CN111539344A - Control system and method for preventing container truck from being lifted based on video stream and artificial intelligence - Google Patents
Control system and method for preventing container truck from being lifted based on video stream and artificial intelligence Download PDFInfo
- Publication number
- CN111539344A CN111539344A CN202010341734.1A CN202010341734A CN111539344A CN 111539344 A CN111539344 A CN 111539344A CN 202010341734 A CN202010341734 A CN 202010341734A CN 111539344 A CN111539344 A CN 111539344A
- Authority
- CN
- China
- Prior art keywords
- camera
- truck
- video stream
- bracket
- stream data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000003384 imaging method Methods 0.000 claims description 8
- 230000000007 visual effect Effects 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 abstract description 8
- 238000009434 installation Methods 0.000 abstract description 5
- 238000005286 illumination Methods 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 abstract description 2
- 239000004576 sand Substances 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000021615 conjugation Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Closed-Circuit Television Systems (AREA)
- Control And Safety Of Cranes (AREA)
Abstract
The invention discloses a control system and a method for preventing a container truck from being lifted based on video streaming and artificial intelligence, wherein the system comprises a processor, an Ethernet switch and a camera which are connected in sequence, wherein: the camera is arranged on the working side of the cart and used for shooting video stream data of the truck collecting bracket in real time and transmitting the video stream data to the processor through the Ethernet switch; the processor detects and judges video stream data and outputs an alarm signal and a control signal to an external protection system. The invention has simple hardware composition, convenient installation and maintenance and low failure rate; a mature camera is selected and a method based on image characteristic detection is adopted, so that the system is slightly influenced by external illumination, wind, sand, rain, snow and other environments; the system is analyzed and processed based on the image video stream, the operation response time is short, the real-time performance is high, the accident of mistakenly hanging the container truck in the port and wharf operation process is effectively avoided, and the safety of personnel and vehicles is protected.
Description
Technical Field
The invention relates to a control system and a method for preventing a container truck from being lifted based on video streaming and artificial intelligence.
Background
The pick-up accidents are usually due to one of the potential safety hazards of a field bridge (RTG/RMG, etc.) caused by incomplete opening of pick-up latches during lifting, and most of the results are that a gantry crane lifts a pick-up bracket at the junction together with a container truck, resulting in danger to personnel and vehicles.
The following conclusions can be drawn through investigation of the safety detection protection system aiming at the problem on the market at present: most judge through using photoelectric switch device to judge the space between container and the bracket thereby whether the judgement of safe separation is reachd, however the drawback lies in that the device excessively relies on cart PLC to obtain data such as hoist encoder, switching lock state, detects moreover and receives the high influence of container truck bracket, and the separation detects and has very big uncertainty to can't satisfy the needs of safety in production.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a control system and a method for preventing a container truck from being lifted based on video streaming and artificial intelligence. When the cart is in an operation state, the processor carries out lifting judgment according to video stream data collected by the camera arranged on the operation side, and outputs an alarm signal and a control signal to an external system or a component for protection response when a safety control strategy is met, so that secondary injury to the truck concentrator and workers is prevented.
The technical scheme adopted by the invention for solving the technical problems is as follows: the utility model provides a collection card prevents hoisting control system based on video stream and artificial intelligence, includes treater, ethernet switch and the camera that connects gradually, wherein: the camera is arranged on the working side of the cart and used for shooting video stream data of the truck collecting bracket in real time and transmitting the video stream data to the processor through the Ethernet switch; the processor detects and judges video stream data and outputs an alarm signal and a control signal to an external protection system.
The invention also provides a control method for preventing the container truck from being hoisted based on the video stream and artificial intelligence, which comprises the following steps:
step one, a camera shoots video stream data of a collecting card bracket in real time and transmits the video stream data to a processor through an Ethernet switch;
secondly, the processor performs visual target detection on the video stream data and then performs visual target tracking on a detection result area;
step three, judging whether the box unloading operation is carried out currently through the tracking result: if not, returning to the step two; if yes, entering the step four;
step four, judging whether the container truck bracket is lifted: if yes, the processor outputs an alarm signal and a control signal to an external protection system; if not, entering the step five;
step five, judging whether the truck collection vehicle moves horizontally: if not, returning to the fourth step; if yes, the operation detection is finished.
Compared with the prior art, the invention has the following positive effects:
the invention has simple hardware composition, convenient installation and maintenance and low failure rate; a mature camera is selected and a method based on image characteristic detection is adopted, so that the system is slightly influenced by external illumination, wind, sand, rain, snow and other environments; the system analyzes and processes based on the image video stream, the job response time is short, and the real-time performance is high; the system is operated without depending on a PLC, and the operation state and the hoisting state are detected based on the video stream. The system combines the camera, the switch and the processor system by fully considering and combining the actual situation of the field bridge operation, and simultaneously effectively avoids the accident of mistakenly hanging the container truck in the operation process of the port and the wharf by utilizing the latest technology in the fields of machine vision and mode recognition, thereby protecting the safety of personnel and vehicles.
The invention fully considers various container types, can install a camera by utilizing the mechanical structure of a field bridge, and can acquire clear images of the container and the collection truck. On the basis, the invention utilizes a video stream-based object detection algorithm to detect and track the truck tray in real time, thereby ensuring that the system can send out alarm signals and control signals to an external system or component for protection response when the truck tray is hoisted.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a schematic diagram of the present system;
FIG. 2 is a schematic view of a camera mounting location;
FIG. 3 is a schematic top view of the camera mounting;
FIG. 4 is a schematic view of a camera mounting angle;
FIG. 5 is a schematic view of the imaging effect of the camera;
FIG. 6 is a schematic diagram of the detection result area division of the pallet.
Detailed Description
A video streaming and artificial intelligence based control system for preventing the lift of a hub is disclosed, as shown in FIG. 1, which comprises a processor, an Ethernet switch and a camera (at least 1 is installed on the working side of a cart), wherein:
(1) the switch is connected with the camera and the processor for data transmission.
The switch in the system selects the model DS-3E0510P-S, and can also select other bandwidths of hundreds of megabytes or more.
(2) The camera is a front-end video data acquisition device and is used for acquiring video stream data of the operation lane. The system supports 1 or more cameras installed on the working side, each camera carries out detection and logic judgment independently, and the system takes a union set of detection results of the cameras to carry out lifting protection. The specific implementation is illustrated in 1 and 2, and the others are not described again, as follows:
1) work side 1 camera. If a fisheye camera is selected, one fisheye camera can be arranged on the working side. The suggested installation mode is that the device is fixed at the center of a cart mechanism, is 1.6 meters vertically away from the ground, has an error range of 10cm, and can be adjusted according to the field condition; as shown in fig. 4, the camera is shooting the truck tray forward, ensuring that the truck tray is all within the camera imaging range.
2) 2 cameras on the working side. If non-fisheye cameras are selected, at least 2 cameras need to be installed, and the horizontal rotation angles of the cameras are different according to different camera view angles. The suggested installation mode is that two cameras are horizontally and symmetrically installed, the distance between the horizontal position and the center of the large truck mechanism is 3-3.8 meters, the distance between the horizontal position and the ground is 1.6 meters, the error range is 10cm, the two cameras respectively face the direction of the head and the tail of the operation truck, and the two cameras can be adjusted according to the field conditions. As shown in figure 4, the front camera shoots towards the tail of the truck-collecting bracket, the rear camera shoots towards the front of the truck-collecting bracket, and the respective imaging ranges of the two cameras are crossed at the middle part of the truck-collecting bracket, so that the shooting ranges of the two cameras can cover the complete truck-collecting bracket.
Installation schematic as shown in fig. 2, 3 and 4, imaging effect as shown in fig. 5, with the upper edge of the pallet parallel to the lower bottom line of the image and within the vertical range of 3/7-4/7 of the image, within the imaging range of a single camera.
3) The camera in the system is a DS-2CD7A26FWD-IZS camera or other cameras with resolution of standard definition or above.
(3) The processor is used as a main data processing unit in the system and is responsible for processing video data collected by a camera connected with the processor in real time, detecting the operation state of the cart, comprehensively judging whether a lifting accident happens or not according to video stream data of the camera at the operation side, and immediately outputting an alarm signal and a control signal to an external system or a component to perform protection response when the lifting is detected, so that a collecting card and workers are prevented from being secondarily injured.
The processor needs to meet the requirement of 4G and above of a memory, and the CPU is at least i5, 4 cores and 2GHz of main frequency.
The system device of the invention comprises a processor, a switch and a camera (at least 1 on the working side of the cart), and realizes the functions of alarming and automatic protection through the cooperation with external systems or components. After the system runs, the processor acquires video stream data of the camera in real time, detects key components, comprehensively analyzes the detection result and judges the working state of the cart; when the cart works, the operation trends of the container truck and the container are analyzed according to the detection result and the historical detection result, so that the hoisting logic judgment is carried out. And when the judgment result is that the lifting is carried out, the processor immediately outputs an alarm signal and a control signal to an external system or component for protection response.
The invention also provides a control method for preventing the container truck from being hoisted based on the video stream and artificial intelligence, which comprises the following steps:
(1) after the processor is powered on, the system automatically runs, camera communication parameters (such as IP, ports, user names and passwords) in the configuration file are loaded, initialization work such as camera connection, login verification, decoding and stream fetching is carried out by using a corresponding communication protocol, and after initialization is completed, the system acquires video stream data shot by a camera at an operation side in real time;
(2) the system carries out characteristic identification on the collected video stream data to identify a container truck bracket:
1) carrying out convolution processing on video stream data by using trained convolution kernel to obtain bracket characteristic map layer
b is the amount of deviation, ZlAnd Zl+1Convolution inputs and outputs representing the L +1 th layer, also known as feature maps (featuremas), Ll+1Is Zl+1The size of (c). Z (i, j) corresponds to the pixel of the feature map, K is the channel number of the feature map, f, s0And p is a convolutional layer parameter, corresponding to convolutional kernel size, convolutional step size (stride), and number of padding (padding) layers.
2) Extracting position-sensitive roi (region positive) from the feature map layer through position-sensitive score maps:
a RoI must be that K x K sub-regions all contain corresponding parts of a certain object, so that the RoI can be judged to belong to the object, if a plurality of parts of the object do not appear in the corresponding sub-regions, the RoI is judged to be a background class, and finally K x K probabilities of one class are added to extract the RoI of the corresponding object.
3) And outputting a predicted value of the area of the pallet of the container truck according to the vote and the softmax to obtain the area information of the pallet in the image.
(3) When the pallet is in the identification result and the pallet does not horizontally displace but integrally rises, the current operation state of the cart is judged to be the unloading operation, and then the step (4) is carried out;
(4) dividing the detection result of the pallet in the step (3) into a plurality of areas (the number of the areas is odd, and the minimum number of the areas is 5); as shown in fig. 6, area 1 is the raw image data captured by the camera, area 2 is the output area of the target detection (i.e. the pallet) of step (3), and area 3 is the division of the pallet range into small tracking areas.
And tracking each small tracking area in real time by using a visual target tracking algorithm, wherein the tracking algorithm comprises the following steps:
4.1) acting the filter on the current frame to obtain a target result, if the current frame is the first frame, using the input as the target result, and then carrying out iterative tracking.
4.2) training the Filter
4.2.1) obtaining a sample
4.2.2) extracting features
4.2.3) training Filter
4.2.4) iteratively updating the Filter
At lFourier transform numerator of a current frame filter; a. thet-1 lη is the learning rate;
is a fourier transform of the sample;
fourier transform conjugation is carried out on the samples; gtIs a desired response; b istIs the filter fourier transform denominator.
And 4.3) executing the step 1 to perform iterative tracking on the input image data to obtain a target result.
(5) In the tracking process, analyzing the movement trend and change of each small tracking area, and comprehensively judging whether the truck collecting bracket is lifted: 1) in the lifting process of the lifting appliance, more than half of the truck-collecting brackets in the tracking area continuously rise after the rising height of the truck-collecting brackets exceeds an elastic interval (generally about 20 cm), and then the camera side lock is not unlocked and lifted; 2) in the lifting process of the lifting appliance, more than half of the truck-collecting brackets in the tracking area go up first and then fall, and the condition that the opposite side lock of the camera is not unlocked and the lifting occurs is indicated. If the collecting card is detected to be lifted, the processor outputs an alarm signal and a control signal to an external system or component for protection response; meanwhile, in the lifting process of the lifting appliance, if the horizontal movement of the truck collection body is detected, the operation detection is completed.
Claims (10)
1. The utility model provides a control system that lifts by crane is prevented to collection card based on video stream and artificial intelligence which characterized in that: including treater, ethernet switch and the camera that connects gradually, wherein: the camera is arranged on the working side of the cart and used for shooting video stream data of the truck collecting bracket in real time and transmitting the video stream data to the processor through the Ethernet switch; the processor detects and judges video stream data and outputs an alarm signal and a control signal to an external protection system.
2. The video streaming and artificial intelligence based truck anti-hang control system of claim 1, wherein: the camera is a fisheye camera, is arranged at the center of the cart mechanism, is vertically 1.6 meters away from the ground, and has an error range of 10 cm; the camera shoots the card collecting bracket in the positive direction, and the card collecting bracket is ensured to be in the imaging range of the camera.
3. The video streaming and artificial intelligence based truck anti-hang control system of claim 1, wherein: the cameras are non-fisheye cameras and are horizontally and symmetrically installed, the distance from the horizontal to the center of the cart mechanism is 3-3.8 m, the distance from the vertical to the ground is 1.6 m, and the error range is 10 cm; wherein, the front camera shoots towards the tail part of the collecting card bracket, the rear camera shoots towards the front part of the collecting card bracket, the respective imaging ranges of the two cameras are crossed in the middle part of the collecting card, and the shooting ranges of the two cameras can be ensured to cover the complete collecting card bracket.
4. The video streaming and artificial intelligence based truck anti-pick up control system according to claim 2 or 3, wherein: the upper edge of the pallet is parallel to the lower bottom line of the image within the imaging range of the camera and within the 3/7-4/7 vertical range of the image.
5. The video streaming and artificial intelligence based truck anti-hang control system of claim 1, wherein: the memory of the processor is 4G or more, the CPU is at least i5, 4 cores and the main frequency is 2 GHz.
6. A control method for preventing a container truck from being hoisted based on video streaming and artificial intelligence is characterized by comprising the following steps of: the method comprises the following steps:
step one, a camera shoots video stream data of a collecting card bracket in real time and transmits the video stream data to a processor through an Ethernet switch;
secondly, the processor performs visual target detection on the video stream data and then performs visual target tracking on a detection result area;
step three, judging whether the box unloading operation is carried out currently through the tracking result: if not, returning to the step two; if yes, entering the step four;
step four, judging whether the container truck bracket is lifted: if yes, the processor outputs an alarm signal and a control signal to an external protection system; if not, entering the step five;
step five, judging whether the truck collection vehicle moves horizontally: if not, returning to the fourth step; if yes, the operation detection is finished.
7. The method according to claim 6, wherein the control method comprises: step two, the method for detecting the visual target of the video stream data comprises the following steps:
(1) performing convolution processing on video stream data by using the trained convolution kernel to obtain a characteristic map layer of the truck tray;
(2) extracting position-sensitive RoI from the characteristic image layer of the truck tray through a position-sensitive score map;
(3) and outputting the predicted value of the area of the pallet bracket according to the vote and the softmax to obtain the area information of the pallet bracket in the image.
8. The method according to claim 6, wherein the control method comprises: and step two, when the visual target tracking is carried out on the detection result area, the area of the truck tray is divided into at least 5 odd small tracking areas.
9. The method according to claim 6, wherein the control method comprises: step three, the method for judging whether the box unloading operation is currently carried out is as follows: and when the truck collecting bracket exists in the detection result area and does not horizontally displace but is raised on the whole, judging that the current cart operation state is unloading operation.
10. The method according to claim 6, wherein the control method comprises: step four, the method for judging whether the container truck bracket is hoisted comprises the following steps: in the lifting process of the lifting appliance, if:
(1) if more than half of the truck trays in the tracking area continuously rise after the rise height exceeds the set height interval, judging that the side lock of the camera is not unlocked and is lifted;
(2) if more than half of the truck trays in the tracking area rise first and then fall, it is determined that the side lock of the camera is not unlocked and the camera is lifted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010341734.1A CN111539344B (en) | 2020-04-27 | 2020-04-27 | Video stream and artificial intelligence based integrated card anti-lifting control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010341734.1A CN111539344B (en) | 2020-04-27 | 2020-04-27 | Video stream and artificial intelligence based integrated card anti-lifting control system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111539344A true CN111539344A (en) | 2020-08-14 |
| CN111539344B CN111539344B (en) | 2024-09-06 |
Family
ID=71978865
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010341734.1A Active CN111539344B (en) | 2020-04-27 | 2020-04-27 | Video stream and artificial intelligence based integrated card anti-lifting control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111539344B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112027918A (en) * | 2020-09-04 | 2020-12-04 | 上海驭矩信息科技有限公司 | Detection method for preventing lifting of container truck based on machine vision |
| CN112489045A (en) * | 2020-12-25 | 2021-03-12 | 苏州巨能图像检测技术有限公司 | Anti-lifting detection method for collecting card |
| CN113177431A (en) * | 2021-03-15 | 2021-07-27 | 福建电子口岸股份有限公司 | Method and system for preventing container truck from being lifted based on machine vision and deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205788226U (en) * | 2016-06-02 | 2016-12-07 | 北京国泰星云科技有限公司 | Container number based on image procossing and truck car number identification system |
| JP2016204058A (en) * | 2015-04-15 | 2016-12-08 | 三井造船株式会社 | Crane operation assisting system and crane operation assisting method |
| CN106986272A (en) * | 2017-02-24 | 2017-07-28 | 北京航天自动控制研究所 | It is a kind of to prevent slinging method and system based on the container container car that machine vision is tracked |
| CN108639956A (en) * | 2018-06-27 | 2018-10-12 | 上海沪东集装箱码头有限公司 | The container crane intelligent early-warning system and method for view-based access control model detection technique |
-
2020
- 2020-04-27 CN CN202010341734.1A patent/CN111539344B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016204058A (en) * | 2015-04-15 | 2016-12-08 | 三井造船株式会社 | Crane operation assisting system and crane operation assisting method |
| CN205788226U (en) * | 2016-06-02 | 2016-12-07 | 北京国泰星云科技有限公司 | Container number based on image procossing and truck car number identification system |
| CN106986272A (en) * | 2017-02-24 | 2017-07-28 | 北京航天自动控制研究所 | It is a kind of to prevent slinging method and system based on the container container car that machine vision is tracked |
| CN108639956A (en) * | 2018-06-27 | 2018-10-12 | 上海沪东集装箱码头有限公司 | The container crane intelligent early-warning system and method for view-based access control model detection technique |
Non-Patent Citations (1)
| Title |
|---|
| 黄伟: "基于机器视觉的港口集装箱卡车防吊起技术的研究", 中国优秀硕士学位论文全文数据库（电子期刊）(工程科技Ⅱ辑)》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112027918A (en) * | 2020-09-04 | 2020-12-04 | 上海驭矩信息科技有限公司 | Detection method for preventing lifting of container truck based on machine vision |
| CN112489045A (en) * | 2020-12-25 | 2021-03-12 | 苏州巨能图像检测技术有限公司 | Anti-lifting detection method for collecting card |
| CN112489045B (en) * | 2020-12-25 | 2024-02-27 | 苏州巨能图像检测技术有限公司 | Anti-lifting detection method for integrated circuit card |
| CN113177431A (en) * | 2021-03-15 | 2021-07-27 | 福建电子口岸股份有限公司 | Method and system for preventing container truck from being lifted based on machine vision and deep learning |
| CN113177431B (en) * | 2021-03-15 | 2023-12-08 | 福建电子口岸股份有限公司 | Method and system for preventing lifting of collection card based on machine vision and deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111539344B (en) | 2024-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539344A (en) | Control system and method for preventing container truck from being lifted based on video stream and artificial intelligence | |
| CN108446630B (en) | Intelligent monitoring method for airport runway, application server and computer storage medium | |
| CN106067023B (en) | Container number and truck number identification system and method based on image processing | |
| CN111832415B (en) | Truck safety intelligent protection system for container hoisting operation | |
| CN105611244B (en) | A kind of airport alien material detection method based on ball machine monitor video | |
| CN108221755B (en) | Intelligent parking spot lock based on license plate recognition technology | |
| CN105893940B (en) | The implementation method of system is fixed in container hoisting anticollision based on edge detection | |
| CN109335964B (en) | Container twist lock detection system and detection method | |
| CN106447699B (en) | High iron catenary object detecting and tracking method based on Kalman filtering | |
| CN104601956A (en) | Power transmission line online monitoring system and method based on fixed-wing unmanned aerial vehicle | |
| CN112661013B (en) | Automatic wharf bridge crane legacy lock pad detection method and system | |
| CN107200274A (en) | A kind of anti-container truck based on machine vision is lifted method | |
| CN205788226U (en) | Container number based on image procossing and truck car number identification system | |
| CN112489125B (en) | Automatic detection method and device for pedestrians in storage yard | |
| CN113435278A (en) | Crane safety detection method and system based on YOLO | |
| CN114926422B (en) | Method and system for detecting passenger flow of getting on and off vehicles | |
| CN106960193A (en) | A kind of lane detection apparatus and method | |
| CN212847166U (en) | Movable traffic guidance lamp based on big data analysis and gesture recognition | |
| CN212101717U (en) | Control system is prevented lifting by collection card based on video stream and artificial intelligence | |
| CN110597165A (en) | Steel piling monitoring system and steel piling monitoring method | |
| CN111915561A (en) | Bolt state monitoring method based on image recognition and machine learning | |
| CN109410250B (en) | Visual image-based vehicle arrival identification method and terminal | |
| CN113415727A (en) | Container loading and unloading identification safety guiding device and method | |
| CN111646349B (en) | Elevator protection method and device based on TOF image | |
| CN108615028A (en) | The fine granularity detection recognition method of harbour heavy vehicle |
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 |