CN118153914A - Container disease vector biological detection early warning method and system based on image analysis - Google Patents
Container disease vector biological detection early warning method and system based on image analysis Download PDFInfo
- Publication number
- CN118153914A CN118153914A CN202410571369.1A CN202410571369A CN118153914A CN 118153914 A CN118153914 A CN 118153914A CN 202410571369 A CN202410571369 A CN 202410571369A CN 118153914 A CN118153914 A CN 118153914A
- Authority
- CN
- China
- Prior art keywords
- container
- organisms
- image acquisition
- image
- disease
- 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
- 239000013598 vector Substances 0.000 title claims abstract description 78
- 201000010099 disease Diseases 0.000 title claims abstract description 66
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 66
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000010191 image analysis Methods 0.000 title claims abstract description 30
- 230000007613 environmental effect Effects 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 244000052769 pathogen Species 0.000 claims description 48
- 238000005192 partition Methods 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 14
- 238000012163 sequencing technique Methods 0.000 claims description 14
- 238000010801 machine learning Methods 0.000 claims description 13
- 238000007635 classification algorithm Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 6
- 239000002028 Biomass Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000002265 prevention Effects 0.000 abstract description 5
- 230000004044 response Effects 0.000 abstract description 4
- 238000013178 mathematical model Methods 0.000 abstract description 3
- 241000255925 Diptera Species 0.000 description 10
- 238000012549 training Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012706 support-vector machine Methods 0.000 description 5
- 239000003795 chemical substances by application Substances 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000004659 sterilization and disinfection Methods 0.000 description 4
- 241000238631 Hexapoda Species 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 1
- 235000016936 Dendrocalamus strictus Nutrition 0.000 description 1
- 241000803586 Gloridonus yolo Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000001954 sterilising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Human Computer Interaction (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a container vector biological detection early warning method and system based on image analysis, and relates to the technical field of image analysis, wherein the system comprises an image acquisition module, an identification classification module, a comprehensive evaluation module and an early warning scheduling module; the technical key points are as follows: by combining environmental data in the container, the number of disease medium organisms and other factors, a mathematical model is established to quantitatively evaluate the risk degree, personalized evaluation can be carried out aiming at the risk conditions of different areas in the container, the overall risk condition can be mastered more accurately, the important prevention and control high-risk container can be better identified, the basis is provided for subsequent dispatching and processing, a priority index model is established based on the container risk degree and distance factors, the processing sequence of staff can be reasonably arranged, the optimal utilization of limited resources is ensured, quick response is provided for the high-risk area, and the efficiency and the safety of overall management are improved.
Description
Technical Field
The invention relates to the technical field of image analysis, in particular to a container disease vector biological detection and early warning method and system based on image analysis.
Background
With the development of international trade, international ocean vessels, airplanes and international bans are important places for hiding and breeding disease-vector organisms, and the used containers become main risk factor carriers for international transmission of disease-vector infectious diseases, so that great health and safety hazards exist.
However, in reality, the effect of target detection is still to be improved due to the complexity of the application scene of customs. Along with the continuous promotion of the construction of intelligent customs, the image target detection technology becomes an indispensable component element of intelligent supervision service of customs. The image target detection technology is applied to a customs video monitoring system, and specifically realizes logistics supervision including container number detection, identification and tracking of abnormal personnel and vehicles, identification of simple commodities and the like, and the image target detection can improve the working efficiency and efficiency of customs in multiple aspects.
The image analysis technology refers to the process of analyzing, identifying and understanding the image by utilizing computer vision and image processing technology; the technology can be used for identifying information such as objects, scenes, characters and the like in the image, and realizing automatic image understanding and processing; image analysis techniques include, but are not limited to, the following: target detection and identification, image segmentation, feature extraction, image identification and classification, image reconstruction and restoration, and image enhancement and processing; the target detection and identification is to identify specific targets in the image, such as faces, vehicles, animals and the like, and classify or mark the targets by an algorithm; the image segmentation is to divide an image into a plurality of areas or objects, and is commonly used in the fields of medical image analysis, map making and the like; feature extraction is to extract feature information such as edges, textures, colors and the like in an image for subsequent analysis and identification; the technology is widely applied in the fields of computer vision, image processing, artificial intelligence and the like, such as intelligent monitoring systems, medical image analysis, automatic driving, image detection and the like, and has important significance for realizing automatic and intelligent image analysis and processing.
At present, when an image analysis technology is applied to the detection direction of the container disease medium organisms, a high-definition camera is usually carried in the container, according to image data shot by the camera, an associated image analysis algorithm is adopted for analysis, and after the disease medium organisms with corresponding quantity or coverage area size are detected, early warning treatment is carried out, so that a worker is reminded of carrying out high-temperature disinfection operation on the associated container to remove the disease medium organisms;
however, the above conventional technical solutions have some problems in the implementation process: firstly, the harm degree of the vector organisms in the container cannot be effectively judged only according to the related characteristics of the vector organisms, such as coverage or quantity, if the environment in the container is very suitable for the vector organisms to grow, the vector organisms can continuously and burst in a short period, the priority treatment is required for the situation, if the number of the containers with risks in the same area is large, the number of staff cannot meet the requirement, the priority treatment is required for the risk conditions in the containers, the priority treatment is very important, and the allocation of the staff is obviously unreasonable only by the experience of the staff or according to the distance of the positions of the containers.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a container vector biological detection early warning method and system based on image analysis, which can quantitatively evaluate the risk degree by combining environmental data, vector biological quantity and other factors in a container, can perform personalized evaluation on the risk conditions of different areas in the container, grasp the overall risk condition more accurately, is favorable for better identifying a high-risk container with important prevention and control, provides basis for subsequent dispatching and processing, and based on the container risk degree and distance factors, establishes a priority index model, can reasonably arrange the processing sequence of staff, ensures optimal utilization of limited resources, provides quick response for the high-risk area, improves the efficiency and safety of the overall management, and solves the problems in the background technology.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
container disease vector biological detection early warning system based on image analysis includes:
the image acquisition module divides the interior of each container into at least four equally-divided image acquisition subareas and acquires image data in each image acquisition subarea;
The identification and classification module is used for analyzing and classifying the image data acquired in each image acquisition partition by utilizing an image processing and machine learning technology, identifying common disease organisms and suspected disease organisms, counting the number of the common disease organisms and the number of the suspected disease organisms in each image acquisition partition, and executing a strategy of halving the image acquisition frequency if the common disease organisms or the suspected disease organisms are not identified in the image data acquired by any image acquisition partition;
The comprehensive evaluation module is used for constructing a data analysis calculation model according to the preprocessed environmental data, the number of the common disease organisms and the number of the suspected disease organisms under the condition that the common disease organisms exist in the corresponding image acquisition subareas are identified and obtained by combining the acquired environmental data in each container, and generating a risk degree index Q of the corresponding container;
The warning scheduling module is used for sequencing a plurality of containers in the same area according to the sequence from large to small, a first sequencing table is generated, when the risk degree index Q of the corresponding container is obtained and is larger than zero, an early warning signal is sent out, a GIS tool is used for calculating the distance between each container sending out the early warning signal and a workstation, a priority computing model is built according to the risk degree index Q and the distance, a priority index Pi corresponding to the container is generated, the priority indexes Pi corresponding to the containers are sequenced according to the sequence from large to small, a second sequencing table is generated, and staff in the workstation sequentially operate the containers according to the sequence of the second sequencing table.
Further, a corresponding image acquisition device is arranged in each divided area for acquiring image data.
Further, the image processing and machine learning techniques include an object detection algorithm and an image classification algorithm, wherein the object detection algorithm is any one of YOLO and SSD, and the image classification algorithm is any one of CNN and SVM.
Further, the acquired environmental data in each container comprises the temperature and the humidity in each image acquisition zone in the same container, and then the pretreatment of the environmental data, the number of common disease vector organisms and the number of suspected disease vector organisms comprises the following steps: and normalizing the environmental data, the number of common disease-related organisms and the number of suspected disease-related organisms.
Further, before the risk degree index Q of the corresponding container is generated, calculating a risk degree predicted value corresponding to each image acquisition partition in the same containerThe formula according to is as follows:
In the method, in the process of the invention, Representing the temperature of the corresponding image acquisition zone,The preset standard temperature is indicated to be the same,Indicating the difference in temperature and the temperature value,Representing the humidity of the corresponding image acquisition zone,Indicating the preset standard humidity level to be used,Indicating the difference in humidity value and,Representing the number of common disease agents within the corresponding image acquisition partition,Representing the suspected vector biomass in the corresponding image acquisition partition,Respectively the temperature difference value, the humidity difference value, the common vector quantity and the suspected vector quantity, and。
Further, the formula according to which the risk level index Q of the container is generated is as follows:
where n=1, 2, …, k is a positive integer.
Further, the process of calculating the distance between each container sending out the early warning signal and the workstation by using the GIS tool is as follows:
S101, acquiring accurate position information of a container and a working station of a worker;
S102, inputting longitude and latitude coordinates of a container and a workstation by using a Geographic Information System (GIS) tool comprising any one of Google Maps API and ArcGIS;
S103, in a GIS tool, calculating the actual path distance between the container and the workstation by using a distance measuring tool;
and S104, after the calculation is completed, the GIS tool gives the distance between the container and the workstation.
Further, the formula according to which the priority index Pi corresponding to the container is generated is as follows:
In the method, in the process of the invention, Representing the distance value between the same container and the workstation,Respectively the risk degree index of the same container and the weight coefficient of the distance value between the container and the workstation, and。
The container vector biological detection early warning method based on image analysis comprises the following steps:
S1, dividing the interior of each container into at least four equally-divided image acquisition subareas, and acquiring image data in each image acquisition subarea;
s2, analyzing and classifying the image data acquired in each image acquisition partition by utilizing an image processing and machine learning technology, identifying common disease organisms and suspected disease organisms, counting the number of the common disease organisms and the number of the suspected disease organisms in each image acquisition partition, and executing a strategy of halving the image acquisition frequency if the common disease organisms or the suspected disease organisms are not identified in the image data acquired by any image acquisition partition;
S3, combining the acquired environmental data in each container, under the condition that common vector organisms exist in the corresponding image acquisition subareas, building a data analysis calculation model according to the preprocessed environmental data, the number of the common vector organisms and the number of suspected vector organisms, and generating a risk degree index Q of the corresponding container;
S4, sorting a plurality of containers in the same area according to the order from large to small, generating a sorting table I, sending out early warning signals when the risk degree index Q of the corresponding container is obtained to be larger than zero, calculating the distance between each container sending out the early warning signals and a workstation by using a GIS tool, building a priority calculation model according to the risk degree index Q and the distance, generating a priority index Pi corresponding to the container, sorting the priority indexes Pi corresponding to the containers according to the order from large to small, generating a sorting table II, and sequentially operating the containers by staff in the workstation according to the order of the sorting table II.
The invention has the beneficial effects that:
1. Common disease medium organisms in the images can be rapidly identified and counted through a target detection and image classification algorithm, uncertain suspected disease medium organisms can be rapidly marked, a basis is provided for subsequent deep analysis and evaluation, when any disease medium organism is not detected in a certain area in the container, the image acquisition frequency can be automatically reduced, resources are saved, and the dynamic adjustment mechanism can improve the adaptability and the flexibility of the system;
2. By combining environmental data in the container, the number of disease medium organisms and other factors, a mathematical model is established to quantitatively evaluate the risk degree, personalized evaluation can be carried out aiming at the risk conditions of different areas in the container, the overall risk condition can be mastered more accurately, the important prevention and control high-risk container can be better identified, the basis is provided for subsequent dispatching and processing, a priority index model is established based on the container risk degree and distance factors, the processing sequence of staff can be reasonably arranged, the optimal utilization of limited resources is ensured, quick response is provided for the high-risk area, and the efficiency and the safety of overall management are improved.
3. The container vector biological detection and early warning method based on image analysis can be applied to the field of intelligent logistics or intelligent customs, thereby promoting the development of intelligent customs and laying a foundation for the 'intelligent customs, intelligent border and intelligent sharing communication' of port foreign trade economy.
Drawings
FIG. 1 is a schematic diagram of the overall flow of a container vector biological detection and early warning method based on image analysis;
Fig. 2 is a schematic block diagram of a container disease medium biological detection and early warning system based on image analysis in the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: referring to fig. 2, the embodiment provides a container disease medium biological detection and early warning system based on image analysis, which comprises an image acquisition module, an identification and classification module, a comprehensive evaluation module and an early warning and scheduling module, wherein the whole system is applied to a field where a plurality of containers are stacked, and each container needs to be filled with corresponding goods, so that the condition in the container needs to be detected in real time, each container needs to be ensured to be kept in a closed state before detection, the internal environment of the container is prevented from being influenced by the outside, and the accuracy of the disease medium biological detection in the container is ensured;
The image acquisition module divides the interior of each container into at least four equally-divided image acquisition subareas and acquires image data in each image acquisition subarea; dividing the interior of each container into four image acquisition partitions can help to improve the comprehensiveness and accuracy of image acquisition so as to better detect possible vector organisms;
the container is divided into four or more areas, each area is ensured to cover the whole container, no blind area exists, reasonable division can be performed according to the size and the shape of the container, each area can be ensured to be fully covered, and the container can be divided into four areas in a shape of a Chinese character 'tian';
Setting corresponding image acquisition equipment, such as a high-definition camera or a cloud deck for monitoring, in each divided area; ensuring that the image capture device of each partition is able to capture clear, high quality image data and to cover all corners and details of the area; starting an image acquisition device, starting to acquire data of each image acquisition partition, ensuring stable device position in the acquisition process, ensuring good image quality, avoiding image blurring or unclear caused by movement or vibration, and integrating the image data acquired by each image acquisition partition into a system for subsequent processing and analysis;
For example, assuming we have a standard container, we divide its interior into four image acquisition bays: front, rear, left and right; in each subarea, a corresponding camera is arranged for image acquisition; after the image acquisition equipment is started, each camera starts to capture the image data of the partition where the camera is positioned; for example, the front camera captures an image of the front of the container, the rear camera captures an image of the rear of the container, and so on; after integrating the image data acquired by all the subareas, the system analyzes and processes the data to detect whether any disease vector organisms or suspected disease vector organisms exist in the container.
The identification and classification module is used for analyzing and classifying the image data acquired in each image acquisition partition by utilizing image processing and machine learning technologies, and identifying common disease media organisms, such as: the method comprises the steps of (1) mosquitoes or flies and suspected disease organisms, counting the number of common disease organisms in each image acquisition partition, and if the common disease organisms or the suspected disease organisms are not identified in image data acquired by any image acquisition partition, executing a strategy of halving the image acquisition frequency;
wherein the image processing and machine learning techniques include a target detection algorithm and an image classification algorithm;
Detecting organisms in the image by means of a target detection algorithm, e.g. YOLO, SSD; the algorithms can locate and mark the position of the living being in the image, providing a basis for subsequent classification;
Then classifying and identifying the detected organisms by using an image classification algorithm, such as CNN and SVM; these algorithms may extract features from a large number of training samples and classify them; in the training process, the image samples containing various disease-related organisms are required to be used for training a model, and corresponding category information is marked so that the model learns and distinguishes different types of organisms;
for common disease organisms such as mosquitoes and flies, a CNN model can be trained for identification;
the training data set contains various types and varieties of mosquito images, category information is marked, and the existence of mosquitoes can be accurately identified in the images through the trained model; for unusual disease agents, the system marks them as suspected disease agents and requires more data and expertise to identify; for example, if an unknown insect appears in the image, the system may label it as a suspected vector organism and further classify and evaluate it;
For example: assuming that the system detects the existence of mosquitoes in the images in the container, determining the existence of organisms in the images by the system through a target detection algorithm, and marking the positions of the mosquitoes; then, the system classifies and identifies the organisms by using the trained CNN model, and the model learns various types of mosquito images in the training process, so that the organisms can be accurately identified as mosquitoes, and a rectangular frame of each common disease vector organism can be obtained, thereby facilitating the subsequent statistics of the number of the common disease vector organisms.
After labeling as suspected vector organisms, the further evaluation was performed in the following manner: carrying out subsequent evaluation by using a complex combined model, wherein the method comprises the following specific steps and examples;
Feature extraction and pretreatment: extracting features from the image, including morphological features, color features, and texture features, which can help describe and distinguish suspected disease organisms; preprocessing the image, such as denoising, graying and scale normalization, so as to ensure the accuracy and consistency of feature extraction;
Feature fusion and classification: fusing the extracted features to construct a comprehensive feature vector; classifying and identifying the feature vectors by using machine learning algorithms such as a Support Vector Machine (SVM) and a random forest, wherein the algorithms can learn interfaces among different categories in the training process so as to accurately classify suspected vector organisms;
Expert system assistance: introducing an expert system, and further judging and evaluating suspected disease vector organisms by using the knowledge and experience of field experts; the expert system can evaluate and predict the risk of the suspected disease vector organism under the specific characteristic combination based on rules, a knowledge base or expert experience;
model integration and comprehensive evaluation: integrating the machine learning model and the result of the expert system, and comprehensively evaluating the risk degree of suspected disease vector organisms; the results of the models can be integrated by adopting a weighted average method to obtain a final evaluation result;
For example: assuming an unknown insect appears in the image, the system marks it as a suspected vector organism; firstly, extracting morphological characteristics and color characteristics of the insects from an image by a system; these features are then classified using a machine learning algorithm, such as SVM; meanwhile, the system inputs the feature vector into an expert system, and the expert system evaluates suspected vector organisms according to the knowledge and experience of field experts; finally, the system integrates the machine learning model and the expert system result, and comprehensively evaluates the risk degree of the suspected disease vector organism so as to take corresponding early warning and countermeasure.
The identification and classification module is built in each image acquisition device, can perform preliminary identification and classification operation, and can rapidly identify the disease vector organisms in the images to obtain common disease vector organisms and suspected disease vector organisms; the risk and detailed situation of the suspected disease vector organisms are not considered, but are sent to the cloud outside the system, and the follow-up evaluation is carried out through a combined model carried in the cloud, so that the operation load of each image acquisition device is greatly reduced, and the system is ensured to be capable of efficiently and accurately obtaining the classified common disease vector organisms and the suspected disease vector organisms.
Specifically, common disease organisms in the image can be rapidly identified and counted through a target detection and image classification algorithm, uncertain suspected disease organisms can be rapidly marked, a basis is provided for subsequent deep analysis and evaluation, when any disease organisms are not detected in a certain area in the container, the image acquisition frequency can be automatically reduced, resources are saved, and the dynamic adjustment mechanism can improve the adaptability and the flexibility of the system.
The comprehensive evaluation module is used for constructing a data analysis calculation model according to the preprocessed environmental data, the number of common disease organisms and the number of suspected disease organisms under the condition that the existence of the common disease organisms in the corresponding image acquisition subareas is recognized and obtained by combining the acquired environmental data in each container, and generating a risk degree pre-estimated value corresponding to each image acquisition subarea in the same containerAnd predicting the risk degree of each containerCarrying out average calculation to obtain a risk degree index Q of the corresponding container;
The environmental data in each container comprises the temperature and the humidity in each image acquisition zone in the same container, and the pretreatment of the environmental data, the number of common disease vector organisms and the number of suspected disease vector organisms comprises the following steps: normalizing the environmental data, the number of common disease vector organisms and the number of suspected disease vector organisms;
generating risk degree predicted value corresponding to each image acquisition partition in the same container The formula is as follows:
In the method, in the process of the invention, Representing the temperature of the corresponding image acquisition zone,The preset standard temperature is indicated to be the same,Indicating the difference in temperature and the temperature value,Representing the humidity of the corresponding image acquisition zone,Indicating the preset standard humidity level to be used,Indicating the difference in humidity value and,Representing the number of common disease agents within the corresponding image acquisition partition,Representing the suspected vector biomass in the corresponding image acquisition partition,Respectively the temperature difference value, the humidity difference value, the common vector quantity and the suspected vector quantity, andAnd (2) andThe range of the values is 0 to 1,N in the container represents the number of the corresponding image acquisition zone in the same container, and the sequence of the numbers is sequentially distributed according to the sequence from left to right and from front to back in the container;
It should be noted that, the standard temperature and the standard humidity respectively correspond to the standard values adapted to the disease vector organism, and the standard values are obtained according to historical experience and actual data statistics, for example: standard temperature is 25 ℃, and mark humidity is 70%; the larger the corresponding temperature difference value and humidity difference value are, the less adaptation to the growth or propagation of disease-related organisms is, and the lower the risk degree in the corresponding image acquisition zone in the container is, so that the temperature difference value and the humidity difference value are inversely proportional to the risk degree predicted value;
The more the number of common disease medium organisms and the number of suspected disease medium organisms, the higher the risk degree in the corresponding image acquisition partition in the container, so the number of common disease medium organisms and the number of suspected disease medium organisms are in direct proportion to the risk degree predicted value;
the formula according to which the risk level index Q of the container is generated is as follows:
Where n=1, 2, …, k is a positive integer, and the value of k is 4 in this embodiment.
The early warning scheduling module is used for sequencing a plurality of containers with risk degree indexes Q larger than zero in the same area according to the sequence from large to small to generate a first sequencing table, sending out early warning signals when the risk degree indexes Q of the corresponding containers are acquired to be larger than zero, triggering a GPS module in the corresponding containers, calculating the distance between each container sending out the early warning signals and a workstation by using a GIS tool, building a priority calculation model according to the risk degree indexes Q and the distance, generating priority indexes Pi corresponding to the containers, sequencing the priority indexes Pi corresponding to the containers according to the sequence from large to small to generate a second sequencing table, and sequentially operating the containers by staff in the workstation according to the sequence of the second sequencing table;
The important disinfection treatment is carried out on the high-risk container, so that the disease medium organisms are effectively eliminated, and the occurrence of subsequent harm is prevented; through the monitoring and accurate emergency dispatch of the system, the sanitary safety of goods in the container can be better ensured; the omnibearing prevention and control measure is helpful for practically maintaining the health of personnel and the quality safety of goods.
The generated sorting table can be used for monitoring by staff to determine the risk degree of the containers in the same batch, so that the arrangement condition of the containers with risks can be analyzed conveniently;
the process of calculating the distance between each container sending out the early warning signal and the workstation by using the GIS tool is as follows:
s101, acquiring accurate position information of a container and a working station of a worker through a global positioning system;
S102, inputting longitude and latitude coordinates of a container and a workstation by using a Geographic Information System (GIS) tool, such as a Google Maps API (application program interface) and an ArcGIS;
S103, in the GIS tool, a distance measuring tool can be used for calculating the linear distance or the actual path distance between the container and the workstation; for the linear distance, the GIS tool directly gives the linear distance between two points; for the actual path distance, the GIS tool takes the factors such as the ground surface topography and the like into consideration to give the distance under the actual path; the actual distance is specifically;
S104, after calculation is completed, the GIS tool gives the distance between the container and the workstation, and the distance is usually expressed in kilometers; this distance can be used as a reference for planning the travel or scheduling of the staff.
The formula according to which the priority index Pi corresponding to the container is generated is as follows:
In the method, in the process of the invention, Representing the distance value between the same container and the workstation,Respectively the risk degree index of the same container and the weight coefficient of the distance value between the container and the workstation, and，The value ranges of the two are all 0-1;
the workstation is a place for workers to rest and store disinfection tools;
Staff in the workstation carries out sequential operation to each container according to the order of the second sequencing table, and the content of operation is to carry out high-temperature sterilization treatment in the container with risk, eliminates the sick medium organism in the container, guarantees the sanitation of the internal environment of the container, reduces the harm of sick medium organism to the articles stored in the subsequent container.
Specifically, through combining environmental data in the container, many factors such as the biological quantity of disease vector, establish mathematical model and carry out the quantitative evaluation to the risk degree, can carry out individualized aassessment to the risk situation of the inside different regions of container, grasp whole risk condition more accurately, help better discern the high risk container of key prevention and control, provide the basis for subsequent dispatch and processing, based on container risk degree and distance factor, establish priority index model, can rationally arrange staff's processing order, guarantee that limited resources obtains optimal utilization, provide quick response to high risk region, the efficiency and the security of overall management have been improved.
Example 2: referring to fig. 1, based on embodiment 1, the present embodiment further provides a container disease vector biological detection and early warning method based on image analysis, which includes the following specific steps:
S1, dividing the interior of each container into at least four equally-divided image acquisition subareas, and acquiring image data in each image acquisition subarea;
s2, analyzing and classifying the image data acquired in each image acquisition partition by utilizing an image processing and machine learning technology, identifying common disease organisms and suspected disease organisms, counting the number of the common disease organisms and the number of the suspected disease organisms in each image acquisition partition, and executing a strategy of halving the image acquisition frequency if the common disease organisms or the suspected disease organisms are not identified in the image data acquired by any image acquisition partition;
S3, combining the acquired environmental data in each container, under the condition that common vector organisms exist in the corresponding image acquisition subareas, building a data analysis calculation model according to the preprocessed environmental data, the number of the common vector organisms and the number of suspected vector organisms, and generating a risk degree index Q of the corresponding container;
S4, sorting a plurality of containers in the same area according to the order from large to small, generating a sorting table I, sending out early warning signals when the risk degree index Q of the corresponding container is obtained to be larger than zero, calculating the distance between each container sending out the early warning signals and a workstation by using a GIS tool, building a priority calculation model according to the risk degree index Q and the distance, generating a priority index Pi corresponding to the container, sorting the priority indexes Pi corresponding to the containers according to the order from large to small, generating a sorting table II, and sequentially operating the containers by staff in the workstation according to the order of the sorting table II.
In the application, the related formulas are all the numerical calculation after dimensionality removal, and the formulas are one formulas for obtaining the latest real situation by software simulation through collecting a large amount of data, and the formulas are set by a person skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (9)
1. Container disease vector biological detection early warning system based on image analysis, its characterized in that includes:
the image acquisition module divides the interior of each container into at least four equally-divided image acquisition subareas and acquires image data in each image acquisition subarea;
The identification and classification module is used for analyzing and classifying the image data acquired in each image acquisition partition by utilizing an image processing and machine learning technology, identifying common disease organisms and suspected disease organisms, counting the number of the common disease organisms and the number of the suspected disease organisms in each image acquisition partition, and executing a strategy of halving the image acquisition frequency if the common disease organisms or the suspected disease organisms are not identified in the image data acquired by any image acquisition partition;
The comprehensive evaluation module is used for constructing a data analysis calculation model according to the preprocessed environmental data, the number of the common disease organisms and the number of the suspected disease organisms under the condition that the common disease organisms exist in the corresponding image acquisition subareas are identified and obtained by combining the acquired environmental data in each container, and generating a risk degree index Q of the corresponding container;
The warning scheduling module is used for sequencing a plurality of containers in the same area according to the sequence from large to small, a first sequencing table is generated, when the risk degree index Q of the corresponding container is obtained and is larger than zero, an early warning signal is sent out, a GIS tool is used for calculating the distance between each container sending out the early warning signal and a workstation, a priority computing model is built according to the risk degree index Q and the distance, a priority index Pi corresponding to the container is generated, the priority indexes Pi corresponding to the containers are sequenced according to the sequence from large to small, a second sequencing table is generated, and staff in the workstation sequentially operate the containers according to the sequence of the second sequencing table.
2. The image analysis-based container disease vector biological detection and early warning system according to claim 1, wherein: and setting corresponding image acquisition equipment in each divided area for acquiring image data.
3. The container disease vector biological detection and early warning system based on image analysis according to claim 2, wherein: the image processing and machine learning techniques include an object detection algorithm, which is any one of YOLO and SSD, and an image classification algorithm, which is any one of CNN and SVM.
4. The image analysis-based container vector biological detection and early warning system according to claim 3, wherein: the acquired environmental data in each container comprises the temperature and the humidity in each image acquisition zone in the same container, and then the process of preprocessing the environmental data, the number of common disease vector organisms and the number of suspected disease vector organisms is as follows: and normalizing the environmental data, the number of common disease-related organisms and the number of suspected disease-related organisms.
5. The image analysis-based container disease vector biological detection and early warning system according to claim 4, wherein: before the risk degree index Q of the corresponding container is generated, calculating a risk degree predicted value corresponding to each image acquisition partition in the same containerThe formula according to is as follows:
；
In the method, in the process of the invention, Representing the temperature of the corresponding image acquisition zone,/>Representing a preset standard temperature,/>Representing the temperature difference,/>Representing the humidity of the corresponding image acquisition partition,/>Representing a preset standard humidity,/>Indicating the difference in humidity value and,Representing the number of common disease vector organisms in the corresponding image acquisition partition,/>Representing suspected vector biomass in corresponding image acquisition partition,/>Preset proportionality coefficients of temperature difference, humidity difference, common vector quantity and suspected vector quantity respectively, and/>。
6. The image analysis-based container disease vector biological detection and early warning system according to claim 5, wherein: the formula according to which the risk level index Q of the container is generated is as follows:
；
where n=1, 2, …, k is a positive integer.
7. The image analysis-based container disease vector biological detection and early warning system according to claim 6, wherein: the process of calculating the distance between each container sending out the early warning signal and the workstation by using the GIS tool is as follows:
S101, acquiring accurate position information of a container and a working station of a worker;
S102, inputting longitude and latitude coordinates of a container and a workstation by using a Geographic Information System (GIS) tool comprising any one of Google Maps API and ArcGIS;
S103, in a GIS tool, calculating the actual path distance between the container and the workstation by using a distance measuring tool;
and S104, after the calculation is completed, the GIS tool gives the distance between the container and the workstation.
8. The image analysis-based container disease vector biological detection and early warning system according to claim 7, wherein: the formula according to which the priority index Pi corresponding to the container is generated is as follows:
；
In the method, in the process of the invention, Representing the distance value between the same container and the workstation,/>Respectively the risk degree index of the same container and the weight coefficient of the distance value between the container and the workstation, and/>。
9. The container vector biological detection and early warning method based on image analysis, which uses the system of any one of claims 1 to 8, is characterized by comprising the following steps:
S1, dividing the interior of each container into at least four equally-divided image acquisition subareas, and acquiring image data in each image acquisition subarea;
s2, analyzing and classifying the image data acquired in each image acquisition partition by utilizing an image processing and machine learning technology, identifying common disease organisms and suspected disease organisms, counting the number of the common disease organisms and the number of the suspected disease organisms in each image acquisition partition, and executing a strategy of halving the image acquisition frequency if the common disease organisms or the suspected disease organisms are not identified in the image data acquired by any image acquisition partition;
S3, combining the acquired environmental data in each container, under the condition that common vector organisms exist in the corresponding image acquisition subareas, building a data analysis calculation model according to the preprocessed environmental data, the number of the common vector organisms and the number of suspected vector organisms, and generating a risk degree index Q of the corresponding container;
S4, sorting a plurality of containers in the same area according to the order from large to small, generating a sorting table I, sending out early warning signals when the risk degree index Q of the corresponding container is obtained to be larger than zero, calculating the distance between each container sending out the early warning signals and a workstation by using a GIS tool, building a priority calculation model according to the risk degree index Q and the distance, generating a priority index Pi corresponding to the container, sorting the priority indexes Pi corresponding to the containers according to the order from large to small, generating a sorting table II, and sequentially operating the containers by staff in the workstation according to the order of the sorting table II.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410571369.1A CN118153914B (en) | 2024-05-10 | 2024-05-10 | Container disease vector biological detection early warning method and system based on image analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410571369.1A CN118153914B (en) | 2024-05-10 | 2024-05-10 | Container disease vector biological detection early warning method and system based on image analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118153914A true CN118153914A (en) | 2024-06-07 |
| CN118153914B CN118153914B (en) | 2024-07-23 |
Family
ID=91287070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410571369.1A Active CN118153914B (en) | 2024-05-10 | 2024-05-10 | Container disease vector biological detection early warning method and system based on image analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118153914B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801214A (en) * | 2021-03-17 | 2021-05-14 | 广东技术师范大学 | Mouse quantity prediction method based on interaction of mouse recognition terminal and cloud computing platform |
| US20220028535A1 (en) * | 2020-07-27 | 2022-01-27 | VergeSense, Inc. | Method for mitigating disease transmission in a facility |
| KR20220053718A (en) * | 2020-10-22 | 2022-05-02 | 주식회사 마크로젠 | Container type infectious disease diagnosis platform device |
| CN115660532A (en) * | 2022-11-11 | 2023-01-31 | 大连海事大学 | Control system of equipment is transported to whole car goods intelligence for truck container |
| CN115760682A (en) * | 2022-09-09 | 2023-03-07 | 安徽大学 | Multi-visual-range vector biological detection method and system |
| CN116612126A (en) * | 2023-07-21 | 2023-08-18 | 青岛国际旅行卫生保健中心(青岛海关口岸门诊部) | Container disease vector biological detection early warning method based on artificial intelligence |
| CN117740749A (en) * | 2024-02-08 | 2024-03-22 | 深圳市华盛源城市服务集团有限公司 | Urban disease medium density control system based on data analysis |
-
2024
- 2024-05-10 CN CN202410571369.1A patent/CN118153914B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220028535A1 (en) * | 2020-07-27 | 2022-01-27 | VergeSense, Inc. | Method for mitigating disease transmission in a facility |
| KR20220053718A (en) * | 2020-10-22 | 2022-05-02 | 주식회사 마크로젠 | Container type infectious disease diagnosis platform device |
| CN112801214A (en) * | 2021-03-17 | 2021-05-14 | 广东技术师范大学 | Mouse quantity prediction method based on interaction of mouse recognition terminal and cloud computing platform |
| CN115760682A (en) * | 2022-09-09 | 2023-03-07 | 安徽大学 | Multi-visual-range vector biological detection method and system |
| CN115660532A (en) * | 2022-11-11 | 2023-01-31 | 大连海事大学 | Control system of equipment is transported to whole car goods intelligence for truck container |
| CN116612126A (en) * | 2023-07-21 | 2023-08-18 | 青岛国际旅行卫生保健中心(青岛海关口岸门诊部) | Container disease vector biological detection early warning method based on artificial intelligence |
| CN117740749A (en) * | 2024-02-08 | 2024-03-22 | 深圳市华盛源城市服务集团有限公司 | Urban disease medium density control system based on data analysis |
Non-Patent Citations (1)
| Title |
|---|
| 朱彬彬;李枝金;李慧甫;沈超;薛宏俊;杜平;雷晓春;: "宜昌市城区常见病媒生物监测调查研究", 中华卫生杀虫药械, no. 06, 20 December 2011 (2011-12-20), pages 61 - 63 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118153914B (en) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Alvarez et al. | Body condition estimation on cows from depth images using Convolutional Neural Networks | |
| US20220051404A1 (en) | Pathological section image processing method and apparatus, system, and storage medium | |
| US20180089828A1 (en) | Colony contrast gathering | |
| Kellenberger et al. | 21 000 birds in 4.5 h: efficient large‐scale seabird detection with machine learning | |
| Millan et al. | On‐the‐Go Grapevine Yield Estimation Using Image Analysis and Boolean Model | |
| CN108241905A (en) | For predicting the method for soil and/or plant situation | |
| Goodbody et al. | Digital aerial photogrammetry for assessing cumulative spruce budworm defoliation and enhancing forest inventories at a landscape-level | |
| CN112819821B (en) | Cell nucleus image detection method | |
| CN113658174B (en) | Microkernel histology image detection method based on deep learning and image processing algorithm | |
| CN113052295B (en) | Training method of neural network, object detection method, device and equipment | |
| Zhang et al. | A hybrid framework for single tree detection from airborne laser scanning data: A case study in temperate mature coniferous forests in Ontario, Canada | |
| CN115512215B (en) | Underwater biological monitoring method, device and storage medium | |
| CN113378785A (en) | Forest type identification method and device | |
| US11610080B2 (en) | Object detection improvement based on autonomously selected training samples | |
| CN117218553A (en) | Control method of plant protection monitoring system and related equipment | |
| CN118153914B (en) | Container disease vector biological detection early warning method and system based on image analysis | |
| CN112465821A (en) | Multi-scale pest image detection method based on boundary key point perception | |
| WO2024002930A1 (en) | Vegetation management system and vegetation management method | |
| CN110738208A (en) | efficient scale-normalized target detection training method | |
| CN115424196A (en) | Tracking monitoring system based on artificial intelligence | |
| Iqbal et al. | Towards Efficient Segmentation and Classification of White Blood Cell Cancer Using Deep Learning | |
| Chang et al. | Spatiotemporal analysis using deep learning and fuzzy inference for evaluating broiler activities | |
| CN113850762A (en) | Eye disease identification method, device, equipment and storage medium based on anterior segment image | |
| Chellasamy et al. | Automatic training sample selection for a multi-evidence based crop classification approach | |
| Shirai et al. | Detection method for Convallaria keiskei colonies in Hokkaido, Japan, by combining CNN and FCM using UAV-based remote sensing data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |