CN114723689A - Container body damage detection method - Google Patents
Container body damage detection method Download PDFInfo
- Publication number
- CN114723689A CN114723689A CN202210306006.6A CN202210306006A CN114723689A CN 114723689 A CN114723689 A CN 114723689A CN 202210306006 A CN202210306006 A CN 202210306006A CN 114723689 A CN114723689 A CN 114723689A
- Authority
- CN
- China
- Prior art keywords
- image
- container
- container body
- partial
- complete
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 25
- 238000010191 image analysis Methods 0.000 claims description 8
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 238000003703 image analysis method Methods 0.000 claims 1
- 230000000007 visual effect Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012360 testing method 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
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The application provides a container body damage detection method, which comprises the following steps: continuously acquiring a local left image, a local right image and a local top image of the container body when the vehicle passes through the detection area; respectively carrying out image splicing on a partial left image, a partial right image and a partial top image of the continuously acquired container body to obtain a complete left image, a complete right image and a complete top image; container numbers identified from the complete left image, the complete right image, and the complete top image; acquiring a container 3D model of a container number attribute corresponding to the container number from a container 3D model library; mapping the complete left image, the complete right image and the complete top image to the surface corresponding to the 3D model of the container to obtain a three-dimensional model of the container; the container body damage detection method improves the vehicle container body damage detection efficiency and accuracy, ensures the manual safety, and retains the image data.
Description
Technical Field
The application belongs to the technical field of container damage detection, and more particularly relates to a container body damage detection method.
Background
In recent years, with the continuous development of economy in China, the service of port containers is rapidly increased, and the demand for improving the throughput is more and more strong. The container body damage detection is an inevitable inspection work when a container enters a dock of a harbor area, and mainly prevents disputes caused by the damage of the container body in transportation enterprises and docks.
In the past, the work is manually recorded when the personnel enter the gate at the entrance port, and the personnel need to climb a higher gallery bridge to check the top surface of the box body, so that the problems of high danger and inaccurate treatment exist. However, the technical means of the wharf in China generally falls behind at present, vehicles are arranged in a long queue in front of the gate due to manual intervention at a plurality of gates, and errors caused by manual recording increase the repeated processing burden of the system. The service level of the wharf is reduced due to the problems, so that the living environment of the wharf is influenced, and great economic loss is caused to import and export enterprises in the coverage area of the wharf.
Disclosure of Invention
An object of the embodiment of the application is to provide a container body damage detection method, so as to solve the technical problem that the detection efficiency and the accuracy rate are low in the container damage detection process in the prior art.
In order to achieve the purpose, the technical scheme adopted by the application is as follows: the provided method for detecting the damage of the container body comprises the following steps:
continuously acquiring a local left image, a local right image and a local top image of a container body when a vehicle passes through a detection area;
respectively carrying out image splicing on a partial left image, a partial right image and a partial top image of the continuously acquired container body to obtain a complete left image, a complete right image and a complete top image;
container numbers identified from the complete left image, the complete right image, and the complete top image;
acquiring a container 3D model of a container number attribute corresponding to the container number from a container 3D model library;
mapping the complete left image, the complete right image and the complete top image to the surface corresponding to the 3D model of the container to obtain a three-dimensional model of the container;
and carrying out image analysis on the container three-dimensional model and outputting a container body damage detection result.
Preferably, an alarm is given if no container number or a plurality of different sets of container numbers are identified from the full left image, the full right image and the full top image.
Preferably, before continuously acquiring the partial left image, the partial right image and the partial top image of the container body when the vehicle passes through the detection area, the method further comprises the following steps:
and detecting the running speed of the vehicle, and changing the acquisition frequency of the partial left image, the partial right image and the partial top surface image according to the running speed of the vehicle.
Preferably, before continuously acquiring the partial left image, the partial right image and the partial top image of the container body when the vehicle passes through the detection area, the method further comprises the following steps:
and acquiring a front image of the container body when the vehicle head enters the detection area, wherein the front image of the container body is used for mapping to the surface corresponding to the 3D model of the container, and obtaining a container three-dimensional model with the front image of the container body.
Preferably, after the partial left image, the partial right image and the partial top image of the container body are continuously acquired when the vehicle passes through the detection area, the method further comprises the following steps:
and when the tail of the vehicle leaves the detection area, acquiring a tail image of the container body, wherein the tail image of the container body is used for mapping to the surface corresponding to the 3D model of the container, so as to obtain a container three-dimensional model with the tail image of the container body.
Preferably, before continuously acquiring the partial left image, the partial right image and the partial top image of the container body when the vehicle passes through the detection area, the method further comprises the following steps:
and sensing the light intensity of the detection area, and supplementing light to the detection area.
Preferably, the method of image analysis comprises:
deriving a plurality of different view angle pictures from the container stereo model;
detecting a target in each view picture;
each object is classified.
Preferably, the perspective picture includes at least one of a left view, a right view, a front view, a rear view, a top view, a front perspective view, and an oblique perspective view.
Preferably, if the damage detection result of the container body damage has damage, the vehicle is prompted to move back.
Preferably, if the container body damage detection result does not have damage, the vehicle is prompted to pass, and the data is archived.
The application provides a container body damage detection method's beneficial effect lies in: compared with the prior art, the container body damage detection method provided by the application has the advantages that the container body numbers are identified after the local images of all sides of the container body are spliced, the container 3D model of the box number attribute corresponding to the container body numbers is obtained from the container 3D model library, the complete left image, the complete right image and the complete top image are mapped to the surface corresponding to the container 3D model to obtain the container three-dimensional model, the container three-dimensional model is subjected to image analysis, and the container body damage detection result is output.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a container body damage detection method according to an embodiment of the present disclosure;
fig. 2 is a scene schematic diagram of a vehicle detection area provided in an embodiment of the present application.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
It will be understood that when an element is referred to as being "secured to" or "disposed on" another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element.
It will be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like, as used herein, refer to an orientation or positional relationship indicated in the drawings that is solely for the purpose of facilitating the description and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be considered as limiting the present application.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Referring to fig. 1 to fig. 2, a method for detecting damage to a container body according to an embodiment of the present application will be described. The container body damage detection method comprises the following steps:
step S1, continuously acquiring a local left image, a local right image and a local top image of the container body when the vehicle passes through the detection area;
step S2, respectively carrying out image splicing on the partially left image, the partially right image and the partially top image of the continuously acquired container body to obtain a complete left image, a complete right image and a complete top image;
step S3, identifying container number from the complete left image, the complete right image and the complete top image;
step S4, acquiring a container 3D model of a box number attribute corresponding to the container number from a container 3D model library;
step S5, mapping the complete left image, the complete right image and the complete top image to the surface corresponding to the container 3D model to obtain a container three-dimensional model;
and step S6, performing image analysis on the container three-dimensional model, and outputting a container body damage detection result.
It can be understood that, in step S1, the partial left image, the partial right image and the partial top image should be images captured directly opposite to the left, right and top surfaces of the container body, respectively, so as to reduce the difficulty of image stitching and improve the quality of image stitching.
In steps S3 to S4, all container 3D models specified in the current national standard "external dimensions and rated weight of container" (GB1413-2008) in our country are pre-established in the container 3D model base, and modeling is performed according to the specified dimensions and shapes.
It is worth to be noted that the container number adopts the ISO6346(1995) standard, the first part is composed of 4-Digit english letters, the first three digits (Owner Code) mainly explain the Owner and operator of the container, the fourth Digit (Owner Code) explains the type of the container, the second part is composed of 6 digits (Registration Code) which is a unique identifier held by one container body, and the third part is a Check Code (Check Digit) which is obtained by the first 4-Digit letters and 6 digits through Check rule operation and is used for identifying whether an error occurs during checking. Thus, the type of container can be obtained by identifying the container number.
In steps S5 to S6, the container body damage detection result is output by performing image analysis on the container three-dimensional model, so that manual recording is replaced, and the top surface of the container body does not need to be checked by climbing a higher gallery bridge.
The application provides a container body damage detection method, compared with the prior art, through carrying out the local image with each side of the container body and discerning container box number again after the concatenation, obtain the container 3D model of the case number attribute that this container box number corresponds from the container 3D model storehouse, map complete left side image, complete right side image and complete top surface image to the surface that container 3D model corresponds, obtain container three-dimensional model, carry out image analysis to container three-dimensional model, output container body damage testing result, both improved vehicle container body damage detection efficiency, ensure artifical safety, the image data has been kept again, it can follow to have the certificate, reduce the dispute.
In another embodiment of the present application, in step S3, if no container number or multiple different sets of container numbers are identified from the full left image, the full right image, and the full top image, an alarm is issued.
It will be appreciated that normally the same container number will be identified on the full left image, full right image and full top image of a container, and that a small number of containers may have container numbers on only one or both sides, so that the container body damage detection method can accommodate these situations. However, in the case of a serious violation when no container number exists in the complete left image, the complete right image and the complete top image or a plurality of groups of different container numbers exist, the worker is required to verify and check the condition.
In another embodiment of the present application, before continuously acquiring the partial left image, the partial right image and the partial top image of the container body when the vehicle passes through the detection area in step S1, the method further includes the steps of:
and detecting the running speed of the vehicle, and changing the acquisition frequency of the partial left image, the partial right image and the partial top surface image according to the running speed of the vehicle.
It is understood that, in order to improve the quality of image stitching, the acquisition frequency of the partial left image, the partial right image, and the partial top surface image may be changed according to the traveling speed of the vehicle. The higher the running speed of the vehicle is, the higher the acquisition frequency of the local left image, the local right image and the local top surface image is, the lower the running speed of the vehicle is, and the lower the acquisition frequency of the local left image, the local right image and the local top surface image is, so that the continuity of the images can be ensured, and the overlarge overlapping area of each image can be avoided.
In another embodiment of the present application, before continuously acquiring the partial left image, the partial right image and the partial top image of the container body when the vehicle passes through the detection area in step S1, the method further includes the steps of:
and when the vehicle head enters the detection area, acquiring a front image of the container body, wherein the front image of the container body is used for mapping to the surface corresponding to the 3D model of the container, so as to obtain a three-dimensional model of the container with the front image of the container body.
Further, in step S1, after the partial left image, the partial right image and the partial top image of the container body are continuously acquired when the vehicle passes through the detection area, the method further comprises the following steps:
and when the tail of the vehicle leaves the detection area, acquiring a tail image of the container body, wherein the tail image of the container body is used for mapping to the surface corresponding to the 3D model of the container, so as to obtain a container three-dimensional model with the tail image of the container body.
It can be understood that the container stereo model with the tail image of the container body is obtained by acquiring the front image and the tail image of the container and mapping the front image and the tail image to the corresponding surface of the 3D model of the container. The more complete container panoramic image can be obtained, and the accuracy of container body damage detection is improved.
In another embodiment of the present application, before continuously acquiring the partial left image, the partial right image and the partial top image of the container body when the vehicle passes through the detection area in step S1, the method further includes the steps of:
and sensing the light intensity of the detection area, and supplementing light to the detection area.
It can be understood that the light intensity of the detection area is sensed, the light is supplemented to the detection area, the image quality can be improved, and the definition of the image is ensured no matter at night or in rainy days.
In another embodiment of the present application, in step S6, the method of image analysis includes:
deriving a plurality of different view angle pictures from the container stereo model;
detecting a target in each view picture;
each object is classified.
It can be understood that a plurality of different visual angle pictures are derived from the container three-dimensional model, the visual angle pictures can be searched in an all-around mode, the visual angle pictures comprise front views and shaft side visual angles, and due to the fact that partial damage exists on a plurality of faces of the container body at the same time, the partial damage cannot be accurately judged from one face, therefore, the faces can be displayed at the same time through the shaft side visual angles, and the detection is accurate. Detecting a target in each view picture, and obtaining each damaged target by using a target detector; classifying each target, and performing class prediction by using an EfficientNet-b3 classification network, wherein the classes comprise: scratches, depressions, protrusions, paint drops, rust, holes, and the like.
Further, the perspective picture includes at least one of a left view, a right view, a front view, a rear view, a top view, a front perspective view, and an oblique perspective view.
In another embodiment of the present application, in step S6, if there is a damage in the detection result of the damage to the container body, the vehicle is prompted to exit.
It will be appreciated that, according to the relevant regulations, container body damage must not be closed, prompting the vehicle to exit for review.
In another embodiment of the present application, in step S6, if there is no damage in the container damage detection result, the vehicle is prompted to pass through, and the data is archived.
It will be appreciated that the data is archived, backup is retained, and when a dispute arises, the image of the vehicle passing by can be queried again to reduce the dispute.
The above description is only a preferred embodiment of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A container body damage detection method is characterized by comprising the following steps:
continuously acquiring a local left image, a local right image and a local top image of the container body when the vehicle passes through the detection area;
respectively carrying out image splicing on a partial left image, a partial right image and a partial top image of the continuously acquired container body to obtain a complete left image, a complete right image and a complete top image;
container numbers identified from the complete left image, the complete right image, and the complete top image;
acquiring a container 3D model of a container number attribute corresponding to the container number from a container 3D model library;
mapping the complete left image, the complete right image and the complete top image to the surface corresponding to the container 3D model to obtain a container three-dimensional model;
and carrying out image analysis on the container three-dimensional model and outputting a container body damage detection result.
2. The method of claim 1 wherein an alarm is generated if no container number or a plurality of different sets of container numbers are identified from the full left image, the full right image, and the full top image.
3. A method for detecting damage to a container body as claimed in claim 1, wherein before the step of continuously acquiring the partial left image, the partial right image and the partial top image of the container body as the vehicle passes through the detection area, the method further comprises the steps of:
and detecting the running speed of the vehicle, and changing the acquisition frequency of the partial left image, the partial right image and the partial top surface image according to the running speed of the vehicle.
4. A method for detecting damage to a container body as claimed in claim 1, wherein before the step of continuously acquiring the partial left image, the partial right image and the partial top image of the container body as the vehicle passes through the detection area, the method further comprises the steps of:
and when the vehicle head enters the detection area, acquiring a front image of the container body, wherein the front image of the container body is used for mapping to the surface corresponding to the 3D model of the container, so as to obtain a three-dimensional model of the container with the front image of the container body.
5. The container body damage detecting method of claim 4, further comprising the step of, after continuously acquiring the partial left image, the partial right image and the partial top image of the container body while the vehicle passes through the detection area:
and when the tail of the vehicle leaves the detection area, acquiring a tail image of the container body, wherein the tail image of the container body is used for mapping to the surface corresponding to the 3D model of the container, and obtaining a container three-dimensional model with the tail image of the container body.
6. A method for detecting damage to a container body as claimed in claim 1, wherein before the step of continuously acquiring the partial left image, the partial right image and the partial top image of the container body as the vehicle passes through the detection area, the method further comprises the steps of:
and sensing the light intensity of the detection area, and supplementing light to the detection area.
7. A method of detecting damage to a container body as claimed in claim 1, wherein said image analysis method comprises:
deriving a plurality of different view angle pictures from the container stereo model;
detecting a target in each view picture;
each object is classified.
8. A method of detecting damage to a container body as claimed in claim 7, wherein the perspective view picture includes at least one of a left view, a right view, a front view, a rear view, a top view, a front view and an oblique view.
9. The method for detecting the damage to the container body according to claim 1, wherein if the damage exists in the detection result of the damage to the container body, the vehicle is prompted to move back.
10. A method as claimed in claim 9, wherein if there is no damage in the result of the detection of damage to the container body, the vehicle is prompted to pass and the data is stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210306006.6A CN114723689A (en) | 2022-03-25 | 2022-03-25 | Container body damage detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210306006.6A CN114723689A (en) | 2022-03-25 | 2022-03-25 | Container body damage detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114723689A true CN114723689A (en) | 2022-07-08 |
Family
ID=82239431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210306006.6A Pending CN114723689A (en) | 2022-03-25 | 2022-03-25 | Container body damage detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114723689A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953726A (en) * | 2023-03-14 | 2023-04-11 | 深圳中集智能科技有限公司 | Machine vision container surface damage detection method and system |
| CN117437122A (en) * | 2023-12-21 | 2024-01-23 | 宁波港信息通信有限公司 | Method and system for splicing panoramic images of container |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100756008B1 (en) * | 2006-03-13 | 2007-09-06 | 주식회사 지팬스 | System for number recognition of container and a method thereof |
| WO2007122221A1 (en) * | 2006-04-24 | 2007-11-01 | Abb Ab | Automatic system for processing inspection data |
| JP2007322173A (en) * | 2006-05-30 | 2007-12-13 | Sumitomo Heavy Ind Ltd | Damage checking system and method |
| EP2942649A1 (en) * | 2014-05-06 | 2015-11-11 | Astrophysics Inc. | Computed tomography system for cargo and transported containers |
| CN107274121A (en) * | 2017-05-25 | 2017-10-20 | 上海撬动网络科技有限公司 | Without fixed venue Container Survey system |
| CN107525810A (en) * | 2017-08-31 | 2017-12-29 | 中远海运科技股份有限公司 | A kind of container device for detecting breakage and method based on 3D imagings |
| WO2020124247A1 (en) * | 2018-12-21 | 2020-06-25 | Canscan Softwares And Technologies Inc. | Automated inspection system and associated method for assessing the condition of shipping containers |
| US20200341453A1 (en) * | 2019-04-23 | 2020-10-29 | Walmart Apollo, Llc | System and method for adjusting the opening of containers to avoid damage to contents |
| CN112819793A (en) * | 2021-02-01 | 2021-05-18 | 宁波港信息通信有限公司 | Container damage identification method, device, equipment and readable access medium |
| WO2021217914A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Damage evidence extraction method and apparatus, computer device, and storage medium |
| CN217561347U (en) * | 2022-03-25 | 2022-10-11 | 盛视科技股份有限公司 | Container body damage detection system |
-
2022
- 2022-03-25 CN CN202210306006.6A patent/CN114723689A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100756008B1 (en) * | 2006-03-13 | 2007-09-06 | 주식회사 지팬스 | System for number recognition of container and a method thereof |
| WO2007122221A1 (en) * | 2006-04-24 | 2007-11-01 | Abb Ab | Automatic system for processing inspection data |
| JP2007322173A (en) * | 2006-05-30 | 2007-12-13 | Sumitomo Heavy Ind Ltd | Damage checking system and method |
| EP2942649A1 (en) * | 2014-05-06 | 2015-11-11 | Astrophysics Inc. | Computed tomography system for cargo and transported containers |
| CN107274121A (en) * | 2017-05-25 | 2017-10-20 | 上海撬动网络科技有限公司 | Without fixed venue Container Survey system |
| CN107525810A (en) * | 2017-08-31 | 2017-12-29 | 中远海运科技股份有限公司 | A kind of container device for detecting breakage and method based on 3D imagings |
| WO2020124247A1 (en) * | 2018-12-21 | 2020-06-25 | Canscan Softwares And Technologies Inc. | Automated inspection system and associated method for assessing the condition of shipping containers |
| US20200341453A1 (en) * | 2019-04-23 | 2020-10-29 | Walmart Apollo, Llc | System and method for adjusting the opening of containers to avoid damage to contents |
| WO2021217914A1 (en) * | 2020-04-30 | 2021-11-04 | 平安国际智慧城市科技股份有限公司 | Damage evidence extraction method and apparatus, computer device, and storage medium |
| CN112819793A (en) * | 2021-02-01 | 2021-05-18 | 宁波港信息通信有限公司 | Container damage identification method, device, equipment and readable access medium |
| CN217561347U (en) * | 2022-03-25 | 2022-10-11 | 盛视科技股份有限公司 | Container body damage detection system |
Non-Patent Citations (2)
| Title |
|---|
| ZEYNEP EKICI İMAMOĞLU 等: "Container Damage Detection and Classification Using Container Images", 《2020 28TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU)》, 7 January 2021 (2021-01-07) * |
| 刘璇: "铁路集装箱号码与车型智能识别***研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, 15 September 2018 (2018-09-15) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953726A (en) * | 2023-03-14 | 2023-04-11 | 深圳中集智能科技有限公司 | Machine vision container surface damage detection method and system |
| CN115953726B (en) * | 2023-03-14 | 2024-02-27 | 深圳中集智能科技有限公司 | Machine vision container face damage detection method and system |
| CN117437122A (en) * | 2023-12-21 | 2024-01-23 | 宁波港信息通信有限公司 | Method and system for splicing panoramic images of container |
| CN117437122B (en) * | 2023-12-21 | 2024-03-29 | 宁波港信息通信有限公司 | Method and system for splicing panoramic images of container |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114723689A (en) | Container body damage detection method | |
| CN113874927B (en) | Parking detection method, system, processing device and storage medium | |
| CN109949578A (en) | A kind of illegal automatic auditing method of vehicle crimping based on deep learning | |
| US10760898B2 (en) | Optical device and method for inspecting tires | |
| CN106340044A (en) | Camera external parameter automatic calibration method and calibration device | |
| WO2012142548A1 (en) | Method and system of rail component detection using vision technology | |
| CN109871776B (en) | All-weather lane line deviation early warning method | |
| CN104091168A (en) | Method for automatically extracting and locating power line based on unmanned aerial vehicle image | |
| CN104166841A (en) | Rapid detection identification method for specified pedestrian or vehicle in video monitoring network | |
| CN107187464A (en) | Track plates detection car, system and method | |
| CN107316462A (en) | A kind of flow statistical method and device | |
| CN109242035B (en) | Vehicle bottom fault detection device and method | |
| CN115717894B (en) | Vehicle high-precision positioning method based on GPS and common navigation map | |
| CN102346844B (en) | Device and method for identifying fault of losing screw bolts for truck center plates | |
| CN103077526A (en) | Train abnormality detection method and system with deep detection function | |
| Li | Optimising detection of road furniture (pole-like objects) in mobile laser scanning data | |
| CN112960014A (en) | Rail transit operation safety online real-time monitoring and early warning management cloud platform based on artificial intelligence | |
| CN111767902A (en) | Method, device and equipment for identifying dangerous goods of security check machine and storage medium | |
| CN110852151B (en) | Method and device for detecting shielding of berths in roads | |
| CN115035141A (en) | Tunnel crack remote monitoring and early warning method based on image processing | |
| CN113610014A (en) | System and method for detecting freight vehicle with shielding number plate exceeding limit | |
| CN115345945A (en) | Automatic inspection method and system for reconstructing expressway by using multi-view vision of unmanned aerial vehicle | |
| CN103473925B (en) | A kind of verification method of road vehicle detection system | |
| CN115511836A (en) | Bridge crack grade evaluation method and system based on reinforcement learning algorithm | |
| CN111881752B (en) | Guardrail detection classification method and device, electronic equipment and storage medium |
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 |