CN111178143A - Container temperature information acquisition method, device and system - Google Patents
Container temperature information acquisition method, device and system Download PDFInfo
- Publication number
- CN111178143A CN111178143A CN201911238539.XA CN201911238539A CN111178143A CN 111178143 A CN111178143 A CN 111178143A CN 201911238539 A CN201911238539 A CN 201911238539A CN 111178143 A CN111178143 A CN 111178143A
- Authority
- CN
- China
- Prior art keywords
- container
- image
- display area
- character
- temperature display
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Abstract
The invention discloses a container temperature information acquisition method, a device and a system, wherein the method comprises the steps of screening out a container model corresponding to an acquired container image based on the acquired characteristic points of the container image; screening out a temperature display area image from the container image based on the position information of the temperature display area in the container model; and identifying the temperature information of the container based on the temperature display area image, and finishing the acquisition of the temperature information of the container. The invention establishes corresponding container models for containers of different types, screens out the container models corresponding to the container models based on the acquired characteristic points of the container images, screens out the temperature display area images, and finally finishes the acquisition of temperature information, thereby greatly reducing the technical butt joint workload of a port wharf and a container company, and promoting the intelligent, automatic and digital popularization of the port wharf.
Description
Technical Field
The invention belongs to the technical field of temperature acquisition, particularly relates to a container temperature information acquisition method, a device and a system, and particularly relates to a temperature acquisition method of a refrigerated container.
Background
As the transportation industry has developed more and more rapidly, containers are playing an increasingly important role as the primary means of shipping. Unfortunately, although modern management modes have been adopted by many container terminals, the identification of container temperatures still mostly requires manual reading and recording, which greatly affects the operating efficiency of the terminal. The automatic identification system for the temperature of the container is one of the key points for solving the problem.
In order to realize the automation of temperature acquisition, some manufacturers adopt a built-in temperature sensor of a container to acquire the temperature. The main method comprises the following steps: the temperature sensor is embedded in the intelligent container, the temperature sensor transmits the temperature to the single chip microcomputer through a serial port, the single chip microcomputer transmits the temperature to the Internet of things platform through the Internet of things technology, and a user can monitor the temperature in real time through a mobile phone or a PC. This technique needs to rely on the container manufacturer to provide the interface.
In addition, some manufacturers take photographs of containers and perform OCR image recognition on the photographed images to recognize information about the containers. At present, the implementation method for extracting information of a container by using image recognition comprises the following steps: in the box body detection part, firstly, the container image is distorted and corrected through perspective transformation. In the box number extraction part, image preprocessing is mainly carried out through machine vision methods such as graying, edge extraction, mathematical morphology, binarization and the like of an image, then a box number area is obtained through envelope rectangle detection and screening, histogram projection and the like, then characters are segmented to obtain box numbers, and reprocessing is carried out by combining the arrangement characteristics of the box numbers to increase robustness. In the box number identification part, a sparse representation method is mainly adopted to identify the box number, the category with the minimum residual error between the original image and the reconstructed image is calculated to classify, and the high identification rate and the high robustness of the method are embodied through the comparison with template matching. The inaccurate shooting angle can cause the reduction of the recognition rate of the technology; in addition, the technology generally has low recognition rate when light reflection is encountered.
As the refrigerated container thermometer area is used as a part of the text area in the natural scene, the refrigerated container thermometer area has the characteristic of difficult text positioning in the natural scene and also has the characteristic of the refrigerated container thermometer area. At present, most manufacturers adopt a fixed camera (for example, a high-definition camera is placed at a customs clearance), so that the problem that the shooting angle cannot be adjusted is caused, and the effect of correcting the image angle is limited only by relying on; in addition, the non-uniformity of various container models causes the irregularity of the size, the length-width ratio and the like of the serial numbers, and brings certain difficulty to the image positioning detection.
Disclosure of Invention
Aiming at the problems, the invention provides a container temperature information acquisition method, a device and a system, which are used for establishing corresponding container models aiming at containers of different models, screening out the container models corresponding to the container models based on the acquired characteristic points of the container images, then screening out the temperature display area images, and finally completing the acquisition of temperature information, thereby greatly reducing the technical butt joint workload of a port wharf and a container company, and promoting the intelligent, automatic and digital popularization of the port wharf.
The technical purpose is achieved, the technical effect is achieved, and the invention is realized through the following technical scheme:
in a first aspect, the present invention provides a container temperature information collecting method, including:
screening out a container model corresponding to the characteristic points of the container image based on the acquired characteristic points of the container image;
screening out a temperature display area image from the container image based on the position information of the temperature display area in the container model;
and identifying the temperature information of the container based on the temperature display area image, and finishing the acquisition of the temperature information of the container.
Optionally, the identification method of the container temperature information includes:
extracting set characteristics of the temperature display area image;
classifying the temperature display area images by using a trained image classifier based on the extracted set characteristics to obtain corresponding image types;
extracting character features to be matched from the original image based on the character feature parameters corresponding to the image type;
matching the character features to be matched with a character feature library corresponding to the image type to obtain corresponding character data;
and sequentially segmenting and identifying the character data to finish the acquisition of the temperature information of the container.
Optionally, the segmenting the character data includes:
and segmenting the character data by adopting a histogram projection method to obtain a plurality of characters to be recognized.
Optionally, the recognizing the character data includes:
acquiring a character template, wherein the character template is consistent with the font format of a character to be recognized;
and normalizing the character template and the character to be recognized, performing difference on the data subjected to normalization processing, calculating a total pixel value subjected to difference, and if the total pixel value is smaller than a set threshold value, indicating that the character to be recognized and the character template are the same character, and completing primary recognition.
Optionally, before the step of screening out the temperature display area image from the container image based on the position information of the temperature display area in the container model, the method further includes:
identifying temperature display area position information in the collected container image;
identifying a deviation range of a camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image;
and sending a position adjusting instruction to a driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and re-collecting the container image.
In a second aspect, the present invention provides a container information collecting apparatus, including:
the first screening unit is used for screening out a container model corresponding to the characteristic points of the acquired container image;
the second screening unit is used for screening out a temperature display area image from the container image based on the position information of the temperature display area in the container model;
and the processing unit is used for identifying the temperature information of the container based on the temperature display area image and finishing the acquisition of the temperature information of the container.
Optionally, the identification unit includes:
the first extraction unit is used for extracting the set characteristics of the temperature display area image;
the classification unit is used for classifying the temperature display area images based on the extracted set characteristics by using a trained image classifier to obtain corresponding image types;
the second extraction unit is used for extracting character features to be matched from the original image based on the character feature parameters corresponding to the image type;
the matching unit is used for matching the character features to be matched with the character feature library corresponding to the image type to obtain corresponding character data;
and the acquisition unit is used for sequentially segmenting and identifying the character data to finish the acquisition of the temperature information of the container.
Optionally, the segmenting the character data includes:
and segmenting the character data by adopting a histogram projection method to obtain a plurality of characters to be recognized.
Optionally, the recognizing the character data includes:
acquiring a certain character template, wherein the character template is consistent with the font format of a character to be recognized;
and normalizing the character template and the character to be recognized, performing difference on the data subjected to normalization processing, calculating a total pixel value subjected to difference, and if the total pixel value is smaller than a set threshold value, indicating that the character to be recognized and the character template are the same character, and completing primary recognition.
Optionally, the container information collecting device further includes:
the first identification unit is used for identifying the position information of the temperature display area in the collected container image;
the second identification unit is used for identifying the deviation range of the camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image;
and the control unit is used for sending a position adjusting instruction to the driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and acquiring the container image again.
In a third aspect, the present invention provides a container information collecting system, which includes a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of the first aspects.
In a fourth aspect, the present invention provides a container information collecting system, which includes a camera, a driving unit and a processing unit;
a camera;
the driving unit is connected with the camera;
the processing unit is respectively connected with the camera and the driving unit;
the processing unit extracts the characteristic points of the container image sent by the camera and screens out a container model corresponding to the container image based on the characteristic points; identifying a deviation range of a camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image; sending a position adjusting instruction to a driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and acquiring the container image again to form a new container image;
screening out a temperature display area image from the new container image based on the temperature display area position information in the container model;
and identifying the temperature information of the container based on the temperature display area image, and finishing the acquisition of the temperature information of the container.
The invention has the beneficial effects that:
the invention automatically acquires the temperature information by a peripheral photographing mode, thereby solving the technical dependence of the port and the wharf on the container company; the deviation range is calculated through the identification of the key points of the image, so that the horizontal translation and the pitching angle of the camera are automatically controlled, and the identification rate is improved.
According to the invention, a plurality of template models are established for containers of different models, the model of the corresponding container is found through template matching, the correct position of the camera of the container is found, the shooting angle of the current camera is adjusted, and then the character recognition function is finally completed through algorithms such as image correction, image segmentation and image recognition, so that the technical butt joint workload of a port wharf and a container company is reduced, and the intelligent, automatic and digital popularization of the port wharf is promoted.
Drawings
Fig. 1 is an overall flow chart of temperature identification according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of the principles of the invention is provided in connection with the accompanying drawings.
Example 1
A container temperature information acquisition method is characterized by comprising the following steps:
(1) screening out a container model corresponding to the characteristic points of the container image based on the acquired characteristic points of the container image; the characteristic point can be a certain boundary point of a container in the container image or a boundary point of a thermometer, and can be specifically set according to the actual situation;
(2) screening out a temperature display area image from the container image based on the position information of the temperature display area in the container model;
(3) and identifying the temperature information of the container based on the temperature display area image, and finishing the acquisition of the temperature information of the container.
In a specific embodiment of the present invention, the screening out the container model corresponding to the container model in step (1) specifically includes the following steps:
the invention takes the characteristic points in the image as words, and when the image belongs to which class needs to be judged, the distribution range of the words of the current image needs to be judged, thereby deducing the class. It is divided into the following basic steps: the method comprises the steps of obtaining a sample, marking the sample, extracting image characteristics, forming a dictionary by a word bag model, extracting characteristics by the word bag model, training an SVM and classifying an image classifier, wherein the classification process is the prior art, and redundant description is not provided in the invention.
In a specific implementation manner of the embodiment of the present invention, the method for identifying temperature information of a container includes:
extracting set characteristics of the temperature display area image;
classifying the temperature display area images by using a trained image classifier based on the extracted set characteristics to obtain corresponding image types; characters in different image types have different characteristics including color characteristics, contrast characteristics, etc., which are decisive for the segmentation step;
extracting character features to be matched from the original image based on the character feature parameters corresponding to the image type;
matching the character features to be matched with a character feature library corresponding to the image type to obtain corresponding character data;
and sequentially segmenting and identifying the character data to finish the acquisition of the temperature information of the container.
In a specific implementation manner of the embodiment of the present invention, the extracting the character features to be matched from the original image specifically includes:
extracting characteristic points in the temperature display area image, wherein the characteristic points are pixels with certain characteristics (different algorithms are different) in the image;
calculating descriptors of the feature points according to the obtained feature point positions;
matching is performed according to descriptors of feature points, the matching of features is performed on the descriptors of features, the above-mentioned descriptors of features are usually a vector, and the distance between two descriptors of features can reflect the similarity degree, that is, the two feature points are not the same. Depending on the descriptor, different distance metrics may be selected. If the descriptor is a floating point type descriptor, the Euclidean distance of the descriptor can be used; for binary descriptors (BRIEF), their hamming distance (hamming distance between two different binary strings refers to the number of different bits of two binary strings) can be used.
With the method for calculating the similarity of the descriptors, the method adopts a KNN matching algorithm to search the most similar characteristic points in the characteristic point set so as to complete the matching of the characteristic points.
In a specific implementation manner of the embodiment of the present invention, the segmenting the character data includes the following steps:
and segmenting the character data by adopting a histogram projection method to obtain a plurality of characters to be recognized.
In specific implementation, the distribution histogram of the pixels of the binary image can be used for analysis, so that the number of the pixels in the digital area in the vertical direction is reflected by finding out the boundary points of adjacent characters for segmentation and projection. Then, only each column of the projection needs to be judged, and the segmentation point can be found.
In a specific implementation manner of the embodiment of the present invention, the recognizing the character data includes the following steps:
acquiring a character template, wherein the character template is consistent with the font format of a character to be recognized; the character template obtaining process specifically comprises the following steps: the image is corrected for tilt so that the characters are all in front view. Obtaining an ROI according to an ROI positioning method; according to a character segmentation method, obtaining a picture of each character, wherein the size is specified to be 28 × 28; and carrying out mean processing on a plurality of images of each character in each font under each type to obtain a final character template.
And normalizing the character template and the character to be recognized, performing difference on the data subjected to normalization processing, calculating a total pixel value subjected to difference, and if the total pixel value is smaller than a set threshold value, indicating that the character to be recognized and the character template are the same character, and completing primary recognition.
The method specifically comprises the following steps:
manufacturing a character template: the requirement of the character template is consistent with the font format of the character to be recognized, standard characters on Microsoft Word software are adopted in the experiment, the required character template is manufactured according to the processing process of 3-6 steps after screenshot of the software, 10 numbers are obtained from 0 to 9, and 26 letters are obtained from A to Z.
Normalization of the character template: under the condition of meeting the recognition rate, the small template recognition is adopted as much as possible, so that the calculation speed can be refreshed, and the specific size of the template can be adjusted according to the subsequent comparison with the character to be recognized.
The identification process comprises the following steps: and performing the same normalization processing on the character to be recognized and the character template, then traversing and comparing the character template, wherein the processing method comprises the steps of firstly performing difference on the character template, then calculating the total pixel value of the image subjected to difference, and if the total pixel value is smaller than a set threshold value, indicating that the character to be recognized and the template are the same character, thus completing one-time recognition.
All characters can be recognized by circularly performing the same processing on the characters to be recognized, and the result is stored in the character string.
In a specific implementation manner of the embodiment of the present invention, in order to implement automatic correction of a shooting angle, before the step of screening out a temperature display area image from a container image based on the position information of the temperature display area in the container model, the method further includes:
identifying temperature display area position information in the collected container image;
identifying a deviation range of a camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image;
and sending a position adjusting instruction to a driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and re-collecting the container image.
Example 2
Based on the same inventive concept as embodiment 1, an embodiment of the present invention provides a container information collecting apparatus, including:
the first screening unit is used for screening out a container model corresponding to the characteristic points of the acquired container image;
the second screening unit is used for screening out a temperature display area image from the container image based on the position information of the temperature display area in the container model;
and the processing unit is used for identifying the temperature information of the container based on the temperature display area image and finishing the acquisition of the temperature information of the container.
In a specific implementation manner of the embodiment of the present invention, the identification unit includes:
the first extraction unit is used for extracting the set characteristics of the temperature display area image;
the classification unit is used for classifying the temperature display area images based on the extracted set characteristics by using a trained image classifier to obtain corresponding image types;
the second extraction unit is used for extracting character features to be matched from the original image based on the character feature parameters corresponding to the image type;
the matching unit is used for matching the character features to be matched with the character feature library corresponding to the image type to obtain corresponding character data;
and the acquisition unit is used for sequentially segmenting and identifying the character data to finish the acquisition of the temperature information of the container.
In a specific implementation manner of the embodiment of the present invention, the segmenting the character data includes the following steps:
and segmenting the character data by adopting a histogram projection method to obtain a plurality of characters to be recognized.
In a specific implementation manner of the embodiment of the present invention, the recognizing the character data includes the following steps:
acquiring a certain character template, wherein the character template is consistent with the font format of a character to be recognized;
and normalizing the character template and the character to be recognized, performing difference on the data subjected to normalization processing, calculating a total pixel value subjected to difference, and if the total pixel value is smaller than a set threshold value, indicating that the character to be recognized and the character template are the same character, and completing primary recognition.
Example 3
How to ensure the shooting angle of the camera is the first step of image recognition. When the image viewing angle changes, the gray value of the same object also changes. Therefore, it is necessary to find a feature that can move and rotate (change the view angle) in the camera and still remain unchanged, and use the unchanged feature to find the same object in the images from different view angles.
To enable better image matching, it is necessary to select representative regions in the image, such as: corners, edges and some regions in the image, but it is easiest to identify the corners in the image, i.e. the recognition of the corners is highest. But a simple corner point cannot well meet our requirements, for example: the camera gets a corner point from far, but may not be at near; or when the camera rotates, the angular point changes. Therefore, in order to realize automatic correction of the shooting angle of the camera, based on embodiment 2, the embodiment of the present invention is different from embodiment 2 in that the container information collecting device further includes:
the first identification unit is used for identifying the position information of the temperature display area in the collected container image; the container image is obtained by photographing the container based on the existing camera angle;
the second identification unit is used for identifying the deviation range of the camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image;
and the control unit is used for sending a position adjusting instruction to the driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and acquiring the container image again.
Example 4
Based on the same inventive concept as embodiment 1, the embodiment of the invention provides a container information acquisition system, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any of embodiment 1.
Example 5
The embodiment of the invention provides and provides a container information acquisition system, which comprises: the device comprises a camera, a driving unit and a processing unit;
a camera;
the driving unit is connected with the camera;
the processing unit is respectively connected with the camera and the driving unit;
the processing unit extracts the characteristic points of the container image sent by the camera and screens out a container model corresponding to the container image based on the characteristic points; identifying a deviation range of a camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image; sending a position adjusting instruction to a driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and acquiring the container image again to form a new container image;
screening out a temperature display area image from the new container image based on the temperature display area position information in the container model;
and identifying the temperature information of the container based on the temperature display area image, and finishing the acquisition of the temperature information of the container.
Before the container information acquisition system works, the following preparation works are required:
and calibrating the camera, wherein the calibration of the camera is only needed to be carried out once. Because the distortion degree of each camera may be different, in order to ensure the accuracy, each camera needs to be calibrated once.
The container images are classified, only one classification is required to be executed under normal conditions, and only corresponding files are required to be loaded later. However, if there is a new image type, the classification operation needs to be performed again.
Selecting better container images, particularly contrast, definition, inclination angle and the like, if necessary, manually processing the container images to construct a more ideal image set, and training based on the image set to obtain an image classifier.
The character segmentation function seems to be independent of the image type, but is actually largely related. Each type of container corresponds to one image type, and characters in different image types have different characteristics including color characteristics, contrast characteristics and the like, and the characteristics play a decisive role in the preprocessing step of segmentation. A large number of tests for each type of class are required in the early preparation phase to obtain the corresponding optimal methods and parameters. Therefore, the parameters are stored, and the corresponding parameters are selected according to the image types during segmentation, so that the segmentation accuracy can be greatly improved.
The image is corrected for tilt so that the characters are all in front view. Obtaining an ROI according to an ROI positioning method; according to a character segmentation method, obtaining a picture of each character, wherein the size is specified to be 28 × 28; and carrying out mean processing on a plurality of images of each character in each font under each type to obtain a final character template, and storing the character template.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (12)
1. A container temperature information acquisition method is characterized by comprising the following steps:
screening out a container model corresponding to the characteristic points of the container image based on the acquired characteristic points of the container image;
screening out a temperature display area image from the container image based on the position information of the temperature display area in the container model;
and identifying the temperature information of the container based on the temperature display area image, and finishing the acquisition of the temperature information of the container.
2. The container temperature information collection method according to claim 1, wherein: the identification method of the container temperature information comprises the following steps:
extracting set characteristics of the temperature display area image;
classifying the temperature display area images by using a trained image classifier based on the extracted set characteristics to obtain corresponding image types;
extracting character features to be matched from the original image based on the character feature parameters corresponding to the image type;
matching the character features to be matched with a character feature library corresponding to the image type to obtain corresponding character data;
and sequentially segmenting and identifying the character data to finish the acquisition of the temperature information of the container.
3. The container temperature information collection method according to claim 2, wherein: the segmenting the character data comprises the following steps:
and segmenting the character data by adopting a histogram projection method to obtain a plurality of characters to be recognized.
4. The container temperature information collection method according to claim 2, wherein: the recognizing the character data comprises the following steps:
acquiring a character template, wherein the character template is consistent with the font format of a character to be recognized;
and normalizing the character template and the character to be recognized, performing difference on the data subjected to normalization processing, calculating a total pixel value subjected to difference, and if the total pixel value is smaller than a set threshold value, indicating that the character to be recognized and the character template are the same character, and completing primary recognition.
5. The container temperature information collection method according to claim 1, wherein: before the step of screening out the temperature display area image from the container image based on the position information of the temperature display area in the container model, the method further comprises the following steps:
identifying temperature display area position information in the collected container image;
identifying a deviation range of a camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image;
and sending a position adjusting instruction to a driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and re-collecting the container image.
6. A container information collection device, comprising:
the first screening unit is used for screening out a container model corresponding to the characteristic points of the acquired container image;
the second screening unit is used for screening out a temperature display area image from the container image based on the position information of the temperature display area in the container model;
and the processing unit is used for identifying the temperature information of the container based on the temperature display area image and finishing the acquisition of the temperature information of the container.
7. The container information collection device according to claim 6, wherein: the identification unit includes:
the first extraction unit is used for extracting the set characteristics of the temperature display area image;
the classification unit is used for classifying the temperature display area images based on the extracted set characteristics by using a trained image classifier to obtain corresponding image types;
the second extraction unit is used for extracting character features to be matched from the original image based on the character feature parameters corresponding to the image type;
the matching unit is used for matching the character features to be matched with the character feature library corresponding to the image type to obtain corresponding character data;
and the acquisition unit is used for sequentially segmenting and identifying the character data to finish the acquisition of the temperature information of the container.
8. The container information collection device according to claim 7, wherein: the segmenting the character data comprises the following steps:
and segmenting the character data by adopting a histogram projection method to obtain a plurality of characters to be recognized.
9. The container information collection device according to claim 7, wherein: the recognizing the character data comprises the following steps:
acquiring a certain character template, wherein the character template is consistent with the font format of a character to be recognized;
and normalizing the character template and the character to be recognized, performing difference on the data subjected to normalization processing, calculating a total pixel value subjected to difference, and if the total pixel value is smaller than a set threshold value, indicating that the character to be recognized and the character template are the same character, and completing primary recognition.
10. The container information collection device according to claim 6, wherein: further comprising:
the first identification unit is used for identifying the position information of the temperature display area in the collected container image;
the second identification unit is used for identifying the deviation range of the camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image;
and the control unit is used for sending a position adjusting instruction to the driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and acquiring the container image again.
11. A container information acquisition system, characterized by: comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 5.
12. A container information acquisition system, characterized by: the device comprises a camera, a driving unit and a processing unit;
a camera;
the driving unit is connected with the camera;
the processing unit is respectively connected with the camera and the driving unit;
the processing unit extracts the characteristic points of the container image sent by the camera and screens out a container model corresponding to the container image based on the characteristic points; identifying a deviation range of a camera based on the position information of the temperature display area in the container model and the position information of the temperature display area in the collected container image; sending a position adjusting instruction to a driving unit based on the deviation range, driving the camera to move to a specified position, enabling the position information of the temperature display area in the image shot by the camera to be consistent with the position information of the temperature display area in the container model, and acquiring the container image again to form a new container image;
screening out a temperature display area image from the new container image based on the temperature display area position information in the container model;
and identifying the temperature information of the container based on the temperature display area image, and finishing the acquisition of the temperature information of the container.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911238539.XA CN111178143B (en) | 2019-12-06 | 2019-12-06 | Container temperature information acquisition method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911238539.XA CN111178143B (en) | 2019-12-06 | 2019-12-06 | Container temperature information acquisition method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111178143A true CN111178143A (en) | 2020-05-19 |
| CN111178143B CN111178143B (en) | 2022-11-04 |
Family
ID=70657250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911238539.XA Active CN111178143B (en) | 2019-12-06 | 2019-12-06 | Container temperature information acquisition method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178143B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354573A (en) * | 2015-12-15 | 2016-02-24 | 重庆凯泽科技有限公司 | Container license plate identification method and system |
| CN106203239A (en) * | 2015-05-04 | 2016-12-07 | 杭州海康威视数字技术股份有限公司 | Information processing method, device and system for container tally |
| CN107832767A (en) * | 2017-11-14 | 2018-03-23 | 深圳码隆科技有限公司 | Container number identification method, device and electronic equipment |
| CN109612520A (en) * | 2018-10-26 | 2019-04-12 | 中交第航务工程局有限公司 | A kind of frozen products insulated container monitoring system and its monitoring method based on BIM model |
| CN109784272A (en) * | 2019-01-13 | 2019-05-21 | 南京邮电大学盐城大数据研究院有限公司 | A kind of container identifying system and container recognition methods |
-
2019
- 2019-12-06 CN CN201911238539.XA patent/CN111178143B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106203239A (en) * | 2015-05-04 | 2016-12-07 | 杭州海康威视数字技术股份有限公司 | Information processing method, device and system for container tally |
| CN105354573A (en) * | 2015-12-15 | 2016-02-24 | 重庆凯泽科技有限公司 | Container license plate identification method and system |
| CN107832767A (en) * | 2017-11-14 | 2018-03-23 | 深圳码隆科技有限公司 | Container number identification method, device and electronic equipment |
| CN109612520A (en) * | 2018-10-26 | 2019-04-12 | 中交第航务工程局有限公司 | A kind of frozen products insulated container monitoring system and its monitoring method based on BIM model |
| CN109784272A (en) * | 2019-01-13 | 2019-05-21 | 南京邮电大学盐城大数据研究院有限公司 | A kind of container identifying system and container recognition methods |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111178143B (en) | 2022-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111474184B (en) | AOI character defect detection method and device based on industrial machine vision | |
| US9171204B2 (en) | Method of perspective correction for devanagari text | |
| CN113012212B (en) | Depth information fusion-based indoor scene three-dimensional point cloud reconstruction method and system | |
| CN110569878B (en) | Photograph background similarity clustering method based on convolutional neural network and computer | |
| CN111680688B (en) | Character recognition method and device, electronic equipment and storage medium | |
| CN110827247B (en) | Label identification method and device | |
| US11030436B2 (en) | Object recognition | |
| CN112686812B (en) | Bank card inclination correction detection method and device, readable storage medium and terminal | |
| US9076242B2 (en) | Automatic correction of skew in natural images and video | |
| WO2014103297A1 (en) | Object identification device, method, and storage medium | |
| CN113903024A (en) | Handwritten bill numerical value information identification method, system, medium and device | |
| CN111027538A (en) | Container detection method based on instance segmentation model | |
| CN113158895A (en) | Bill identification method and device, electronic equipment and storage medium | |
| CN110288040B (en) | Image similarity judging method and device based on topology verification | |
| CN112070077B (en) | Deep learning-based food identification method and device | |
| CN113989604A (en) | Tire DOT information identification method based on end-to-end deep learning | |
| CN110298347B (en) | Method for identifying automobile exhaust analyzer screen based on GrayWorld and PCA-CNN | |
| CN111178143B (en) | Container temperature information acquisition method, device and system | |
| CN111178200A (en) | Identification method of instrument panel indicator lamp and computing equipment | |
| CN115512381A (en) | Text recognition method, text recognition device, text recognition equipment, storage medium and working machine | |
| CN114332814A (en) | Parking frame identification method and device, electronic equipment and storage medium | |
| CN114092542A (en) | Bolt measuring method and system based on two-dimensional vision | |
| CN112232288A (en) | Satellite map target identification method and system based on deep learning | |
| CN112749664A (en) | Gesture recognition method, device, equipment, system and storage medium | |
| CN112883973A (en) | License plate recognition method and device, electronic equipment and computer 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |