on the video output by each image pickup device to obtain synchronous multichannel video information;
the first output unit outputs the multi-channel video information to the data summarizing and processing assembly.
Further, the data summarizing and processing assembly comprises a second processing unit and a second output unit.
Further, the second processing unit performs frame-by-frame visual segmentation on each channel based on the synchronized multi-channel video information, segments a target ship from the background of the frame-by-frame image, and performs three-dimensional reconstruction on the ship based on a stereoscopic vision method to obtain the absolute elevation of the ship top structure.
Further, the second processing unit compares the absolute elevation of the top of the ship with the absolute elevation of the bottom of the bridge, and when judging the possibility of scraping or collision between the ship and the bottom of the bridge:
when the absolute elevation of the ship's roof structure is greater than a×h, the possibility of scratch or collision is considered, where a is a safety factor less than 1 and H is a preset absolute elevation of the bridge floor.
Further, the first output unit is an I/O interface, and the first output unit is electrically connected to the second processing unit.
Further, the second output unit is a radio frequency signal transmitting module, and the second output unit is in communication connection with the user side.
Further, the first processing unit and the second processing unit are an FPGA or an MCU.
Compared with the prior art, the invention has the following technical advantages:
1) The system in this technical scheme can install the bank at bridge upper and lower reaches conveniently, through shooing the coming and going boats and ships on the river, can realize the detection of boats and ships height to judge in advance whether the height of boats and ships exceeds bridge bottom height, and then judge whether the boats and ships probably with scraping even collision bridge bottom.
2) According to the technical scheme, the three-dimensional reconstruction and the real-time monitoring and early warning of the height relation between the ship height and the bridge height are realized through the upper and lower three-dimensional cooperation of the two-bank distributed video acquisition assembly, the video transmission and synchronization assembly and the data summarizing and processing assembly, and the real-time notification of the user side is realized through the wireless communication technology.
Drawings
Fig. 1 is a schematic diagram of a distributed ship height detection flow based on multi-eye stereoscopic vision in the technical scheme;
fig. 2 is a schematic diagram of a distributed ship height detection scene based on multi-eye stereoscopic vision in the technical scheme.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. Features such as structure/module names, control modes, algorithms, technical processes and the like which are not explicitly described in the technical scheme are all regarded as common technical features disclosed in the prior art.
The invention discloses a distributed ship height detection system based on multi-view stereoscopic vision, which comprises a distributed video acquisition component, a video transmission and synchronization component and a data summarizing and processing component, wherein the specific flow is shown in fig. 1.
The distributed video acquisition assembly is arranged at the upstream and downstream positions of the bridge, and acquires the video information of the ship from the upstream and downstream positions of the bridge; the video transmission and synchronization assembly is in communication connection with the distributed video acquisition assembly, and the video transmission and synchronization assembly performs time synchronization on the video information coming to the ship and performs upper output;
the data summarizing and processing assembly is in communication connection with the video transmission and synchronization assembly, three-dimensional reconstruction is carried out on the ship based on the video information of the ship from the beginning to the end, the absolute elevation of the top structure of the ship is obtained, the absolute elevation of the top of the ship is compared with the absolute elevation of the bottom of the bridge, the possibility of scraping or collision between the ship and the bottom of the bridge is judged, and if scraping or collision risks exist, an early warning message is sent to a user side.
The system in this technical scheme can install the bank at bridge upper and lower reaches conveniently, through shooing the coming and going boats and ships on the river, can realize the detection of boats and ships height to judge in advance whether the height of boats and ships exceeds bridge bottom height, and then judge whether the boats and ships probably with scraping even collision bridge bottom.
The distributed video acquisition assembly comprises a plurality of camera equipment arranged along the upstream and downstream river banks of the bridge, and the camera equipment is arranged on two river banks, see fig. 2. The number, the positions and the postures of the distributed video acquisition components can be flexibly selected according to the specific conditions of the site, and synchronous video shooting can be carried out on the vessels going and going on the river.
In particular embodiments, the video transmission and synchronization assembly includes a first processing unit and a first output unit electrically coupled to each other. The first processing unit is respectively connected with each image pickup device in a communication way, and performs frame-by-frame synchronous correction on the video output by each image pickup device to obtain synchronous multichannel video information; each channel in the present solution refers to multiview video information obtained by each camera only and synchronized with time. The first output unit outputs the multi-channel video information to the data summarizing and processing component. The data summarizing and processing assembly comprises a second processing unit and a second output unit.
In the specific implementation, the second processing unit performs frame-by-frame visual segmentation on each channel based on the synchronized multi-channel video information, segments a target ship from the background of the frame-by-frame image, and then performs three-dimensional reconstruction on the ship based on a stereoscopic vision method to obtain the absolute elevation of the ship top structure. In the specific implementation, the neural network-based multi-eye stereoscopic vision reconstruction or the deep learning and semantic method-based multi-eye stereoscopic vision reconstruction can be adopted, and a specific algorithm model only needs to adopt the existing open source model, so that the description is omitted.
In specific implementation, the second processing unit compares the absolute elevation of the top of the ship with the absolute elevation of the bottom of the bridge, and when the possibility of scraping or collision between the ship and the bottom of the bridge is judged: when the absolute elevation of the ship's roof structure is greater than a×h, the possibility of scratch or collision is considered, where a is a safety factor less than 1 and H is a preset absolute elevation of the bridge floor. The safety coefficient is selected, so that the safety of the system is improved, accidents caused by system errors are avoided, and the numerical value of the safety coefficient can be selected according to specific needs.
In specific implementation, the first output unit is an I/O interface, and the first output unit is electrically connected to the second processing unit. The second output unit is a radio frequency signal transmitting module and is in communication connection with the user side. The first processing unit and the second processing unit are FPGA or MCU of the current mainstream model.
According to the technical scheme, the three-dimensional reconstruction and the real-time monitoring and early warning of the height relation between the ship height and the bridge height are realized through the upper and lower three-dimensional cooperation of the two-bank distributed video acquisition assembly, the video transmission and synchronization assembly and the data summarizing and processing assembly, and the real-time notification of the user side is realized through the wireless communication technology. The user terminal in the technical scheme can be arranged on a mobile communication terminal of a ship driver, or a mobile communication terminal or a PC terminal of a channel manager, or electronic warning signs are arranged on two sides of a channel at fixed distances, and the user terminal in the technical scheme is directly arranged on an MCU (micro control unit) connected with the electronic warning signs, so that early warning prompt is realized.
The previous description of the embodiments is provided to facilitate a person of ordinary skill in the art in order to make and use the present invention. It will be apparent to those skilled in the art that various modifications can be readily made to these embodiments and the generic principles described herein may be applied to other embodiments without the use of the inventive faculty. Therefore, the present invention is not limited to the above-described embodiments, and those skilled in the art, based on the present disclosure, should make improvements and modifications without departing from the scope of the present invention.

Claims (5)

1. A distributed ship height detection system based on multi-eye stereoscopic vision, comprising:
the distributed video acquisition assembly is arranged at the upstream and downstream positions of the bridge and acquires video information of the ship from the upstream and downstream positions of the bridge;
the video transmission and synchronization assembly is in communication connection with the distributed video acquisition assembly, and performs time synchronization on the ship video information from the future and upper output;
the data summarizing and processing assembly is in communication connection with the video transmission and synchronization assembly, performs three-dimensional reconstruction on the ship based on the video information of the ship from the beginning to the end, obtains the absolute elevation of the top structure of the ship, compares the absolute elevation of the top of the ship with the absolute elevation of the bottom of the bridge, judges the possibility of scraping or collision between the ship and the bottom of the bridge, and sends an early warning message to a user side if scraping or collision risks exist;
the video transmission and synchronization assembly comprises a first processing unit and a first output unit which are electrically connected with each other;
the first processing unit is respectively connected with each image pickup device in a communication way, and performs frame-by-frame synchronous correction on the video output by each image pickup device to obtain synchronous multichannel video information;
the first output unit outputs the multichannel video information to the data summarizing and processing assembly;
the data summarizing and processing assembly is characterized by comprising a second processing unit and a second output unit;
the second processing unit performs frame-by-frame visual segmentation on each channel based on the synchronized multi-channel video information, segments a target ship from the background of the frame-by-frame image, and performs three-dimensional reconstruction on the ship based on a stereoscopic vision method to obtain an absolute elevation of a ship top structure;
the second processing unit compares the absolute elevation of the top of the ship with the absolute elevation of the bottom of the bridge, and when the possibility of scraping or collision between the ship and the bottom of the bridge is judged:
when the absolute elevation of the ship's roof structure is greater than a×h, the possibility of scratch or collision is considered, where a is a safety factor less than 1 and H is a preset absolute elevation of the bridge floor.
2. A multi-view stereoscopic based distributed marine vessel height detection system according to claim 1, wherein the distributed video acquisition assembly comprises a plurality of camera devices disposed along the bridge upstream and downstream banks.
3. The multi-view stereoscopic-based distributed marine height detection system of claim 1, wherein the first output unit is an I/O interface, and the first output unit is electrically connected to the second processing unit.
4. The system for detecting the height of the ship based on the multi-view stereoscopic vision according to claim 1, wherein the second output unit is a radio frequency signal transmitting module and is in communication connection with the user side.
5. The multi-view stereoscopic-based distributed ship height detection system according to claim 1, wherein the first processing unit and the second processing unit are FPGAs or MCUs.
CN202210772947.9A 2022-06-30 2022-06-30 Distributed ship height detection system based on multi-view stereoscopic vision Active CN115083211B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210772947.9A CN115083211B (en) 2022-06-30 2022-06-30 Distributed ship height detection system based on multi-view stereoscopic vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210772947.9A CN115083211B (en) 2022-06-30 2022-06-30 Distributed ship height detection system based on multi-view stereoscopic vision

Publications (2)

Publication Number Publication Date
CN115083211A CN115083211A (en) 2022-09-20
CN115083211B true CN115083211B (en) 2024-03-29

Family

ID=83257533

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210772947.9A Active CN115083211B (en) 2022-06-30 2022-06-30 Distributed ship height detection system based on multi-view stereoscopic vision

Country Status (1)

Country Link
CN (1) CN115083211B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6249241B1 (en) * 1995-09-21 2001-06-19 The United States Of America As Represented By The Secretary Of The Navy Marine vessel traffic system
CN101405779A (en) * 2005-04-05 2009-04-08 实物视频影像公司 Video surveillance system employing video primitives
KR101193687B1 (en) * 2011-04-18 2012-10-22 창원대학교 산학협력단 Sailing control system for avoiding ship collision
CN102915650A (en) * 2012-09-21 2013-02-06 交通运输部科学研究院 Convergent photography-based ship navigation safety early-warning equipment for ships in water area of bridges
KR20130076047A (en) * 2011-12-28 2013-07-08 최경래 Ship approach warning system and warning method for bridge protect
CN107230391A (en) * 2017-07-24 2017-10-03 上海市城市建设设计研究总院(集团)有限公司 Actively anti-ship hits system and its application method to bridge
CN107330377A (en) * 2017-06-08 2017-11-07 暨南大学 A kind of virtual navigation channel in bridge collision prevention system is built and DEVIATION detection method
CN109949616A (en) * 2019-03-25 2019-06-28 同济大学 A kind of anti-ship of bridge active hits monitoring and warning system
WO2020046133A1 (en) * 2018-08-29 2020-03-05 Sensorteknikk As Method and system to improve navigation safety for sea-going vessels in hazardous waters
CN111445726A (en) * 2020-04-30 2020-07-24 宁波市市政设施中心 Bridge anti-collision early warning system and method based on distributed video monitoring

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6249241B1 (en) * 1995-09-21 2001-06-19 The United States Of America As Represented By The Secretary Of The Navy Marine vessel traffic system
CN101405779A (en) * 2005-04-05 2009-04-08 实物视频影像公司 Video surveillance system employing video primitives
KR101193687B1 (en) * 2011-04-18 2012-10-22 창원대학교 산학협력단 Sailing control system for avoiding ship collision
KR20130076047A (en) * 2011-12-28 2013-07-08 최경래 Ship approach warning system and warning method for bridge protect
CN102915650A (en) * 2012-09-21 2013-02-06 交通运输部科学研究院 Convergent photography-based ship navigation safety early-warning equipment for ships in water area of bridges
CN107330377A (en) * 2017-06-08 2017-11-07 暨南大学 A kind of virtual navigation channel in bridge collision prevention system is built and DEVIATION detection method
CN107230391A (en) * 2017-07-24 2017-10-03 上海市城市建设设计研究总院(集团)有限公司 Actively anti-ship hits system and its application method to bridge
WO2020046133A1 (en) * 2018-08-29 2020-03-05 Sensorteknikk As Method and system to improve navigation safety for sea-going vessels in hazardous waters
CN109949616A (en) * 2019-03-25 2019-06-28 同济大学 A kind of anti-ship of bridge active hits monitoring and warning system
CN111445726A (en) * 2020-04-30 2020-07-24 宁波市市政设施中心 Bridge anti-collision early warning system and method based on distributed video monitoring

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
一种桥梁防撞系统中的虚拟航道构建与船舶偏航检测方法;郭乾;周曙;何信;邵华平;;软件导刊;20180626(第07期);全文 *
桥梁防船撞主动预警系统设计及实验研究;任慧;中国优秀硕士学位论文全文数据库工程科技辑;20130715(第7期);全文 *

Also Published As

Publication number Publication date
CN115083211A (en) 2022-09-20

Similar Documents

Publication Publication Date Title
KR102112000B1 (en) System for Warning Collision with Marine Bridge and Seaside Facilities based on Radar
CN103714718B (en) A kind of inland river bridge area ship safe navigation precontrol system
KR101805564B1 (en) Alarm system for prevent ship collision and method thereby
CN102730166B (en) Automatic draught monitoring system and method for river vessels
KR102543161B1 (en) Distracted Driving Monitoring Methods, Systems and Electronics
JP2018503913A (en) Ship auxiliary docking method and system
CN201774625U (en) Linkage control system for vessel traffic control/identification system and television monitoring system
CN113050121A (en) Ship navigation system and ship navigation method
CN111986517A (en) Ship anomaly detection method and device and storage medium
CN112562417A (en) Ship emergency command management system and method
KR20240046463A (en) A System for Supporting a Personal Safety and a Sailing Safety Based on an Artificial Intelligence and a Supporting Method with the Same
CN112102361B (en) Multi-ship operation collision detection method and device and computer equipment
KR101935577B1 (en) Security system of offfhore wind farm and submarine cable
CN111445726A (en) Bridge anti-collision early warning system and method based on distributed video monitoring
KR20220011879A (en) Coastal monitoring system based on electronic charts interlocked with radar equipment
CN115083211B (en) Distributed ship height detection system based on multi-view stereoscopic vision
CN111123251A (en) Target object detection method and device of radar
KR102283968B1 (en) System and method for generating and sharing visibility observation information based on image learning
KR101186952B1 (en) Vessel navigation monitoring system
KR20220125398A (en) Ship Safety Operation Support System
CN112686106A (en) Method for converting video image into maritime radar image
CN115798128A (en) Offshore wind farm alarm system and method based on AIS, radar and tripod head linkage
CN207233223U (en) Bridge intelligent anti-collision system module connection structure
KR101258950B1 (en) Vessel monitoring apparatus for unidentified vessel, vessel monitoring system having the same and method for monitoring vessel
CN115311900A (en) Inland waterway ship auxiliary target identification system and method based on visual enhancement

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant