CN112489045A - Anti-lifting detection method for collecting card - Google Patents
Anti-lifting detection method for collecting card Download PDFInfo
- Publication number
- CN112489045A CN112489045A CN202011554711.5A CN202011554711A CN112489045A CN 112489045 A CN112489045 A CN 112489045A CN 202011554711 A CN202011554711 A CN 202011554711A CN 112489045 A CN112489045 A CN 112489045A
- Authority
- CN
- China
- Prior art keywords
- detection
- container
- detection area
- card
- frame
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 66
- 230000003287 optical effect Effects 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims description 27
- 230000002265 prevention Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000011897 real-time detection Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06T2207/30108—Industrial image inspection
Abstract
The invention discloses a lifting-prevention detection method for a container truck. Through the mode, the anti-lifting detection method for the collecting card adopts the optical flow algorithm to perform real-time detection of the anti-lifting of the collecting card, so that the safety and the detection accuracy are ensured, and the working efficiency is improved.
Description
Technical Field
The invention relates to the field of detection of a container truck, in particular to a lifting-prevention detection method for the container truck.
Background
With the rapid development of the intelligent logistics industry in China, the handling capacity of the port container is greatly promoted.
In port yard, the operation of the spreader in the process of hoisting the container is not standard, and the container is easily hoisted or overturned together with the container, so that great potential safety hazard exists, and the working efficiency of transferring the container is reduced.
Disclosure of Invention
The invention mainly solves the technical problem of providing the anti-lifting detection method for the collecting card, has the advantages of high reliability, strong real-time performance and the like, and has wide market prospect in the application and popularization of the collecting card detection.
In order to solve the technical problems, the invention adopts a technical scheme that:
the method for detecting the lifting prevention of the container truck comprises the following steps:
(1) when the container is lifted by the lifting appliance, the image acquisition equipment starts to continuously acquire images;
(2) judging and selecting images meeting preset frame-to-frame difference according to the container hoisting speed and the processing time of anti-hoisting detection, and performing real-time anti-hoisting detection of a container truck on the selected images by adopting an optical flow algorithm;
(2.1) setting of image inter-frame difference:
obtaining the frame difference according to a formula: Δ h F/upsilon > Δ h F/(3 upsilon),
wherein n represents the frame-to-frame difference of the image, Δ h represents the normal fluctuation distance of the container truck, F is the image acquisition speed of the camera, and upsilon represents the hoisting speed of the container;
(2.2) freely setting the detection area of the card concentrator
The local part of the collecting card meeting the preset brightness threshold is freely selected as a detection area to ensure that the detection is effective;
(2.3) mean integration of the light flow graph
Each picture group meeting the frame difference obtains a light flow graph, and the distance average value in the detection area on each light flow graph is obtained through calculation; acquiring a distance average value in the hoisting prevention detection process in real time, and accumulating the acquired distance average value in real time;
(2.4) truck-catching State
When the value of the mean value integral of the detection area is greater than a preset highest threshold value, the collection card is lifted; and when the value of the mean value integral of the detection area is smaller than a preset lowest threshold value, the truck is indicated to turn on the side.
(3) And finishing the detection when the distance between the container and the container card meets a preset height threshold value.
In a preferred embodiment of the invention, the image capture device is mounted on a post on the side of the hub.
In a preferred embodiment of the present invention, the image capturing speed of the image capturing device is 20 to 30 frames/second.
In a preferred embodiment of the present invention, the duration of the anti-lifting detection is 3 to 5 seconds.
In a preferred embodiment of the present invention, in step (2.1), the normal fluctuation distance Δ h of the card is 10cm, the lifting speed is 10cm/s, the image capturing speed is 25 frames/s, and the frame-to-frame difference n ranges from 9 to 25.
In a preferred embodiment of the present invention, the inter-frame difference n is 10.
In a preferred embodiment of the present invention, in step (2.2), the layout positions of a plurality of the cards are freely selected as candidate detection areas, the average value of the luminance change in each candidate detection area is calculated, and the candidate detection area satisfying the luminance threshold is selected as the detection area.
In a preferred embodiment of the invention, the position of the pallet in the image is used as the detection area.
In a preferred embodiment of the present invention, the threshold range of the value integration of the detection region is (-5 to 210).
In a preferred embodiment of the present invention, when the mean integral is greater than 210, the hub is lifted; when the mean integral is less than-5, the container truck is overturned.
The invention has the beneficial effects that: the optical flow algorithm is adopted to carry out real-time detection of the lifting prevention of the container truck, so that the safety and the detection accuracy are ensured, and the working efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive efforts, wherein:
FIG. 1 is a block diagram of a preferred embodiment of a method for detecting pick-up in a pick-up device according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment of the present invention includes:
a lifting-prevention detection method for a container truck detects the movement condition of the container truck in the height direction in the box taking process, and judges the change around the container truck according to a real-time shot picture, so that the container truck is prevented from being lifted or lifted over in the box taking process, and the operation safety is ensured.
Optical flow is the motion of an object, scene, or camera that causes the object to move between successive frames of images. The method is a two-dimensional vector field of an image in the process of translation, can represent a speed field of three-dimensional motion of an object point through a two-dimensional image, and reflects image change formed by motion in a tiny time interval so as to determine the motion direction and the motion rate of the image point.
During normal operation, the height direction of the container truck is only slightly changed (10 cm), the movement process of the container truck can be changed when the container truck is hoisted/overturned, if the height direction is continuously increased, the container truck is hoisted, and if the height direction is continuously increased, the container truck is overturned by the crane. For this reason, optical flow algorithms can be used for the pallet anti-pick-up detection.
The optical flow algorithm needs to satisfy the basic assumption:
a) the brightness is constant. I.e. the brightness of the same object does not change when it moves between different frames. This is an assumption of basic optical flow (all optical flow variants must be satisfied) for obtaining the basic equations of optical flow;
b) temporal continuity or motion is "small motion". I.e. the temporal variation does not cause a drastic change in the target position, the displacement between adjacent frames is relatively small.
Based on the two assumed conditions, the optical flow method is directly used in a wharf container lifting scene, and the effect is not ideal, and the optical flow method is improved.
A lifting-prevention detection method for a card concentrator comprises the following specific steps:
(1) when the container is lifted by the lifting appliance, the image acquisition equipment starts to continuously acquire images, wherein the image acquisition equipment is fixed on the upright column on the side face of the container truck, and the image acquisition speed is 20-30 frames per second.
(2) And judging and selecting images meeting the preset frame difference according to the container hoisting speed and the processing time of the anti-hoisting detection, and performing the real-time anti-hoisting detection of the container truck on the selected images by adopting an optical flow algorithm.
The optical flow method is similar to image contrast to calculate the change speed of an object in an image, wherein the duration of the anti-lifting detection is about 3-5 seconds, namely 3-5 seconds in the lifting process, and the anti-lifting detection is always carried out in the process.
(2.1) setting of image frame-to-frame difference (image frame-to-frame difference, i.e., image frame processing interval):
according to the formula: delta h F/upsilon > n delta h F/(3 upsilon)
Wherein n represents a frame processing interval, Δ h represents a normal fluctuation distance of the container truck, F represents an image acquisition speed of the camera, and upsilon represents a hoisting speed of the container.
For example, the normal fluctuation range Δ h of the card concentrator is 10cm, the hoisting speed is 10cm/s, the image acquisition speed is 25 frames/s, the range of the frame processing interval n is 9-25, the data processing efficiency and the accident finding timeliness are comprehensively considered, the frame processing interval is set to 10, namely, the 1 st frame is compared with the 11 th frame, the 2 nd frame is compared with the 12 th frame, and the like.
(2.2) freely setting the detection area of the card concentrator
In the hoisting process of the container, due to the shielding of the container and other reasons, the brightness of the area of the container truck part can be changed, but the brightness of a large area is unchanged, so that the detection area of the container truck can be freely set according to the field condition to ensure the detection to be effective. The camera shooting position is fixed, the parking position of the collecting card is basically fixed, the position of the collecting card supporting plate in the image fluctuates within a certain range, and the position (position coordinate) of the collecting card supporting plate in the image can be manually and freely set as a detection area.
In addition, the method of averaging the detection area can eliminate the influence caused by a small amount of brightness change and enhance the robustness of the optical flow algorithm.
The specific implementation steps are as follows: and calculating to obtain a light flow graph according to each picture group with the frame-to-frame difference of 10, wherein the light flow graph is consistent with the size of the image shot by the camera, and the average value of the distance (or the position variation) of the detection area (the previously arranged pallet) on each light flow graph is calculated.
(2.3) light flow mean graph integration
The real-time optical flow diagram in the container truck area feeds back the movement speed of the container truck, but there is a big problem that when the container truck is slowly and uniformly lifted along with the container truck, the optical flow diagram is difficult to accurately feed back whether the container truck is lifted or overturned. Since the distance average of one light flow graph can be obtained by averaging the detection areas of each light flow graph, and the distance average of many light flow graphs can be obtained along with the lifting of the container, the distance averages of all the detection areas need to be integrated in real time (i.e., the distance averages are accumulated) to detect the state of the container truck.
When the value of the light flow mean value integral of the detection area is greater than a preset highest threshold value, the collection card is lifted; and when the value of the light flow mean value integral of the detection area is smaller than a preset lowest threshold value, the situation that the truck rolls over is indicated.
For example, during normal operation, the average integral value of the optical flows of the detection area fluctuates within a normal range (-5-210), and when the integral of the optical flow average graph of the truck area is larger than 210, the truck is hung; when the integration of the optical flow mean map of the container truck area is less than-5, the container truck is overturned.
In fig. 1, line 1 indicates a moving state in which the hub is pulled up, line 2 indicates a normal moving state in which the hub is moved, and line 3 indicates a moving state in which the hub is tilted over.
(3) And finishing detection when the container leaves about 0.5 m from the container truck, and completing the whole container hoisting work.
The invention discloses a lifting-prevention detection method for a hub of a hub container, which has the beneficial effects that: the optical flow algorithm is adopted to carry out real-time detection of the lifting prevention of the container truck, so that the safety and the detection accuracy are ensured, and the working efficiency is improved.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by the present specification, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for detecting the lifting prevention of a container truck is characterized by comprising the following steps:
(1) when the container is lifted by the lifting appliance, the image acquisition equipment starts to continuously acquire images;
(2) judging and selecting images meeting preset frame-to-frame difference according to the container hoisting speed and the processing time of anti-hoisting detection, and performing real-time anti-hoisting detection of a container truck on the selected images by adopting an optical flow algorithm;
(2.1) setting of image inter-frame difference:
obtaining the frame difference according to a formula: Δ h F/upsilon > Δ h F/(3 upsilon),
wherein n represents the frame-to-frame difference of the image, Δ h represents the normal fluctuation distance of the container truck, F is the image acquisition speed of the camera, and upsilon represents the hoisting speed of the container;
(2.2) freely setting the detection area of the card concentrator
The local part of the collecting card meeting the preset brightness threshold is freely selected as a detection area to ensure that the detection is effective;
(2.3) mean integration of the light flow graph
Each picture group meeting the frame difference obtains a light flow graph, and the distance average value in the detection area on each light flow graph is obtained through calculation; acquiring a distance average value in the hoisting prevention detection process in real time, and accumulating the acquired distance average value in real time;
(2.4) truck-catching State
When the value of the mean value integral of the detection area is greater than a preset highest threshold value, the collection card is lifted; when the value of the mean value integral of the detection area is smaller than a preset lowest threshold value, the situation that the collection card turns over laterally is indicated;
(3) and finishing the detection when the distance between the container and the container card meets a preset height threshold value.
2. The method of claim 1, wherein the image capture device is affixed to a post on the side of the card.
3. The method for detecting the lifting prevention of the card concentrator according to claim 1, wherein the image acquisition speed of the image acquisition equipment is 20-30 frames/second.
4. The method of claim 1, wherein the duration of the anti-lift detection is 3-5 seconds.
5. The method according to claim 1, wherein in step (2.1), the normal fluctuation distance Δ h of the container truck is 10cm, the hoisting speed is 10cm/s, the image acquisition speed is 25 frames/s, and the frame-to-frame difference n ranges from 9 to 25.
6. The method of claim 5, wherein the frame-to-frame difference n is 10.
7. The method according to claim 1, wherein in step (2.2), the layout positions of a plurality of the cards are freely selected as candidate detection areas, the average value of the luminance change in each candidate detection area is calculated, and the candidate detection area satisfying the luminance threshold value is selected as the detection area.
8. A pick-up prevention detection method for a card hopper according to claim 7, wherein the position of the pallet in the image is used as a detection area.
9. The method of claim 1, wherein the threshold range of the value integral of the detection area is (-5 to 210).
10. The method of claim 9, wherein when the mean integral is greater than 210, the card is lifted; when the mean integral is less than-5, the container truck is overturned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011554711.5A CN112489045B (en) | 2020-12-25 | 2020-12-25 | Anti-lifting detection method for integrated circuit card |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011554711.5A CN112489045B (en) | 2020-12-25 | 2020-12-25 | Anti-lifting detection method for integrated circuit card |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489045A true CN112489045A (en) | 2021-03-12 |
| CN112489045B CN112489045B (en) | 2024-02-27 |
Family
ID=74914374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011554711.5A Active CN112489045B (en) | 2020-12-25 | 2020-12-25 | Anti-lifting detection method for integrated circuit card |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489045B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR200321554Y1 (en) * | 2003-05-02 | 2003-07-28 | 주식회사 포스코 | Apparatus for Preventing Crane from Over-Hoisting with Self Test and Power Supply in Over-Hoisting |
| KR101370571B1 (en) * | 2012-12-17 | 2014-03-06 | 주식회사 포스코 | Overhead crane hook device to prevent excessive traction |
| KR101772928B1 (en) * | 2016-11-04 | 2017-09-12 | 주식회사 아이센트 | Transition detector system and method using luminance smoothin and optical flow analysys |
| CN109534177A (en) * | 2019-01-10 | 2019-03-29 | 上海海事大学 | A kind of anti-hoisting device of truck based on machine vision and truck are prevented slinging method |
| CN209306841U (en) * | 2019-01-10 | 2019-08-27 | 上海海事大学 | A kind of anti-hoisting device of truck based on machine vision |
| CN111539344A (en) * | 2020-04-27 | 2020-08-14 | 北京国泰星云科技有限公司 | Control system and method for preventing container truck from being lifted based on video stream and artificial intelligence |
| WO2020177288A1 (en) * | 2019-03-04 | 2020-09-10 | 青岛港国际股份有限公司 | Automatic container terminal stock yard landside automatic operation system and control method thereof |
| 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 |
-
2020
- 2020-12-25 CN CN202011554711.5A patent/CN112489045B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR200321554Y1 (en) * | 2003-05-02 | 2003-07-28 | 주식회사 포스코 | Apparatus for Preventing Crane from Over-Hoisting with Self Test and Power Supply in Over-Hoisting |
| KR101370571B1 (en) * | 2012-12-17 | 2014-03-06 | 주식회사 포스코 | Overhead crane hook device to prevent excessive traction |
| KR101772928B1 (en) * | 2016-11-04 | 2017-09-12 | 주식회사 아이센트 | Transition detector system and method using luminance smoothin and optical flow analysys |
| CN109534177A (en) * | 2019-01-10 | 2019-03-29 | 上海海事大学 | A kind of anti-hoisting device of truck based on machine vision and truck are prevented slinging method |
| CN209306841U (en) * | 2019-01-10 | 2019-08-27 | 上海海事大学 | A kind of anti-hoisting device of truck based on machine vision |
| WO2020177288A1 (en) * | 2019-03-04 | 2020-09-10 | 青岛港国际股份有限公司 | Automatic container terminal stock yard landside automatic operation system and control method thereof |
| CN111539344A (en) * | 2020-04-27 | 2020-08-14 | 北京国泰星云科技有限公司 | Control system and method for preventing container truck from being lifted based on video stream and artificial intelligence |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 贾来国;刘旭;刘艳;: "基于轮廓特征识别的防集卡吊起检测系统", 港口科技, no. 04, 15 April 2020 (2020-04-15) * |
| 黄伟;赵德安;刘晓洋;: "基于机器视觉的港口集装箱卡车防吊方法研究", 软件导刊, no. 05, 4 January 2019 (2019-01-04) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489045B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359594B (en) | Mine belt abnormity detection method and device based on video processing | |
| EP2919189B1 (en) | Pedestrian tracking and counting method and device for near-front top-view monitoring video | |
| CN107688764B (en) | Method and device for detecting vehicle violation | |
| JP7206421B2 (en) | Smart forklift and detection method of container position and orientation deviation | |
| EP3055988B1 (en) | Integrating image frames | |
| KR20070060002A (en) | Human being detection apparatus, method of detecting human being, and human being detecting program | |
| CN107662875B (en) | Monitoring and detecting of engagement state of step and comb plate of passenger conveyor | |
| CN109784344A (en) | A kind of non-targeted filtering method of image for ground level mark identification | |
| CN106991418B (en) | Winged insect detection method and device and terminal | |
| US20090214081A1 (en) | Apparatus and method for detecting object | |
| WO2018008461A1 (en) | Image processing device | |
| US7221789B2 (en) | Method for processing an image captured by a camera | |
| KR101850835B1 (en) | Method of estimating the location of mobile robot using ray-tracing technique | |
| CN107055331A (en) | Container guides system to case | |
| CN104392203B (en) | A kind of point-like fringes noise detection method based on video analysis | |
| CN107200274A (en) | A kind of anti-container truck based on machine vision is lifted method | |
| CN112489045A (en) | Anti-lifting detection method for collecting card | |
| CN109384150A (en) | The container tapered end framing of automated handling slings method with anti- | |
| CN114066997A (en) | Offset detection method based on binocular vision and symmetry | |
| CN103884332B (en) | A kind of barrier decision method, device and mobile electronic device | |
| CN105869109B (en) | Parking based on different height inverse projection face and leave object differentiating method | |
| CN207276067U (en) | The container tapered end framing of automated handling slings system with anti- | |
| CN114524209A (en) | AGV high-position stacking method and detection device based on double TOF cameras | |
| CN105376523A (en) | Stereoscopic vision detection method and system | |
| CN111611930B (en) | Parking space line detection method based on illumination consistency |
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 |