CN120851625B - A method and system for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion - Google Patents

A method and system for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion

Info

Publication number
CN120851625B
CN120851625B CN202511350984.0A CN202511350984A CN120851625B CN 120851625 B CN120851625 B CN 120851625B CN 202511350984 A CN202511350984 A CN 202511350984A CN 120851625 B CN120851625 B CN 120851625B
Authority
CN
China
Prior art keywords
personnel
grab bucket
risk
trajectory
movement
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
CN202511350984.0A
Other languages
Chinese (zh)
Other versions
CN120851625A (en
Inventor
冯周
庄臣
关添海
陈春春
饶来庆
李靖哲
王丽娜
皋爽
舒鹏
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.)
Jiangsu Sugang Intelligent Equipment Industry Innovation Center Co ltd
Nanjing Port Machinery & Heavy Industry Manufacture Co ltd
Original Assignee
Jiangsu Sugang Intelligent Equipment Industry Innovation Center Co ltd
Nanjing Port Machinery & Heavy Industry Manufacture Co ltd
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 Jiangsu Sugang Intelligent Equipment Industry Innovation Center Co ltd, Nanjing Port Machinery & Heavy Industry Manufacture Co ltd filed Critical Jiangsu Sugang Intelligent Equipment Industry Innovation Center Co ltd
Priority to CN202511350984.0A priority Critical patent/CN120851625B/en
Publication of CN120851625A publication Critical patent/CN120851625A/en
Application granted granted Critical
Publication of CN120851625B publication Critical patent/CN120851625B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/002—Generating a prealarm to the central station
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/016—Personal emergency signalling and security systems
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30241—Trajectory

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Emergency Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Educational Administration (AREA)
  • Human Computer Interaction (AREA)
  • Medical Informatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Development Economics (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Electromagnetism (AREA)
  • Game Theory and Decision Science (AREA)
  • Computing Systems (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Security & Cryptography (AREA)

Abstract

本发明涉及的码头装卸防砸监测技术领域，具体公开了一种基于多传感器融合的船舱作业人员防砸方法及系统，本发明通过获取抓斗运动轨迹以及人员运动轨迹，根据抓斗运动轨迹动态划定安全区域与非安全区域，对于在非安全区域的人员运动轨迹进行防砸风险识别，基于UWB定位单元获取抓斗运动信号以及人员运动信号，将非安全区域内的抓斗运动轨迹与抓斗运动信号结合核对第一轨迹匹配度，人员运动轨迹与人员运动信号结合核对第二轨迹匹配度，根据第一轨迹匹配度以及第二轨迹匹配度核实防砸风险的真实性，对于确定存在的防砸风险划分风险等级，通过多传感器融合，实现动态安全区划定、精准风险识别、风险核实和分级干预，保证了船舱作业人员的安全。

This invention relates to the field of anti-collision monitoring technology for dock loading and unloading, specifically disclosing a method and system for preventing collisions with personnel working in ship holds based on multi-sensor fusion. This invention acquires the movement trajectory of the grab bucket and the movement trajectory of personnel, dynamically delineates safe and unsafe zones based on the grab bucket's movement trajectory, identifies collision risks for personnel movement trajectories in unsafe zones, acquires grab bucket movement signals and personnel movement signals based on UWB positioning units, combines the grab bucket's movement trajectory and the grab bucket's movement signals in unsafe zones to verify a first trajectory matching degree, and combines the personnel movement trajectory and the personnel movement signals to verify a second trajectory matching degree. The authenticity of the collision risk is verified based on the first and second trajectory matching degrees, and risk levels are assigned to identified collision risks. Through multi-sensor fusion, dynamic safe zone delineation, accurate risk identification, risk verification, and graded intervention are achieved, ensuring the safety of personnel working in ship holds.

Description

Cabin operator smashing prevention method and system based on multi-sensor fusion
Technical Field
The invention relates to the technical field of wharf loading and unloading anti-smashing monitoring, in particular to a cabin worker anti-smashing method and system based on multi-sensor fusion.
Background
Because the cabin space is relatively closed and the illumination is insufficient, cabin cleaning workers, commanders and the like must enter the cabin to cooperatively work, and often cross the grab bucket working area. The safety protection method is limited by the factors of complex cabin environment, serious dust interference, multiple sight blind areas and the like, the traditional safety protection method which depends on the experience of operators and the communication of interphones is obviously insufficient, and the risk that the operators are injured by smashing due to accidental falling or swinging of the grab bucket is easy to occur.
At present, a camera or a laser radar and other single sensors are relied on to detect personnel and a grab bucket, but under the conditions of low illumination of a cabin, dust interference and cargo shielding, the problem of inaccurate identification or high false alarm rate often occurs, and the existing system only relies on an audible and visual alarm prompt, and cannot form linkage with personnel wearing equipment or mechanical control of the grab bucket, so that dangerous actions are difficult to block in time.
Therefore, it is necessary to provide a method and a system for preventing a cabin worker from smashing based on multi-sensor fusion, and in order to solve the above problems, a technical scheme is provided.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a multi-sensor fusion-based method and a multi-sensor fusion-based system for preventing smashing of cabin operators, which are used for detecting personnel and a grab bucket by means of a single sensor such as a camera or a laser radar at present, but the problems of inaccurate identification or high false alarm rate often occur under the conditions of low illumination, dust interference and goods shielding of the cabin, and the existing system is mainly based on acousto-optic alarm prompt, cannot form linkage with personnel wearing equipment or mechanical control of the grab bucket, and is difficult to block dangerous actions in time.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A cabin worker smashing prevention method based on multi-sensor fusion comprises the following steps:
Acquiring a grab bucket movement track and a personnel movement track through laser radar real-time scanning, and dynamically defining a safe area and a non-safe area according to the grab bucket movement track;
Carrying out smashing prevention risk identification on the personnel movement track in the unsafe area, and judging smashing prevention risk according to the grab bucket movement track and the personnel movement track in the unsafe area;
For an unsafe area with anti-smashing risk, acquiring grab bucket movement signals and personnel movement signals based on a UWB positioning unit, combining grab bucket movement tracks in the unsafe area with the grab bucket movement signals to check the first track matching degree, combining personnel movement tracks with the personnel movement signals to check the second track matching degree, and checking the authenticity of the anti-smashing risk according to the first track matching degree and the second track matching degree;
And triggering a crane PLC execution module to link grab bucket control operation and warning personnel according to the risk classification result for determining the risk classification risk level of the smashing prevention.
As a further scheme of the invention, the motion trail of the grab bucket and the motion trail of the personnel are obtained through laser radar real-time scanning, and a safe area and a non-safe area are dynamically defined according to the motion trail of the grab bucket, and the method comprises the following specific steps:
The method comprises the steps of scanning and collecting three-dimensional point clouds of a cabin operation area in real time through a laser radar, respectively identifying grab bucket targets and personnel targets through a point cloud clustering and tracking algorithm, respectively performing motion trail fitting based on the grab bucket targets and the personnel targets to obtain grab bucket motion trails and personnel motion trails, extracting first space motion characteristics based on the grab bucket motion trails, and extracting second space motion characteristics based on the personnel motion trails, wherein the space motion characteristics comprise speed characteristics and acceleration characteristics;
and extracting the grab bucket movement track and the first space movement characteristic to dynamically define an unsafe area, and marking the area except the unsafe area of the cabin operation area as the safe area.
The method comprises the specific steps of obtaining a grab bucket movement track point gamma 1(t)＝(x1(t),y1(t),z1 (t)) at the moment t, wherein (x 1(t),y1(t),z1 (t)) is the position coordinate of the grab bucket centroid at the moment t, and defining a neighborhood omega 1 (t) of the grab bucket movement track gamma 1 (t);
Predicting a grab bucket movement track Γ 1 (t+DeltaT) in a sampling period DeltaT time period;
Predicting unsafe areas based on grab bucket movement tracks in a sampling period delta T time period to obtain omega 1 (t+delta T), calculating each sampling period delta T to obtain corresponding unsafe areas, and performing intersection operation based on the corresponding unsafe areas and personnel movement tracks gamma 2(t)＝(x2(t),y2(t),z2 (T)) to obtain R ns(t)＝Ω1(t+ΔT)∩Γ2 (T);
R ns (T) is an intersection output result, omega 1 (t+DeltaT) is a corresponding unsafe region in a sampling period DeltaT time period, and Γ 2 (T) is a personnel movement track at the moment T;
and dynamically judging whether the personnel are in the unsafe area according to the intersection output result, if the intersection output result is not an empty set, judging that the personnel are in the unsafe area, and if the intersection output result is an empty set, judging that the personnel are in the safe area.
Analyzing the track coincidence degree according to the grab bucket movement track and the personnel movement track in the unsafe area, judging the anti-smashing risk, and specifically comprising the following steps:
If the person is in the unsafe area, acquiring the grab bucket movement track and the person movement track at the moment, and calculating the intersection proportion of the two movement tracks in a time window as the track coincidence ratio;
And comparing the track overlap ratio with a preset threshold, if the track overlap ratio is greater than or equal to the preset threshold, primarily judging that the risk exists, and if the track overlap ratio is less than the preset threshold, primarily judging that the risk does not exist.
As a further scheme of the invention, for the unsafe area with risk of smashing prevention, a grab bucket movement signal and a personnel movement signal are acquired based on a UWB positioning unit, the grab bucket movement track in the unsafe area is combined with the grab bucket movement signal to check the first track matching degree, the personnel movement track is combined with the personnel movement signal to check the second track matching degree, and the authenticity of the risk of smashing prevention is checked according to the first track matching degree and the second track matching degree, and the specific steps are as follows:
positioning base stations in the UWB positioning units are deployed at four corners of a cabin operation area, a first UWB signal is obtained through a first positioning tag on a personnel helmet, and a second UWB signal is obtained based on a second positioning tag on a grab bucket;
Respectively carrying out two-way distance measurement on the first positioning tag and the second positioning tag with four base stations, and calculating to obtain the distance from the first positioning tag to each base station as a first distance, and the distance from the second positioning tag to each base station as a second distance;
Transmitting the first distance and the second distance to a central positioning engine through a wired network;
the central positioning engine respectively calculates real-time three-dimensional coordinates of the grab bucket and real-time three-dimensional coordinates of a helmet wearer according to the first distance and the second distance by using a trilateration method, and takes the real-time three-dimensional coordinates of the grab bucket as grab bucket movement signals and the real-time three-dimensional coordinates of the helmet wearer as personnel movement signals;
The method comprises the steps of obtaining a grab bucket movement track and a personnel movement track, calculating Euclidean distance between the grab bucket movement track and a grab bucket movement signal at the same time in real time as a first distance value, calculating Euclidean distance between the personnel movement track and the personnel movement signal at the same time as a second distance value, comparing the first distance value and the second distance value with a preset distance threshold value respectively, if the first distance value is larger than or equal to the preset distance threshold value, the authenticity of the anti-smashing risk is unreliable, if the first distance value is smaller than the preset distance threshold value, the authenticity of the anti-smashing risk is reliable, if the second distance value is larger than or equal to the preset distance threshold value, the authenticity of the anti-smashing risk is unreliable, and if the second distance value is smaller than the preset distance threshold value, the authenticity of the anti-smashing risk is reliable.
As a further scheme of the invention, for determining the risk classification risk level of the existing anti-smashing risk, triggering a crane PLC execution module to link with grab bucket control operation and warning personnel according to the risk classification result, the concrete steps are as follows:
When the authenticity of the anti-smashing risk is reliable, the safety distance is automatically adjusted according to the state of the grab bucket, wherein the calculation formula of the safety distance is D safe＝k·(Vgrab·Tresp+Lgrab), D safe is the safety distance, k is the safety coefficient, V grab is the instantaneous speed of the grab bucket, T resp is the response time, and L grab is the projection length of the grab bucket;
And (3) classifying risk grades according to the safety distance, triggering a crane PLC execution module to link grab bucket control operation according to a risk grade classification result, and carrying out personnel warning.
As a further aspect of the invention, the safety factor k in the calculation formula of the safety distance is 1.2 when the grab is empty and 1.5 when the grab is full.
As a further scheme of the invention, the control operation of the crane PLC execution module linked grab bucket is triggered according to the risk classification result and the personnel warning is carried out, and the specific steps comprise:
triggering a first-level early warning when D safe<D1(τ)≤1.2Dsafe is carried out, and enabling staff to wear UWB bracelet to carry out vibration reminding at the moment;
when the speed of the AR glasses is 0.8D safe<D1(τ)≤Dsafe, triggering a secondary early warning, automatically decelerating the grab bucket at the moment, and displaying a red warning area as an unsafe area by the AR glasses worn by the personnel;
When D 1(τ)≤0.8Dsafe is carried out, triggering three-level early warning, hovering the grab bucket at the moment, and starting audible and visual warning.
A cabin worker anti-smashing system based on multi-sensor fusion comprises a sensing layer, a control layer, an interaction layer and a mechanical execution layer, wherein the sensing layer comprises a laser radar, a UWB positioning unit and a grab bucket state acquisition module;
The control layer comprises a region dividing module, an anti-smashing risk identification module, a risk authenticity checking module and a risk grade dividing module;
the interaction layer comprises UWB hand rings and AR glasses;
the mechanical execution layer comprises a crane PLC execution module.
As a further scheme of the invention, the laser radar is arranged on the arm support head and is used for scanning and acquiring the grab bucket movement track and the personnel movement track in real time;
The system comprises a UWB positioning unit, a grab bucket state acquisition module, a first positioning module, a second positioning module and a first positioning module, wherein the UWB positioning unit is used for comprising a positioning base station, a first positioning tag and a first positioning tag;
The region dividing module is used for acquiring the grab bucket movement track and the personnel movement track through laser radar real-time scanning, and dynamically dividing a safe region and a non-safe region according to the grab bucket movement track;
The anti-smashing risk identification module is used for carrying out anti-smashing risk identification on the personnel movement track in the unsafe area, and judging the anti-smashing risk according to the grab bucket movement track and the personnel movement track analysis track coincidence degree in the unsafe area;
the risk authenticity checking module is used for acquiring grab bucket movement signals and personnel movement signals based on the UWB positioning unit for unsafe areas with risk of smashing, combining grab bucket movement tracks in the unsafe areas with the grab bucket movement signals to check the first track matching degree, combining personnel movement tracks with the personnel movement signals to check the second track matching degree, and checking the authenticity of risk of smashing according to the first track matching degree and the second track matching degree;
The UWB bracelet is used for prompting personnel evacuation by vibration alarm;
The AR glasses are used for displaying the unsafe area as a red warning area;
the crane PLC execution module is used for controlling operation of the grab bucket in a linkage mode according to the risk grade division module and alarming personnel.
According to the invention, a safe area and a non-safe area are dynamically defined according to the grab bucket movement track and the personnel movement track, the personnel movement track in the non-safe area is subjected to anti-smashing risk identification, a grab bucket movement signal and a personnel movement signal are acquired based on a UWB positioning unit, the grab bucket movement track and the grab bucket movement signal in the non-safe area are combined and checked for a first track matching degree, the personnel movement track and the personnel movement signal are combined and checked for a second track matching degree, the authenticity of anti-smashing risk is checked according to the first track matching degree and the second track matching degree, and for determining the existing anti-smashing risk classification risk level, dynamic safety area demarcation, accurate risk identification, risk verification and grading intervention are realized through multi-sensor fusion, so that the safety of the ship cabin operation personnel is ensured.
According to the invention, through multi-sensor fusion, dynamic safety area, track coincidence analysis, UWB signal verification and risk grading linkage control, accurate anti-smashing protection of cabin operators is realized, the problem of high false alarm rate of a single sensor is solved, the reliability of the system in a severe environment is enhanced, and the comprehensive protection effect of combining early warning, real-time intervention and automatic risk avoidance is realized through a man-machine linkage control mechanism.
Drawings
FIG. 1 is a flow chart of a cabin worker smashing prevention method based on multi-sensor fusion, which is provided by the embodiment of the invention;
Fig. 2 is a system block diagram of a cabin worker smashing prevention system based on multi-sensor fusion, which is provided by the embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made in detail, but not necessarily with reference to the accompanying drawings. Based on the technical scheme in the invention, all other technical schemes obtained by a person of ordinary skill in the art without making creative work fall within the protection scope of the invention.
As shown in fig. 1, a flowchart of a method for preventing a cabin worker from smashing based on multi-sensor fusion is provided in an embodiment of the present application, and an execution subject of the method shown in fig. 1 may be a software and/or hardware device. The execution body of the present application may include, but is not limited to, at least one of a user equipment, a network device, etc. The user device may include, but is not limited to, a computer, a smart phone, a Personal Digital Assistant (PDA), and the above-mentioned electronic device. The network device may include, but is not limited to, a single network server, a server group of multiple network servers, or a cloud of a large number of computers or network servers based on cloud computing, where cloud computing is one of distributed computing, and a super virtual computer consisting of a group of loosely coupled computers. This embodiment is not limited thereto. The method comprises the steps S1 to S4, and specifically comprises the following steps:
s1, acquiring a grab bucket movement track and a personnel movement track through laser radar real-time scanning, and dynamically defining a safe area and a non-safe area according to the grab bucket movement track;
S2, carrying out anti-smashing risk identification on the personnel movement track in the unsafe area, and judging the anti-smashing risk according to the grab bucket movement track and the personnel movement track in the unsafe area by analyzing the track coincidence degree;
S3, for the unsafe area with the risk of smashing prevention, acquiring grab bucket movement signals and personnel movement signals based on the UWB positioning unit, combining the grab bucket movement track in the unsafe area with the grab bucket movement signals to check the first track matching degree, combining the personnel movement track with the personnel movement signals to check the second track matching degree, and checking the authenticity of the risk of smashing prevention according to the first track matching degree and the second track matching degree;
And S4, for determining the risk classification risk level of the existing smashing prevention, triggering a crane PLC execution module to link the grab bucket to control operation and warning personnel according to the risk classification result.
Preferably, the motion trail of the grab bucket and the motion trail of the personnel are obtained through laser radar real-time scanning, and a safe area and a non-safe area are dynamically defined according to the motion trail of the grab bucket, and the method specifically comprises the following steps:
The method comprises the steps of scanning and collecting three-dimensional point clouds of a cabin operation area in real time through a laser radar, respectively identifying grab bucket targets and personnel targets through a point cloud clustering and tracking algorithm, respectively performing motion trail fitting based on the grab bucket targets and the personnel targets to obtain grab bucket motion trails and personnel motion trails, extracting first space motion characteristics based on the grab bucket motion trails, and extracting second space motion characteristics based on the personnel motion trails, wherein the space motion characteristics comprise speed characteristics and acceleration characteristics;
and extracting the grab bucket movement track and the first space movement characteristic to dynamically define an unsafe area, and marking the area except the unsafe area of the cabin operation area as the safe area.
In the cabin operation process, laser radar equipment arranged at the hatch position is utilized to scan an operation area in real time, and three-dimensional point cloud information of the whole cabin operation environment is obtained. The point cloud data contains various target objects such as grab buckets, operators and cargoes. Different point cloud clusters are distinguished through a point cloud clustering algorithm, and a clustering result is dynamically identified and tracked by combining a target tracking algorithm, so that effective separation and identification of a grab bucket target and a personnel target are realized. And then, generating motion tracks of the identified grab bucket targets and the identified personnel targets along with time by using a fitting algorithm, so as to obtain the grab bucket motion track and the personnel motion track.
On the basis of track generation, the first space motion characteristics including speed characteristics and acceleration characteristics of the grab bucket in each time segment are further extracted from the grab bucket motion track, and the characteristics can accurately reflect the running state and possible future motion trend of the grab bucket. And likewise, extracting a second space motion characteristic for the motion trail of the personnel, and describing the moving speed and acceleration change condition of the personnel in the working area.
And then, dynamically defining an unsafe area, namely a dangerous space range which can be covered and influenced by the grab bucket in a short time by taking the grab bucket movement track and the corresponding first space movement characteristic as the basis and combining the running direction, the running speed and the projection range of the grab bucket. The unsafe area can be dynamically adjusted along with the real-time updating of the grab bucket movement track, and the real-time performance and accuracy of dangerous area division are ensured. The work area other than the safe area is automatically marked as a safe area for personnel activities and work. By the method, dynamic safety area division can be realized in a complex cabin operation environment, and potential collision or drop risk caused by grab bucket movement is avoided.
Preferably, the method comprises the steps of extracting a grab bucket movement track and a first space movement feature to dynamically define an unsafe region, wherein the specific steps are that a grab bucket movement track point gamma 1(t)＝(x1(t),y1(t),z1 (t) at the moment t is obtained, wherein (x 1(t),y1(t),z1 (t)) is the position coordinate of the grab bucket mass center at the moment t, and the neighborhood of the grab bucket movement track is defined as omega 1(t)＝{(x,y,z)|||(x,y,z)-Γ1(t)||≤R(t)};R(t)＝r0 +alpha v (t) +beta a (t);
wherein omega 1 (t) is the neighborhood of a grab bucket movement track point at the moment t, (x, y, z) is the three-dimensional coordinate of any point in a cabin operation area, R (t) is the neighborhood radius at the moment t, R 0 is the geometric reference radius, alpha is the velocity gain coefficient, v (t) is the velocity characteristic in the first space movement characteristic, beta is the acceleration gain coefficient, and a (t) is the acceleration characteristic in the first space movement characteristic;
predicting the grab bucket movement track in the sampling period delta T time period: Wherein Γ 1 (t+DeltaT) is the grab bucket movement track in the time period of the sampling period DeltaT;
Predicting unsafe areas based on grab bucket movement tracks in a sampling period delta T time period to obtain omega 1 (t+delta T), calculating each sampling period delta T to obtain corresponding unsafe areas, and performing intersection operation based on the corresponding unsafe areas and personnel movement tracks gamma 2(t)＝(x2(t),y2(t),z2 (T)) to obtain R ns(t)＝Ω1(t+ΔT)∩Γ2 (T);
R ns (T) is an intersection output result, omega 1 (t+DeltaT) is a corresponding unsafe region in a sampling period DeltaT time period, and Γ 2 (T) is a personnel movement track at the moment T;
and dynamically judging whether the personnel are in the unsafe area according to the intersection output result, if the intersection output result is not an empty set, judging that the personnel are in the unsafe area, and if the intersection output result is an empty set, judging that the personnel are in the safe area.
In the embodiment of the invention, in the cabin operation process, the barycenter position coordinate of the grab bucket is Γ 1(t)＝(x1(t),y1(t),z1 (t) obtained through a laser radar at the time t. In order to evaluate the possible risk range of the grab, a dynamic neighborhood Ω 1 (t) needs to be established around this location point. The radius R (t) of the neighborhood is not a fixed value, but is adjusted in real time according to the geometric dimension R 0 of the grab and the motion state of the grab, for example, when the grab speed v (t) is higher, the radius of the neighborhood is increased to reflect the expansion of the potential danger zone of the grab at a high speed, and similarly, when the grab acceleration a (t) is higher, the radius is also increased. The omega 1 (t) thus defined reflects the dangerous area of the grab movement more realistically.
Then, during a sampling period DeltaT, the system predicts the next movement position of the grab, Γ 1 (t+DeltaT), the prediction formula taking into account the speed and acceleration of the grab, e.g. if the grab is falling at a speed of 2m/s and has a certain acceleration, then within DeltaT=0.5 s, the predicted Γ 1 (t+DeltaT) will be closer to the real trajectory than a pure linear extrapolation. Based on the predicted position, a corresponding unsafe region Ω 1 (t+Δt) is generated again, thereby forming a dangerous space that dynamically changes over time.
At the same time, the motion trail Γ 2(t)＝(x2(t),y2(t),z2 (t)) of the person is also acquired in real time by the positioning system. For example, a worker is moving along the bulkhead, and the movement track point of the worker is continuously changed. The system calculates the intersection R ns (T) of Γ 2(t)＝(x2(t),y2(t),z2 (T)) with the predicted unsafe region Ω 1 (t+Δt). If the intersection result is not empty, namely the personnel track point falls into the dangerous area predicted by the grab bucket, the system immediately judges that the personnel is in the unsafe area. For example, if a certain calculation result shows that a person will enter the falling path of the grab bucket after 1 second, the system will trigger the anti-smashing risk early warning immediately. Otherwise, if the intersection result is an empty set, the condition that the personnel moving range is not intersected with the grab bucket dangerous area is indicated, and the personnel is judged to be in a safe state without an alarm. According to the embodiment, through the grab bucket track prediction and dynamic unsafe area demarcation and combining the intersection judgment of the real-time tracks of the personnel, the false judgment caused by demarcation only depending on the static area can be effectively avoided, and the accuracy and the instantaneity of the anti-smashing early warning are obviously improved.
Preferably, the method for judging the risk of smashing comprises the following specific steps of:
if the person is in the unsafe area, acquiring the grab bucket movement track and the person movement track at the moment, and calculating the intersection proportion of the two movement tracks in a time window as the track overlap ratio, wherein the calculation formula is as follows:
Wherein eta ΔT is the track coincidence degree in the sampling period delta T time period, D 1(τ)＝d(Γ1(τ),Γ2 (tau)) is the Euclidean distance between the grab bucket movement track and the personnel movement track at the moment tau, D th is a dangerous threshold, delta is an indication function, the output result of the meeting condition is 1, the output result of the non-meeting condition is 0,
In order that the moment distance between the grab bucket movement track and the personnel movement track is smaller than the accumulated duration of the dangerous threshold value in the time window [ T, t+delta T ];
And comparing the track overlap ratio with a preset threshold, if the track overlap ratio is greater than or equal to the preset threshold, primarily judging that the risk exists, and if the track overlap ratio is less than the preset threshold, primarily judging that the risk does not exist.
In actual cabin operation, after the system detects that the personnel track enters the unsafe area predicted by the grab bucket, the coincidence condition of the grab bucket movement track and the personnel movement track in a period of time is further analyzed. Assuming that the motion trajectory of the grab bucket centroid is Γ 1 (τ) and the motion trajectory of the person is Γ 2 (τ) within the time window [ T, t+Δt ], the system first calculates the euclidean distance D 1(τ)＝d(Γ1(τ),Γ2 (τ) of both at each instant by time. For example, when the grab bucket approaches the bilge during the descent phase, and the personnel just enters the hatch work area, if the distance between the two at a plurality of moments τ is less than the danger threshold D th, the output of the indication function δ (D 1(τ)<dth) is 1, which indicates that there is a potential collision risk at that moment, and if the distance is greater than the threshold, the output is 0, which indicates that the moment is relatively safe.
Then, the system integrates the results of all the moments in the whole time window [ T, t+delta T ] to obtain the accumulated duration of the dangerous distance state between the grab bucket and the personnel, and divides the duration by the length delta T of the time window to obtain the track coincidence degree eta ΔT. For example, if the duration of the grab bucket to person distance less than the hazard threshold is 3 seconds within a predicted time window of 5 seconds, the trajectory overlap ratio is η ΔT =0.6.
Preferably, for an unsafe area with risk of smashing prevention, a grab bucket motion signal and a personnel motion signal are acquired based on a UWB positioning unit, a grab bucket motion track in the unsafe area is combined with the grab bucket motion signal to check a first track matching degree, the personnel motion track is combined with the personnel motion signal to check a second track matching degree, and authenticity of the risk of smashing prevention is checked according to the first track matching degree and the second track matching degree, and the method comprises the following specific steps of:
positioning base stations in the UWB positioning units are deployed at four corners of a cabin operation area, a first UWB signal is obtained through a first positioning tag on a personnel helmet, and a second UWB signal is obtained based on a second positioning tag on a grab bucket;
Respectively carrying out two-way distance measurement on the first positioning tag and the second positioning tag with four base stations, and calculating to obtain the distance from the first positioning tag to each base station as a first distance, and the distance from the second positioning tag to each base station as a second distance;
Transmitting the first distance and the second distance to a central positioning engine through a wired network;
the central positioning engine respectively calculates real-time three-dimensional coordinates of the grab bucket and real-time three-dimensional coordinates of a helmet wearer according to the first distance and the second distance by using a trilateration method, and takes the real-time three-dimensional coordinates of the grab bucket as grab bucket movement signals and the real-time three-dimensional coordinates of the helmet wearer as personnel movement signals;
acquiring a grab bucket movement track and a personnel movement track, calculating Euclidean distance between the grab bucket movement track and a grab bucket movement signal at the same moment in real time to serve as a first distance value, and calculating Euclidean distance between the personnel movement track and the personnel movement signal at the same moment to serve as a second distance value;
the first distance value and the second distance value are respectively compared with a preset distance threshold, if the first distance value is larger than or equal to the preset distance threshold, the authenticity of the anti-smashing risk is unreliable, if the first distance value is smaller than the preset distance threshold, the authenticity of the anti-smashing risk is reliable, if the second distance value is larger than or equal to the preset distance threshold, the authenticity of the anti-smashing risk is unreliable, and if the second distance value is smaller than the preset distance threshold, the authenticity of the anti-smashing risk is reliable.
In the embodiment of the invention, in a certain operation in the actual cabin operation process, the grab bucket falls down to take materials, a worker enters an unsafe area of the grab bucket, a grab bucket movement track and a personnel movement track are established through the laser radar, and the high track overlapping degree of the grab bucket movement track and the personnel movement track is judged, so that the risk of smashing prevention is primarily judged. To further verify the authenticity of the risk, the UWB positioning unit is activated for verification.
Four UWB base stations which are deployed in advance at four corners of the cabin start to work. The first positioning tag mounted on the helmet of the worker continuously transmits signals to the four base stations, and the system obtains a first distance from the tag to each base station through two-way ranging. Likewise, a second locating tag mounted on the grab bucket communicates with the base stations to obtain a second distance from each base station, and the data are transmitted to the central locating engine in real time through the wired network.
The central positioning engine calculates the first distance to obtain the three-dimensional coordinate of the worker at the moment by using a trilateration method, and calculates the second distance to obtain the three-dimensional coordinate of the grab bucket. Thus, the real-time position of the worker is defined as the personnel movement signal and the real-time position of the grapple is defined as the grapple movement signal.
Next, the motion trajectory of the grapple is compared with the real-time motion signal of the grapple. For example, at some point in time, the Euclidean distance between the predicted grapple position and the actual coordinates of the grapple measured by UWB is 0.15m, and the preset distance threshold is 0.3m. Since 0.15m is smaller than 0.3m, the predicted track of the grab bucket is highly matched with the actual motion, and the first track matching degree is reliable. Similarly, the system compares the worker's motion profile with the actual position of the person measured by the UWB. If the calculated Euclidean distance is 0.12m and is smaller than a preset threshold value of 0.3m, the fact that the movement track of the person is consistent with the actual signal height is indicated, and the second track matching degree is reliable.
When the first distance value and the second distance value are both smaller than the threshold value, the track information is considered to be highly matched with the UWB signal, namely the authenticity of the anti-smashing risk is reliable, the fact that the worker is in the dangerous area of the grab bucket falling is indicated, the real anti-smashing risk exists, and high-level early warning is immediately sent out and emergency linkage is triggered. If the deviation between the predicted track of the grab bucket and the actual signal is too large in a certain comparison, for example, the first distance value reaches 0.5m and is higher than the threshold value 0.3m, the track prediction is indicated to be possibly deviated, at the moment, the authenticity of the anti-smashing risk is in doubt, and the system marks the risk as unreliable and prompts to recheck.
By the mode, the motion trail of the grab bucket and the personnel can be calibrated by utilizing the real-time motion signals provided by the UWB positioning unit on the basis of preliminary risk judgment, so that the real-time performance and the reliability of final anti-smashing risk identification are ensured, and the situations of false alarm and missing report are avoided.
Preferably, for determining the risk classification risk level of the existing smashing prevention, triggering a crane PLC execution module to link grab bucket control operation and warning personnel according to the risk classification result, wherein the concrete steps are as follows:
When the authenticity of the anti-smashing risk is reliable, the safety distance is automatically adjusted according to the state of the grab bucket, the calculation formula of the safety distance is D safe＝k·(Vgrab·Tresp+Lgrab), wherein D safe is the safety distance, k is the safety coefficient, V grab is the instantaneous speed of the grab bucket, T resp is the response time, L grab is the projection length of the grab bucket, wherein the safety coefficient k is 1.2 when the grab bucket is empty and 1.5 when the grab bucket is full, the risk grade is divided according to the safety distance, and the PLC execution module of the crane is triggered to link the grab bucket to control the operation and warn personnel according to the risk grade division result.
Preferably, triggering a crane PLC execution module to link grab bucket control operation and warn personnel according to a risk classification result, wherein the specific steps comprise:
triggering a first-level early warning when D safe＜D1(τ)≤1.2Dsafe is carried out, and enabling staff to wear UWB bracelet to carry out vibration reminding at the moment;
When the speed of the AR glasses is 0.8D safe＜D1(τ)≤Dsafe, triggering a secondary early warning, automatically decelerating the grab bucket at the moment, and displaying a red warning area as an unsafe area by the AR glasses worn by the personnel;
When D 1(τ)≤0.8Dsafe is carried out, triggering three-level early warning, hovering the grab bucket at the moment, and starting audible and visual warning.
In cabin operation, after the risk of smashing prevention is verified through laser radar and UWB combined positioning, risk grades are further classified according to states of the grab bucket and real-time motion parameters. At a certain moment, the grab bucket is in a full-load state, the system detects that the instantaneous speed of the grab bucket is 1.5m/s, the response time is set to be 0.8s, and the projection length of the grab bucket is 2.0m. Firstly, safety distance calculation is carried out according to a calculation formula of the safety distance, wherein the safety coefficient k=1.5 when the vehicle is fully loaded. Substituting data gives D safe =1.5· (1.5×0.8+2.0) =4.8 m, i.e. a safety distance of 4.8m.
The real-time relative distance D 1 (τ) of the grapple from the operator is then compared to the safety distance D safe. If the shortest distance between a worker and the grab bucket is monitored to be 5.2m and D safe<D1(τ)≤1.2Dsafe is met, namely, 4.8m <5.2m is less than or equal to 5.76m, the primary early warning is triggered. At this time, the UWB bracelet worn by the worker can vibrate to remind, and prompt personnel to pay attention to keeping a safe distance.
If the relative distance between the other worker and the grab bucket is shortened to 4.5m at a certain moment, and 0.8D safe＜D1(τ)≤Dsafe is met, namely 3.84m <4.5m < 4.8m, the risk is judged to be increased to the second-level early warning. At this time, the grab bucket control system automatically performs a deceleration operation, and marks the unsafe area as a red warning area in the AR glasses worn by the worker, further enhancing warning.
If in extreme cases, a person suddenly enters the position right below the grab bucket and keeps a distance of 3.5m with the grab bucket, D 1(τ)≤0.8Dsafe is met, namely, the distance is less than or equal to 3.84m, and three-level early warning is triggered immediately. At the moment, the grab bucket can hover emergently, and meanwhile, the audible and visual alarm device is triggered, so that operators can sense danger and withdraw from a dangerous area at the first time, and the risk of smashing down accidents is reduced to the greatest extent.
A cabin worker smash-proof system based on multi-sensor fusion comprises a sensing layer, a control layer, an interaction layer and a mechanical execution layer:
The sensing layer comprises a laser radar, a UWB positioning unit and a grab bucket state acquisition module;
The control layer comprises a region dividing module, an anti-smashing risk identification module, a risk authenticity checking module and a risk grade dividing module;
the interaction layer comprises UWB hand rings and AR glasses;
the mechanical execution layer comprises a crane PLC execution module.
The system comprises a cantilever crane, a laser radar, a grab bucket state acquisition module, a PLC, a first positioning tag, a second positioning tag, a first UWB signal and a second UWB signal, wherein the laser radar is arranged at the head of the cantilever crane and used for scanning and acquiring the motion trail of the grab bucket and the motion trail of personnel in real time;
The region dividing module is used for acquiring the grab bucket movement track and the personnel movement track through laser radar real-time scanning, and dynamically dividing a safe region and a non-safe region according to the grab bucket movement track;
The anti-smashing risk identification module is used for carrying out anti-smashing risk identification on the personnel movement track in the unsafe area, and judging the anti-smashing risk according to the grab bucket movement track and the personnel movement track analysis track coincidence degree in the unsafe area;
the risk authenticity checking module is used for acquiring grab bucket movement signals and personnel movement signals based on the UWB positioning unit for unsafe areas with risk of smashing, combining grab bucket movement tracks in the unsafe areas with the grab bucket movement signals to check the first track matching degree, combining personnel movement tracks with the personnel movement signals to check the second track matching degree, and checking the authenticity of risk of smashing according to the first track matching degree and the second track matching degree;
The UWB bracelet is used for prompting personnel evacuation by vibration alarm;
The AR glasses are used for displaying the unsafe area as a red warning area;
the crane PLC execution module is used for controlling operation of the grab bucket in a linkage mode according to the risk grade division module and alarming personnel.
As shown in fig. 2, a system block diagram of a cabin worker smash-proof system based on multi-sensor fusion according to an embodiment of the present invention is correspondingly applicable to executing steps in the method embodiment shown in fig. 1, and its implementation principle and technical effects are similar, and are not repeated here.
By introducing the embodiment, the safety area and the non-safety area are dynamically defined according to the grab bucket movement track and the personnel movement track, the personnel movement track in the non-safety area is subjected to anti-smashing risk identification, the grab bucket movement signal and the personnel movement signal are obtained based on the UWB positioning unit, the grab bucket movement track in the non-safety area and the grab bucket movement signal are combined and checked to form a first track matching degree, the personnel movement track and the personnel movement signal are combined and checked to form a second track matching degree, the authenticity of the anti-smashing risk is checked according to the first track matching degree and the second track matching degree, and the dynamic safety area definition, accurate risk identification, risk verification and grading intervention are realized through multi-sensor fusion, so that the safety of cabin operation personnel is ensured.
According to the invention, through multi-sensor fusion, dynamic safety area, track coincidence analysis, UWB signal verification and risk grading linkage control, accurate anti-smashing protection of cabin operators is realized, the problem of high false alarm rate of a single sensor is solved, the reliability of the system in a severe environment is enhanced, and the comprehensive protection effect of combining early warning, real-time intervention and automatic risk avoidance is realized through a man-machine linkage control mechanism.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Finally, the foregoing is merely illustrative of the preferred embodiments of the present invention and is not intended to limit the invention thereto, and any modifications, equivalents, improvements or the like made within the spirit and principles of the present invention are intended to be included within the scope of the present invention.

Claims (10)

1.一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，包括以下步骤：1. A method for preventing personnel from being struck by objects while working in a ship's cabin based on multi-sensor fusion, characterized by comprising the following steps: 通过激光雷达实时扫描获取抓斗运动轨迹以及人员运动轨迹，根据抓斗运动轨迹动态划定安全区域与非安全区域；The movement trajectory of the grab bucket and personnel is obtained in real time by LiDAR scanning, and safe and unsafe areas are dynamically delineated based on the movement trajectory of the grab bucket. 对于在非安全区域的人员运动轨迹进行防砸风险识别，根据非安全区域内的抓斗运动轨迹以及人员运动轨迹分析轨迹重合度，判别防砸风险；For personnel movement trajectories in unsafe areas, anti-collision risk identification is performed. The overlap of trajectories is analyzed based on the movement trajectory of the grab bucket and personnel movement trajectories in unsafe areas to determine the anti-collision risk. 对于存在防砸风险的非安全区域，基于UWB定位单元获取抓斗运动信号以及人员运动信号，将非安全区域内的抓斗运动轨迹与抓斗运动信号结合核对第一轨迹匹配度，人员运动轨迹与人员运动信号结合核对第二轨迹匹配度，根据第一轨迹匹配度以及第二轨迹匹配度核实防砸风险的真实性，具体方案包括：For unsafe areas with potential impact risks, the movement signals of the grab bucket and personnel are acquired using UWB positioning units. The grab bucket movement trajectory within the unsafe area is combined with the grab bucket movement signal to verify the first trajectory matching degree, and the personnel movement trajectory is combined with the personnel movement signal to verify the second trajectory matching degree. The authenticity of the impact risk is verified based on the first and second trajectory matching degrees. Specific solutions include: 实时计算同时刻抓斗运动轨迹与抓斗运动信号之间的欧几里得距离作为第一距离值，计算同时刻人员运动轨迹与人员运动信号之间的欧几里得距离作为第二距离值；The Euclidean distance between the grab's movement trajectory and the grab's movement signal at the same moment is calculated in real time as the first distance value, and the Euclidean distance between the personnel's movement trajectory and the personnel's movement signal at the same moment is calculated as the second distance value. 分别将第一距离值以及第二距离值与预设距离阈值进行对比，若第一距离值大于等于预设距离阈值，则防砸风险的真实性不可靠；若第一距离值小于预设距离阈值；则防砸风险的真实性可靠；若第二距离值大于等于预设距离阈值，则防砸风险的真实性不可靠；若第二距离值小于预设距离阈值，则防砸风险的真实性可靠；The first distance value and the second distance value are compared with the preset distance threshold respectively. If the first distance value is greater than or equal to the preset distance threshold, the authenticity of the anti-smashing risk is unreliable; if the first distance value is less than the preset distance threshold, the authenticity of the anti-smashing risk is reliable. If the second distance value is greater than or equal to the preset distance threshold, the authenticity of the anti-smashing risk is unreliable; if the second distance value is less than the preset distance threshold, the authenticity of the anti-smashing risk is reliable. 对于确定存在的防砸风险划分风险等级，根据风险等级划分结果触发起重机PLC执行模块联动抓斗控制操作并进行人员警示。Once an existing risk of falling debris is identified, a risk level is assigned. Based on the risk level assignment, the crane's PLC execution module is triggered to control the grab bucket and issue a warning to personnel. 2.根据权利要求1所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，通过激光雷达实时扫描获取抓斗运动轨迹以及人员运动轨迹，根据抓斗运动轨迹动态划定安全区域与非安全区域，具体步骤如下：2. The method for preventing personnel from being struck by objects in ship cabins based on multi-sensor fusion as described in claim 1, characterized in that the movement trajectory of the grab bucket and the movement trajectory of the personnel are obtained in real time by laser radar scanning, and safe and unsafe areas are dynamically delineated according to the movement trajectory of the grab bucket. The specific steps are as follows: 通过激光雷达实时扫描采集船舱作业区域的三维点云，通过点云聚类以及跟踪算法分别识别抓斗目标以及人员目标，基于抓斗目标以及人员目标分别进行运动轨迹拟合，获取抓斗运动轨迹以及人员运动轨迹，基于抓斗运动轨迹提取第一空间运动特征，并基于人员运动轨迹提取第二空间运动特征；空间运动特征包括速度特征以及加速度特征；The three-dimensional point cloud of the ship's working area is collected in real time by LiDAR scanning. The grab target and personnel target are identified by point cloud clustering and tracking algorithms. Motion trajectory fitting is performed on the grab target and personnel target respectively to obtain the grab motion trajectory and personnel motion trajectory. The first spatial motion feature is extracted based on the grab motion trajectory, and the second spatial motion feature is extracted based on the personnel motion trajectory. The spatial motion features include velocity features and acceleration features. 提取抓斗运动轨迹以及第一空间运动特征动态划定非安全区域，将船舱作业区域除非安全区域以外的区域标记为安全区域。Extract the movement trajectory of the grab bucket and the movement characteristics of the first space to dynamically delineate unsafe areas, and mark the area outside the unsafe area in the cabin operation area as a safe area. 3.根据权利要求2所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，提取抓斗运动轨迹以及第一空间运动特征动态划定非安全区域，具体步骤如下：获取t时刻的抓斗运动轨迹点Γ1(t)＝(x1(t),y1(t),z1(t))，其中，(x1(t)，y1(t)，z1(t))为时刻抓斗质心的位置坐标，定义此时抓斗运动轨迹Γ1(t)的邻域Ω1(t)；3. A method for preventing personnel from being struck by objects in a ship's cabin based on multi-sensor fusion according to claim 2, characterized in that the non-safe area is dynamically delineated by extracting the motion trajectory of the grab bucket and the first spatial motion features, and the specific steps are as follows: obtain the motion trajectory point Γ1 (t) = ( x1 (t), y1 (t), z1 (t)) of the grab bucket at time t, where ( x1 (t), y1 (t), z1 (t)) are the position coordinates of the centroid of the grab bucket at time t, and define the neighborhood Ω1 (t) of the motion trajectory Γ1 (t) of the grab bucket at this time; 对采样周期ΔT时间段内的抓斗运动轨迹Γ1(t+ΔT)进行预测；Predict the trajectory Γ1 (t+ΔT) of the grab bucket within the sampling period ΔT; 基于采样周期ΔT时间段内的抓斗运动轨迹预测非安全区域得到Ω1(t+ΔT)；The unsafe area is predicted based on the grab's motion trajectory within the sampling period ΔT, resulting in Ω 1 (t+ΔT). 对于每个采样周期ΔT进行计算获得对应非安全区域，基于对应非安全区域与人员运动轨迹Γ2(t)＝(x2(t)，y2(t)，z2(t))进行交集运算：For each sampling period ΔT, the corresponding unsafe area is calculated, and the intersection of the corresponding unsafe area and the personnel movement trajectory Γ2 (t)＝( x2 (t), y2 (t), z2 (t)) is performed: Rns(t)＝Ω1(t+ΔT)∩Γ2(t)；R ns (t)=Ω 1 (t+ΔT)∩Γ 2 (t); 式中：Rns(t)为交集输出结果，Ω1(t+ΔT)为采样周期ΔT时间段的对应非安全区域，Γ2(t)为t时刻人员运动轨迹；In the formula: R <sub>ns</sub> (t) is the intersection output result, Ω<sub>1</sub> (t+ΔT) is the corresponding unsafe area during the sampling period ΔT, and Γ <sub>2</sub> (t) is the trajectory of the person at time t; 根据交集输出结果动态判定人员是否处于非安全区域，若交集输出结果非空集，即判定人员处于非安全区域；若交集输出结果为空集，则判定人员处于安全区域。The system dynamically determines whether a person is in an unsafe area based on the intersection output. If the intersection output is not an empty set, the person is determined to be in an unsafe area; if the intersection output is an empty set, the person is determined to be in a safe area. 4.根据权利要求1所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，根据非安全区域内的抓斗运动轨迹以及人员运动轨迹分析轨迹重合度，判别防砸风险，具体步骤如下：4. The method for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion as described in claim 1, characterized in that the risk of being struck by falling objects is determined by analyzing the overlap between the movement trajectory of the grab bucket and the movement trajectory of personnel in the unsafe area, and the specific steps are as follows: 若人员处于非安全区域，获取此时的抓斗运动轨迹以及人员运动轨迹，计算两条运动轨迹在时间窗内的交集比例作为轨迹重合度；If personnel are in an unsafe area, obtain the movement trajectory of the grab bucket and the movement trajectory of the personnel at this time, and calculate the intersection ratio of the two movement trajectories within the time window as the trajectory overlap. 通过将轨迹重合度与预设阈值进行对比，若轨迹重合度大于等于预设阈值，则初步判定存在风险；若轨迹重合度小于预设阈值，则初步判定不存在风险。By comparing the trajectory overlap with a preset threshold, if the trajectory overlap is greater than or equal to the preset threshold, it is initially determined that there is a risk; if the trajectory overlap is less than the preset threshold, it is initially determined that there is no risk. 5.根据权利要求1所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，对于存在防砸风险的非安全区域，基于UWB定位单元获取抓斗运动信号以及人员运动信号，将非安全区域内的抓斗运动轨迹与抓斗运动信号结合核对第一轨迹匹配度，人员运动轨迹与人员运动信号结合核对第二轨迹匹配度，根据第一轨迹匹配度以及第二轨迹匹配度核实防砸风险的真实性，具体步骤如下：5. A method for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion as described in claim 1, characterized in that, for unsafe areas with potential striking risks, the grab's motion signal and personnel motion signal are acquired based on a UWB positioning unit; the grab's motion trajectory within the unsafe area is combined with the grab's motion signal to verify a first trajectory matching degree; the personnel motion trajectory is combined with the personnel motion signal to verify a second trajectory matching degree; and the authenticity of the striking risk is verified based on the first and second trajectory matching degrees. The specific steps are as follows: 将UWB定位单元中定位基站部署于船舱作业区域的四角，通过人员头盔上的第一定位标签获取第一UWB信号，基于抓斗上的第二定位标签获取第二UWB信号；The positioning base stations in the UWB positioning unit are deployed at the four corners of the ship's cabin operation area. The first UWB signal is obtained through the first positioning tag on the personnel's helmet, and the second UWB signal is obtained based on the second positioning tag on the grab bucket. 将第一定位标签以及第二定位标签分别与四个基站进行双向测距，计算获得第一定位标签到每个基站的距离作为第一距离，第二定位标签到每个基站的距离作为第二距离；The first positioning tag and the second positioning tag are respectively used to perform bidirectional ranging with four base stations. The distance from the first positioning tag to each base station is calculated as the first distance, and the distance from the second positioning tag to each base station is calculated as the second distance. 通过有线网络将第一距离以及第二距离传输至中央定位引擎；The first and second distances are transmitted to the central positioning engine via a wired network; 中央定位引擎利用三边测量法，根据第一距离以及第二距离分别计算出抓斗的实时三维坐标和佩戴头盔人员的实时三维坐标，将抓斗的实时三维坐标作为抓斗运动信号，佩戴头盔人员的实时三维坐标作为人员运动信号；The central positioning engine uses trilateration to calculate the real-time three-dimensional coordinates of the grab bucket and the helmet-wearing personnel based on the first distance and the second distance, respectively. The real-time three-dimensional coordinates of the grab bucket are used as the grab bucket motion signal, and the real-time three-dimensional coordinates of the helmet-wearing personnel are used as the personnel motion signal. 获取抓斗运动轨迹以及人员运动轨迹，实时计算同时刻抓斗运动轨迹与抓斗运动信号之间的欧几里得距离作为第一距离值，计算同时刻人员运动轨迹与人员运动信号之间的欧几里得距离作为第二距离值；The movement trajectory of the grab bucket and the movement trajectory of the personnel are acquired. The Euclidean distance between the grab bucket movement trajectory and the grab bucket movement signal at the same moment is calculated in real time as the first distance value, and the Euclidean distance between the personnel movement trajectory and the personnel movement signal at the same moment is calculated as the second distance value. 分别将第一距离值以及第二距离值与预设距离阈值进行对比，若第一距离值大于等于预设距离阈值，则防砸风险的真实性不可靠；若第一距离值小于预设距离阈值；则防砸风险的真实性可靠；若第二距离值大于等于预设距离阈值，则防砸风险的真实性不可靠；若第二距离值小于预设距离阈值；则防砸风险的真实性可靠。The first distance value and the second distance value are compared with the preset distance threshold respectively. If the first distance value is greater than or equal to the preset distance threshold, the authenticity of the anti-smashing risk is unreliable; if the first distance value is less than the preset distance threshold, the authenticity of the anti-smashing risk is reliable. If the second distance value is greater than or equal to the preset distance threshold, the authenticity of the anti-smashing risk is unreliable; if the second distance value is less than the preset distance threshold, the authenticity of the anti-smashing risk is reliable. 6.根据权利要求1所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，对于确定存在的防砸风险划分风险等级，根据风险等级划分结果触发起重机PLC执行模块联动抓斗控制操作并进行人员警示，具体步骤如下：6. The method for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion as described in claim 1, characterized in that, for the identified risk of falling objects, a risk level is determined, and the crane PLC execution module is triggered to control the grab bucket and issue a personnel warning based on the risk level determination result. The specific steps are as follows: 当防砸风险的真实性可靠时，根据抓斗状态自动调整安全距离，安全距离的计算公式为：When the risk of falling debris is confirmed to be real, the safety distance is automatically adjusted based on the grab bucket's status. The formula for calculating the safety distance is: Dsafe＝k·(Vgrab·Tresp+Lgrab)式中：D safe = k·(V grab ·T resp +L grab ) where: Dsafe为安全距离，k为安全系数，Vgrab为抓斗瞬时速度，Tresp为响应时间，Lgrab为抓斗投影长度；D safe is the safe distance, k is the safety factor, V grab is the instantaneous speed of the grab, T resp is the response time, and L grab is the projected length of the grab. 根据安全距离划分风险等级，根据风险等级划分结果触发起重机PLC执行模块联动抓斗控制操作并进行人员警示。Risk levels are determined based on safe distances. Based on the risk level determination results, the crane PLC execution module is triggered to control the grab bucket and issue personnel warnings. 7.根据权利要求6所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，安全距离的计算公式中，安全系数k在抓斗空载时为1.2，在抓斗满载时为1.5。7. A method for preventing personnel from being struck by objects in ship cabins based on multi-sensor fusion as described in claim 6, characterized in that, in the formula for calculating the safe distance, the safety factor k is 1.2 when the grab bucket is unloaded and 1.5 when the grab bucket is fully loaded. 8.根据权利要求6所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，根据风险等级划分结果触发起重机PLC执行模块联动抓斗控制操作并进行人员警示，具体步骤包括：8. A method for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion, as described in claim 6, is characterized in that, based on the risk level classification result, the crane PLC execution module is triggered to control the grab bucket and issue a personnel warning, the specific steps of which include: 当Dsafe<D1(τ)≤1.2Dsafe时，触发一级预警，此时员工佩戴UWB手环振动提醒；When D_safe < D_1 (τ) ≤ 1.2D_safe , a Level 1 warning is triggered, and employees wearing UWB wristbands will be alerted by vibration. 当0.8Dsafe<D1(τ)≤Dsafe时，触发二级预警，此时抓斗自动减速，人员佩戴的AR眼镜显示非安全区域为红色警戒区；When 0.8D safe < D 1 (τ)≤D safe , a level 2 warning is triggered. At this time, the grab bucket automatically decelerates, and the AR glasses worn by the personnel display the unsafe area as a red warning zone. 当D1(τ)≤0.8Dsafe时，触发三级预警，此时抓斗悬停，并启动声光报警。When D1 (τ) ≤0.8Dsafe , a level 3 warning is triggered. At this time, the grab bucket hovers and an audible and visual alarm is activated. 9.一种基于多传感器融合的船舱作业人员防砸系统，应用于如权利要求1-8任意一项所述的一种基于多传感器融合的船舱作业人员防砸方法，其特征在于，所述系统包括：包括感知层、控制层、交互层以及机械执行层：9. A multi-sensor fusion-based anti-collision system for personnel working in ship cabins, applied to the multi-sensor fusion-based anti-collision method for personnel working in ship cabins as described in any one of claims 1-8, characterized in that the system comprises: a perception layer, a control layer, an interaction layer, and a mechanical execution layer. 感知层包括激光雷达、UWB定位单元、抓斗状态获取模块；The perception layer includes lidar, UWB positioning unit, and grab status acquisition module; 控制层包括区域划分模块、防砸风险识别模块、风险真实性核对模块以及风险等级划分模块；交互层包括UWB手环、AR眼镜；The control layer includes a region division module, an anti-smashing risk identification module, a risk authenticity verification module, and a risk level classification module; the interaction layer includes a UWB wristband and AR glasses. 机械执行层包括起重机PLC执行模块。The mechanical execution layer includes the crane PLC execution module. 10.根据权利要求9所述的一种基于多传感器融合的船舱作业人员防砸系统，其特征在于，激光雷达安装于臂架头部，用于实时扫描获取抓斗运动轨迹以及人员运动轨迹；10. A ship cabin operation personnel anti-collision system based on multi-sensor fusion according to claim 9, characterized in that a lidar is installed at the boom head for real-time scanning to acquire the movement trajectory of the grab bucket and the movement trajectory of personnel; UWB定位单元用于包括定位基站、第一定位标签以及第一定位标签；定位基站部署于船舱作业区域的四角，通过人员头盔上的第一定位标签获取第一UWB信号，基于抓斗上的第二定位标签获取第二UWB信号；The UWB positioning unit includes a positioning base station, a first positioning tag, and a second positioning tag. The positioning base station is deployed at the four corners of the ship's cabin operation area, and obtains a first UWB signal through the first positioning tag on the personnel's helmet and a second UWB signal based on the second positioning tag on the grab bucket. 抓斗状态获取模块用于通过PLC获取抓斗开闭状态以及负载重量；The grab bucket status acquisition module is used to acquire the grab bucket's open/closed status and load weight via PLC; 区域划分模块用于通过激光雷达实时扫描获取抓斗运动轨迹以及人员运动轨迹，根据抓斗运动轨迹动态划定安全区域与非安全区域；The area division module is used to obtain the movement trajectory of the grab bucket and personnel in real time through LiDAR scanning, and dynamically delineate safe and unsafe areas based on the movement trajectory of the grab bucket. 防砸风险识别模块用于对于在非安全区域的人员运动轨迹进行防砸风险识别，根据非安全区域内的抓斗运动轨迹以及人员运动轨迹分析轨迹重合度，判别防砸风险；The anti-smashing risk identification module is used to identify the anti-smashing risk based on the movement trajectory of personnel in unsafe areas. It analyzes the overlap of the movement trajectory of the grab bucket and the movement trajectory of personnel in unsafe areas to determine the anti-smashing risk. 风险真实性核对模块用于对于存在防砸风险的非安全区域，基于UWB定位单元获取抓斗运动信号以及人员运动信号，将非安全区域内的抓斗运动轨迹与抓斗运动信号结合核对第一轨迹匹配度，人员运动轨迹与人员运动信号结合核对第二轨迹匹配度，根据第一轨迹匹配度以及第二轨迹匹配度核实防砸风险的真实性；The risk authenticity verification module is used to acquire grab bucket movement signals and personnel movement signals based on UWB positioning units for unsafe areas with anti-collision risks. It combines the grab bucket movement trajectory in the unsafe area with the grab bucket movement signals to verify the first trajectory matching degree, and combines the personnel movement trajectory with the personnel movement signals to verify the second trajectory matching degree. The authenticity of the anti-collision risk is verified based on the first trajectory matching degree and the second trajectory matching degree. 风险等级划分模块用于对于确定存在的防砸风险划分风险等级；The risk level classification module is used to classify the risk level of identified falling hazards. UWB手环用于振动警报提示人员撤离；UWB wristbands are used for vibration alarms to alert personnel to evacuate; AR眼镜用于显示非安全区域为红色警戒区；AR glasses are used to display unsafe areas as red alert zones; 起重机PLC执行模块用于根据风险等级划分模块联动抓斗控制操作并进行人员警示。The crane PLC execution module is used to control the grab bucket operation according to the risk level classification module and to issue personnel warnings.
CN202511350984.0A 2025-09-22 2025-09-22 A method and system for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion Active CN120851625B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202511350984.0A CN120851625B (en) 2025-09-22 2025-09-22 A method and system for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202511350984.0A CN120851625B (en) 2025-09-22 2025-09-22 A method and system for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion

Publications (2)

Publication Number Publication Date
CN120851625A CN120851625A (en) 2025-10-28
CN120851625B true CN120851625B (en) 2026-01-20

Family

ID=97426294

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202511350984.0A Active CN120851625B (en) 2025-09-22 2025-09-22 A method and system for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion

Country Status (1)

Country Link
CN (1) CN120851625B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120397759A (en) * 2025-05-12 2025-08-01 大连华锐重工集团股份有限公司 A human-machine anti-collision system and method for grab ship unloader based on UWB technology
CN120482944A (en) * 2025-04-11 2025-08-15 中船第九设计研究院工程有限公司 Anti-collision monitoring method for crane on dock platform

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112423222B (en) * 2020-11-18 2022-05-03 苏州爱蓝信电子科技有限公司 Fork truck collision avoidance system based on UWB location
CN120108104A (en) * 2025-02-17 2025-06-06 国网江苏省电力有限公司句容市供电分公司 Substation personnel safety operation warning system and method integrating UWB and imaging technology
CN120673572A (en) * 2025-06-17 2025-09-19 广东电网有限责任公司江门供电局 Operation early warning method and device for electric power operation site, terminal equipment and storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120482944A (en) * 2025-04-11 2025-08-15 中船第九设计研究院工程有限公司 Anti-collision monitoring method for crane on dock platform
CN120397759A (en) * 2025-05-12 2025-08-01 大连华锐重工集团股份有限公司 A human-machine anti-collision system and method for grab ship unloader based on UWB technology

Also Published As

Publication number Publication date
CN120851625A (en) 2025-10-28

Similar Documents

Publication Publication Date Title
CN109212520B (en) Road condition sensing abnormal event detection alarm system and method for omnibearing detection radar
JP6892309B2 (en) Safety management system
CA2917060C (en) Operator drowsiness detection in surface mines
Maalek et al. Accuracy assessment of ultra-wide band technology in locating dynamic resources in indoor scenarios
EP3477329B1 (en) System with global positioning and rf time-of-flight ranging for supervising the safety on a site
EP2654028A1 (en) Orientation sensitive traffic collision warning system
CN110602449A (en) Intelligent construction safety monitoring system method in large scene based on vision
CN108242126A (en) A smart wearable device that actively detects and identifies hazards and alerts
KR102140195B1 (en) Method for detecting invasion of wild animal using radar and system thereof
CN119126117A (en) Intelligent collision detection method and system
CN118419788A (en) Intelligent control system for approaching protection and anti-collision protection of monorail crane personnel
CN120851625B (en) A method and system for preventing personnel from being struck by falling objects in ship cabins based on multi-sensor fusion
CN117746572A (en) High-altitude falling accident detection method and system based on intelligent safety helmet
CN120851626A (en) Overhead line threat classification assessment method and system based on dynamic trajectory tracking
CN119012135B (en) A mechanical driving collision detection system based on UWB positioning
CN115947276A (en) Anti-collision control system and its control method, processor and aerial work platform
CN113077659B (en) Intelligent bridge ship collision prevention early warning method and system based on multi-source data fusion
CN120526562A (en) Mixing station safety early warning system
WO2025212506A1 (en) Assurance-driven architecture for multi-modal sensing in human- cyber-physical systems
CN120397751A (en) Bucket wheel machine anti-collision system and anti-collision method
CN118771231A (en) Building site tower crane safety monitoring method
CN118760996A (en) Smart yard multi-level safety control device with no blind spots
DuCarme Developing effective proximity detection systems for underground coal mines
Lee et al. Stereo Vision based Hazardous Area Detection for Construction Worker's Safety
CN118962705B (en) Anti-smashing detection method and device for personnel on ship

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