Target detection and control system and method, container, electronic equipment and storage medium

Abstract

The invention discloses a target detection and control system and method, a container, electronic equipment and a storage medium. The method comprises the following steps: acquiring image information in a preset environment range; detecting and identifying the image information to determine whether the image information contains a target object; in response to the target object contained in the preset environment range, obtaining individual information and a behavior state of the target object; and adjusting or maintaining environment information in a preset environment range based on the behavior state of the target object. According to the method, the image information in the preset environment range is identified through a machine vision target detection technology, so that the variety, the individual, the appearance characteristics and the like of the target object in the preset environment range are obtained for viewing, observing, learning and knowing the individual information of the target object; and the health state of the fish is obtained according to a target detection algorithm, and a specific execution mechanism is controlled to execute operations such as feeding, oxygenation and light turning on and off, so that the monitoring accuracy of the target object is improved.

Description

Technical Field

[0001] This application relates to the field of computer vision technology, and specifically relates to an object detection and control system, method, container, electronic device, and storage medium. Background Art

[0002] Machine vision and object detection technologies have become an indispensable part of our daily lives. From facial recognition unlocking of smartphones to obstacle detection during vehicle driving, the applications of these technologies are constantly expanding, and their influence and popularity are growing at an unprecedented speed.

[0003] In related technologies, for example, in the management and intelligent monitoring of aquarium organisms, the monitoring methods are single and inaccurate, and the effects of breeding, intelligent monitoring, and automation control of aquarium organisms are not ideal. Summary of the Invention

[0004] In view of this, this application provides an object detection and control system, method, container, electronic device, and storage medium to solve the problems of single, inaccurate object detection methods and unsatisfactory monitoring and control effects in the prior art.

[0005] To solve the above technical problems, the first technical solution provided by this application is: to provide an object detection and control method, including:

[0006] Obtain image information within a preset environmental range;

[0007] Detect and identify the image information to determine whether the image information contains a target object;

[0008] In response to the target object being included within the preset environmental range, obtain the individual information and behavior state of the target object;

[0009] Based on the behavior state of the target object, adjust or maintain the environmental information within the preset environmental range.

[0010] In one embodiment, before obtaining the image information within the preset environmental range, it includes:

[0011] Establish an image processing model and train the image processing model;

[0012] The obtaining of the image information within the preset environmental range includes:

[0013] Dynamically collect the image information within the preset environmental range;

[0014] The detecting and identifying of the image information to determine whether the image information contains a target object includes:

[0015] Input the image information into the image processing model;

[0016] Use the image processing model to detect and recognize the image information to determine whether the target object is included within the preset environment range.

[0017] In one embodiment, in response to the target object being included within the preset environment range, obtaining the individual information and behavior state of the target object includes:

[0018] In response to the target object being included within the preset environment range, recognize the target object within the image information to obtain the individual information of the target object;

[0019] Track the target object to obtain the behavior state of the target object.

[0020] In one embodiment, based on the behavior state of the target object, adjusting or maintaining the environmental information within the preset environment range includes:

[0021] In response to the behavior state of the target object reaching a preset condition, adjust the environmental information; otherwise, maintain the current environmental information;

[0022] Wherein, the preset condition includes a preset state and a preset quantity; the preset state includes hunger, hypoxia, and illness; the preset quantity is 50% or more of the quantity of all the target objects.

[0023] In one embodiment, in response to the behavior state of the target object reaching a preset condition, adjusting the environmental information includes:

[0024] Classify the recognized target objects;

[0025] Summarize the quantity of each type of target object according to the classified information;

[0026] In response to the target object reaching a preset state and the quantity of the target objects reaching the preset state reaching the preset quantity, adjust the environmental information.

[0027] In one embodiment, the method further includes:

[0028] Dynamically display the individual information and behavior state of the target object externally using a display screen.

[0029] To solve the above technical problems, the second technical solution provided by this application is: to provide a target detection and control system, including:

[0030] An acquisition module, configured to acquire image information within a preset environment range;

[0031] A processing module, configured to detect and identify the image information to determine whether a target object is included in the image information;

[0032] A control module, configured to acquire the individual information and behavior state of the target object, and adjust or maintain the environmental information within the preset environment range based on the behavior state of the target object.

[0033] In an embodiment, the target detection and control system further includes: a display module, configured to dynamically display the individual information and the behavior state of the target object externally.

[0034] To solve the above technical problems, the third technical solution provided by the present application is: to provide a container, the interior of which has a first space, and the first space forms a preset environment range containing a plurality of target objects; wherein, a partial area or all areas of at least one side wall of the container are composed of a transparent display unit.

[0035] In an embodiment, the container is a fish tank, an aquarium, a pet museum or a zoo.

[0036] To solve the above technical problems, the fourth technical solution provided by the present application is: to provide an electronic device, including: a processor and a memory, the memory is connected to the processor and is configured to store a computer program that can run on the processor; wherein, when the processor executes the computer program, the method described in any one of the above is implemented.

[0037] To solve the above technical problems, the fifth technical solution provided by the present application is: to provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the above is implemented.

[0038] Advantages of this application: Different from the prior art, the object detection and control method of this application includes: obtaining image information within a preset environmental range; detecting and recognizing the image information to determine whether the image information contains a target object; in response to the target object being included within the preset environmental range, obtaining the individual information and behavioral state of the target object; and adjusting or maintaining the environmental information within the preset environmental range based on the behavioral state of the target object. This application uses machine vision object detection technology to identify the image information within the preset environmental range, so as to obtain the variety, individual, appearance characteristics, etc. of the target object within the preset environmental range, anchor the frame and display the individual information of the target object on the transparent display screen set on the aquarium for viewing, observing, learning, and understanding the individual information of the target object. And according to the object detection algorithm, the health status of the fish is obtained, and an instruction is sent to the lower computer to control specific actuators to perform operations such as feeding, oxygenation, and turning on the light, realizing the biological intelligent monitoring and automatic feeding within the preset environmental range, improving the monitoring accuracy of the target object; and at the same time facilitating observation and viewing. Description of the Drawings

[0039] To more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0040] Figure 1 It is a flowchart of the object detection and control method provided by an embodiment of this application;

[0041] Figure 2 It is a flowchart of the image processing of the object detection and control method provided by an embodiment of this application;

[0042] Figure 3 It is a schematic structural diagram of a container provided by an embodiment of this application;

[0043] Figure 4 is Figure 1 a flowchart of the sub-steps of step S2 provided;

[0044] Figure 5 is Figure 1 a flowchart of the sub-steps of step S3 provided;

[0045] Figure 6 is Figure 1 a flowchart of the sub-steps of step S4 provided;

[0046] Figure 7 It is a flowchart of the object detection and control method provided by another embodiment of this application;

[0047] Figure 8 It is a connection block diagram of an object detection and control system provided by an embodiment of the present application;

[0048] Figure 9 It is a schematic diagram of the working process of an object detection and control system provided by an embodiment of the present application;

[0049] Figure 10 It is a schematic diagram of an image enhancement processing flow provided by an embodiment of the present application;

[0050] Figure 11 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application;

[0051] Figure 12 It is a schematic block diagram of the structure of a computer-readable storage medium provided by an embodiment of the present application.

[0052] Explanation of reference numerals:

[0053] 100, object detection and control system; 10, acquisition module; 101, monitoring system; 1, container; 11, preset environmental range; 110, first space; 111, aquarium; 112, side wall; 12, image acquisition device; 20, processing module; 21, embedded processor; 22, conversion and transmission device; 30, display module; 301, display system; 31, display screen; 32, anchor box; 321, target object; 33, light source enhancement device; 34, human-computer interaction device; 35, text information; 40, control module; 401, automation system; 41, control device; 42, oxygen supply device; 43, automatic feeding device; 200, electronic device; 210, processor; 220, memory; 230, peripheral device interface; 240, radio frequency circuit; 250, display screen; 260, audio circuit; 270, power supply; 300, computer-readable storage medium. Detailed implementation manners

[0054] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0055] The terms "first", "second" and "first" in this application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" can expressly or implicitly include at least one of the features. All directional indications (such as up, down, left, right, front, back ...) in the embodiments of the present application are only used to explain the relative position relationship, movement conditions, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the steps or units listed, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0056] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0057] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device for processing personal information, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

[0058] In the research process of this application, it is found that: In recent years, with the breakthrough of deep learning technology, the performance of machine vision and object detection has been significantly improved. Convolutional neural networks and other advanced machine learning models have become the key driving forces in these fields, capable of handling complex visual tasks such as image classification, object tracking, and scene understanding. The progress of these technologies has promoted the development of industrial automation and intelligent manufacturing, and has been widely applied in multiple industries such as retail, healthcare, and security monitoring.

[0059] In related technologies, for example, in the management and intelligent monitoring of aquarium organisms, the monitoring methods are single and inaccurate, and the effects of aquaculture, intelligent monitoring, and automatic control of aquarium organisms are not ideal.

[0060] To solve the above problems, this application provides an object detection and control system, method, container, electronic device, and storage medium.

[0061] Please refer to Figures 1 to 3 and Figure 10 , Figure 1 is a flowchart of an object detection and control method provided by an embodiment of this application; Figure 2 is an image processing flowchart of an object detection and control method provided by an embodiment of this application; Figure 3 is a schematic structural diagram of a container provided by an embodiment of this application; Figure 10 is a schematic diagram of an image enhancement processing flow provided by an embodiment of this application.

[0062] The object detection and control method provided by this application may include the following steps:

[0063] S1: Obtain image information within a preset environment range 11.

[0064] Among them, the preset environment range 11 can be understood as the environment where the target object 321 is located. For example, when the target object 321 is a fish, the preset environment range 11 can be an aquarium 111; when the target object 321 is a pet, the preset environment range 11 can be a pet museum; when the target object 321 is other animals, the preset environment range 11 can be a zoo, etc.

[0065] S2: Detect and identify the image information to determine whether the target object 321 is included in the image information.

[0066] S3: In response to the target object 321 being included in the preset environment range 11, obtain the individual information and behavior state of the target object 321.

[0067] S4: Based on the behavior state of the target object 321, adjust or maintain the environmental information within the preset environment range 11.

[0068] The target detection and control method based on machine vision provided in the present application utilizes a combination of a machine vision target detection algorithm, a display screen 31 and an automated device to realize intelligent control and a preset environment range 11 that is easy to view, such as an aquarium 111. Among them, the target detection algorithm can automatically identify the species, individuals, and appearance characteristics of the organisms in the preset environment range 11, and the anchor frame 32 displays various information on the display screen 31 set outside the preset environment range 11 for viewing, observation, learning, and understanding the health status of the internal organisms. At the same time, the behavior state can reflect the needs and health status of the organisms to a certain extent, such as hungry organisms will ask for food outside the aquarium 111, oxygen-deficient organisms will frequently be located in the water surface area, and the swimming posture of sick organisms will change. Through the observation and identification of these behavior state characteristics, the automatic control device 41 performs operations such as feeding, turning on and off lights, oxygenation, and medication on the organisms to adjust the environmental information of the environment where the organisms are located, thereby realizing accurate monitoring of the target organisms and accurate adjustment of the environmental information.

[0069] In order to solve the above technical problems, the present application also provides a container. The structure of the container 1 is shown in FIG. Figure 3 shown.

[0070] The container 1 provided in an embodiment of the present application has a first space 110 therein, and the first space 110 forms a preset environment range 11 including a plurality of target objects 321; wherein a part or all of at least one side wall 112 of the container 1 is formed by a transparent display unit. The transparent display unit may be a part of the display screen 31.

[0071] In one embodiment, the container 1 may be a fish tank, an aquarium 111, a pet house or a zoo, and the target object 321 contained in the container 1 may be a fish, a pet or other animal. When the target object 321 is a fish, the preset environment range 11 may be a fish tank or an aquarium 111; when the target object 321 is a pet, the preset environment range 11 may be a pet house; when the target object 321 is other animals, the preset environment range 11 may be a zoo, etc., which is not specifically limited here.

[0072] For the convenience of description and illustration, the following embodiments of the present application take the aquarium 111 as the container 1 and the fish as the target object 321 as an example to specifically illustrate the technical solution of the present application.

[0073] S1: Acquire image information within a preset environment range 11.

[0074] See also Figures 1 to 3, specifically, the image information within the preset environment range 11 can be obtained through the image acquisition device 12, and the image acquisition device 12 can be a conventional camera, an industrial camera, or other devices capable of implementing the image acquisition function, etc. For example, the inside of the aquarium 111 is dynamically photographed by a camera to obtain the image information inside the aquarium 111.

[0075] Further, the step S1 of obtaining the image information within the preset environment range 11 may include: dynamically acquiring the image information within the preset environment range 11.

[0076] Specifically, dynamic acquisition can be understood as using the image acquisition device 12 to dynamically capture the images within the preset environment range 11. That is to say, the image capture within the preset environment range 11 is not to shoot at one position, but to shoot at multiple positions within the preset environment range 11 in multiple directions and at multiple angles, so as to obtain the image information of multiple positions within the preset range. For example, multiple image acquisition devices 12 can be arranged inside the aquarium 111, and each image acquisition device 12 is set to rotate and shoot cyclically within a certain range (for example, 0.5 meters to 2 meters) and at a certain angle (for example, 90 degrees to 270 degrees) to obtain the image information within the preset environment range 11. It can be understood that since the organisms within the preset environment range 11 are often in a dynamic state, the accuracy of image acquisition can be higher by dynamically acquiring the image information, and the detection accuracy of the target object 321 can be improved.

[0077] In one embodiment, before the step S1 of obtaining the image information within the preset environment range 11, the following steps may be included:

[0078] Establish an image processing model and train the image processing model.

[0079] Specifically, the image processing model uses object detection algorithms to detect and identify image information to determine whether the image contains a target object 321, such as fish. The object detection algorithms can be YOLO (You Only Look Once) series algorithms, RCN series algorithms (R-CNN, Region-based Convolutional Neural Network), SSD (Single Shot MultiBox Detector), or traditional machine learning feature extraction algorithms, etc. Any algorithm that can achieve the object detection function can be selected. The YOLO series algorithms are object detection algorithms based on deep learning, such as YOLOv3. The RCN series algorithms include R-CNN, Fast R-CNN, and Faster R-CNN, etc. The SSD algorithm can build multiple feature layers for detection on the basis of a basic network (such as VGG or ResNet). Each feature layer has a set of default anchor boxes 32, and the sizes and aspect ratios of these default anchor boxes 32 can be predefined. During the training process, by calculating the matching situation between the default anchor boxes 32 and the true target object 321 boxes, the loss function is used to train the model so that the model can accurately predict the position and category of the target object 321. The traditional machine learning feature extraction algorithms can be feature extraction algorithms such as Histogram of Oriented Gradient (HOG) or Local Binary Pattern (LBP).

[0080] Among them, the YOLO series algorithms, RCN series algorithms, and SSD are all current mainstream deep learning convolutional neural network algorithms. The dataset can be divided into a training set, a validation set, and a test set by including the original image and the manually annotated anchor box 32 information. After setting parameters such as the YAML (YAML Ain't Markup Language) model configuration file, epochs, and batch-size, the convolutional neural network can automatically train according to the structure set by YAML and the loaded dataset. Among them, YAML is a data serialization format, usually used for configuration files and data storage, which is convenient for reading and writing and can be parsed and generated by computer programs. The YAML file has the extension.yml or.yaml.

[0081] For example, during the training of an image processing model, the features of the target object 321 can be input into the image processing model in advance. The object detection algorithm continuously extracts image features for anchor box 32 prediction, and then compares the obtained results with the validation set, and continuously performs regression tasks through a loss function until the optimal model is obtained. The program algorithm can call and load the trained image processing model through a path. After inputting image information into the program, the object detection algorithm will automatically detect the target object 321 in the image information according to the previously trained image processing model, and identify the specified target object 321 in the image information. Traditional deep learning requires manual selection of features for model training, and its effect is not as good as that of deep learning convolutional neural networks, but it can still complete the object detection task; the above algorithms are only for illustrative purposes, and any solution that only changes the loaded image processing model or uses other object detection algorithms to achieve the purpose of this application should fall within the protection scope of this application.

[0082] Please refer to Figures 1 to 3 and Figure 10 , the process of making training data for the image processing model of this application can be as follows: The data source is preferably the data of the target object 321 collected in the actual background, with better recognition effect. It can also be migrated and trained based on cloud data or on the basis of a pre-trained open-source model. The open-source model does not specify a specific model. It can be data publicly released by large institutions, such as AI (Artificial Intelligence, manual intelligence) training data, or models or data trained by some small teams and shared on the network.

[0083] The means of image enhancement for images can include but are not limited to color jitter, grayscale transformation, brightness transformation, adding noise, filtering, etc.; for the enhanced images, multi-label image annotation can be performed using LabelImage (an open-source image annotation tool) or other annotation tools to produce two datasets for training, one is the basic information dataset, and the other is the monitoring information dataset; the label content of the basic information dataset can include the type, individual, appearance features, etc. of the target object 321; the label content of the monitoring information dataset can include deep features such as the diseased features and body posture features of the target object 321. Separating the datasets for annotation can train the model more flexibly, and the effect of the trained model is also better (in the training of deep learning models, for example, the image processing model of this application, the target can have multiple labels at the same time. For example, when identifying a certain target object 321 as a fish, it can have other labels such as biology, living thing, female, afraid, injured, etc. depending on the content of the training set and the parameters set by the program).

[0084] Further, when loading the same dataset, different types, depths, and structures of models will result in different training effects. The image processing model can be optimized according to specific circumstances. For example, for surface or simple features, depthwise separable convolutions can be used, the number of convolutional layers can be reduced, and a structure with lower precision requirements but faster speed can be used; for deep features, methods such as increasing the number of convolutional layers, the depth of feature extraction, using more complex convolutional modules and loss functions, and adding more attention mechanisms can be used to achieve better image recognition effects.

[0085] S2: Detect and recognize the image information to determine whether the target object 321 is included in the image information.

[0086] Specifically, the obtained image information can be detected and recognized by a processor, so as to recognize whether the target object 321 is included in the image information. For example, the processor is an embedded processor 21, and the embedded processor 21 is used to detect the image information to determine whether fish are included in the image information. The embedded processor 21 is used to carry the image processing model and call the target detection algorithm to perform recognition and detection on the image.

[0087] Further, taking the specific detection and recognition control program as an example of the YOLO algorithm, Python can be used as the programming language, and it can be written and run on the Window system through Pycharm (an integrated development environment (IDE) designed specifically for Python development). The program will automatically call the model according to the model path, load and perform target detection and recognition on the image information; using other programming languages or other operating systems, such as Mac, Linux, etc., the target detection function can also be achieved. Alternative behaviors that only change the specific model without changing the core function should all fall within the protection scope of this application.

[0088] Further, taking the program written in Python language as an example, the camera call program development package can be used to obtain and transmit the image information. The image processing model and image information can be loaded through save and read commands, and information sending and receiving can be achieved through the communication protocol support library. For example, the pyserial library (a library in Python for implementing serial communication) can be used to transmit information with a single-chip microcomputer, and the Modbus library (an industrial communication protocol for transmitting information between electronic devices) can be used to communicate with a PLC (Programmable Logic Controller).

[0089] Please refer to Figures 4 to 6 , Figure 4 is Figure 1 the flowchart of the sub-steps of step S2 provided; Figure 5 is Figure 1Flow chart of sub - steps of step S3 provided Figure 6 Yes Figure 1 Flow chart of sub - steps of step S4 provided

[0090] Please refer to Figure 4 Furthermore, step S2 of detecting and identifying the image information to determine whether the target object 321 is included in the image information may include:

[0091] S21: Input the image information into the image processing model

[0092] Specifically, input the image information obtained in the previous step into the image processing model to detect and identify the image information through the image processing model

[0093] S22: Use the image processing model to detect and identify the image information to determine whether the target object 321 is included within the preset environment range 11

[0094] Specifically, please refer to Figures 1 to 6 When training the image processing model mentioned above, the features of the target object 321 have been input into the image processing model in advance. Therefore, when using the image processing model to detect and identify the image information, input the image information into the image processing model, and the image processing model can call the target detection algorithm to determine whether the target object 321 is included in the image information. For example, train the image processing model with the features of various fish from multiple angles so that the image processing model can obtain the feature information of various fish. Thus, after inputting the image information captured within the preset environment range 11 into the image processing model, the image processing model can determine whether the fish is included in the image information according to the pre - trained fish features

[0095] S3: In response to the target object 321 being included within the preset environment range 11, obtain the individual information and behavior state of the target object 321

[0096] Specifically, that is, the image information within the preset environment range 11 contains the target object 321 to be obtained. For example, the image information captured in the aquarium 111 contains the image of fish. The individual information of the target object 321 may include the individual number of the target object 321, species information (including relevant introductions and popular science information, etc.); the behavior state may include the health state and abnormal information of the target object 321, etc

[0097] In one embodiment, please refer to Figure 5 When step S3 of obtaining the individual information and behavior state of the target object 321 in response to the target object 321 being included within the preset environment range 11 may include:

[0098] S31: In response to the target object 321 being included within the preset environment range 11, identify the target object 321 in the image information to obtain the individual information of the target object 321.

[0099] Specifically, for the identification process of the image information, it can be based on the information pre-stored in the image processing model, and by comparing this stored information with the image information, to identify whether the target object 321 is included in the image information; in the case of identifying that the target object 321 is included, the individual information of the target object 321 can be further obtained. For example, if it is identified that the image information in the aquarium 111 includes fish, then the number, species, characteristics, and habits of the fish can be further obtained and displayed.

[0100] S32: Track the target object 321 to obtain the behavior state of the target object 321.

[0101] Specifically, after identifying the target object 321 and obtaining the individual information of the target object 321, the target object 321 can be further tracked to specifically determine what state the target state is currently in. For example, whether the fish has been in an active state or a resting state for a certain period of time, whether it is in a hungry state, whether it is in a healthy state or a diseased state, etc.

[0102] S4: Based on the behavior state of the target object 321, adjust or maintain the environmental information within the preset environment range 11.

[0103] Specifically, after obtaining the behavior state of the target object 321, it is possible to select whether to adjust the environmental information within the current preset environment range 11 where the target object 321 is located or to continue to maintain the current environmental information according to the behavior state of the target object 321. Among them, the environmental information can be understood as environmental parameters or information on the impact on the target object 321. For example, the environmental information can include the temperature, humidity, oxygen content, etc. in the aquarium 111, and can also include whether to perform feed delivery, drug delivery, etc. on the aquarium 111.

[0104] For example, when the behavior state of the fish is abnormal, the environmental information can be adjusted accordingly according to the specific abnormal situation; if everything is normal, the current environmental information can be continued to be maintained. It can be understood that the normal state can be pre-stored in the process of training the image processing model, and the abnormal state can be obtained by comparing with the normal state. For example, hungry fish will ask for food outside the aquarium 111, fish lacking oxygen will frequently be in the water surface area, and diseased fish will have a changed swimming posture, etc. By these behavior state information of the fish, the ecological situation in the aquarium 111 can be judged, so as to determine whether the environmental information needs to be adjusted.

[0105] In one embodiment, please refer toFigures 1 to 6 , step S4 of adjusting or maintaining the environmental information within the preset environmental range 11 based on the behavior state of the target object 321 may include:

[0106] S40: In response to the behavior state of the target object 321 reaching a preset condition, adjust the environmental information; otherwise, maintain the current environmental information.

[0107] Specifically, the preset conditions include a preset state and a preset quantity. The preset state includes but is not limited to states such as hunger, hypoxia, illness, etc. The preset quantity is 50% or more of the quantity of all target objects 321. For example, if more than half of the fish show a state of hunger, then at this time, the automatic feeding device 43 can be controlled to feed the fish. At the same time, the preset condition can also include a preset time. For example, if a certain number of target objects 321 reach a certain shape state and it lasts for more than 0.5 hours, then it can be determined that the target object 321 has indeed reached the preset condition, and the environmental information can be adjusted.

[0108] For example, if the target object 321 is a fish, and the swimming frequency and range of the fish in the water are small, or it stays in the waterweeds or at the bottom for a long time, and at the same time, if it shows a behavior of asking for food from other objects passing outside the aquarium 111, it can be determined that the fish is in a state of hunger. At this time, a signal can be transmitted through the control device 41 to control the automatic feeding device 43 to feed the fish. The mention of a certain number of fish is to exclude the situation where an individual affects the whole. The state and behavior of an individual have a certain degree of randomness, and setting a threshold can avoid such situations.

[0109] In one embodiment, please refer to Figure 6 , step S40 of adjusting the environmental information in response to the behavior state of the target object 321 reaching a preset condition may include:

[0110] S41: Classify the identified target objects 321.

[0111] Specifically, for example, classify multiple target objects 321 identified in the image information to facilitate feature extraction and state recognition of the target objects 321 of the same category.

[0112] S42: Summarize the quantity of each category of target objects 321 according to the classified information.

[0113] Specifically, after classifying multiple target objects 321, the quantity of each type of target object 321 can be obtained. For example, if multiple types and a large number of fish are identified from the image information, the fish can be classified at this time, and then the quantity of each category of fish can be counted. When sufficient fish information is collected, the behavior state of individual fish can be determined.

[0114] S43: Adjust the environmental information in response to the target object 321 reaching a preset state and the number of target objects 321 reaching the preset state reaching a preset quantity.

[0115] Specifically, setting a preset quantity limit for the behavior state of the target object 321 is to prevent the accidental behaviors of the target object 321 from being recorded and then being determined as a group behavior, thereby improving the accuracy of judging the behavior state of the target object 321. It can be understood that if only individual target objects 321 reach the preset state, the environmental information may not be adjusted temporarily. For example, if a very small number of fish are detected to show hunger, feed should not be immediately dispensed; when more than half of a certain category of target objects 321 exhibit the same behavior, such as asking for food outward, it can be determined that basically all target objects 321 of this category are in a hungry state. For example, when 60% of the fish continuously show hunger behaviors within 0.5 hours, it can be determined that the behavior state of the fish is indeed hunger and feed can be dispensed.

[0116] Please refer to Figure 7 , Figure 7 which is a flowchart of the target detection and control method provided by another embodiment of the present application.

[0117] In another embodiment, the target detection and control method may further include:

[0118] S5: Dynamically display the individual information and behavior state of the target object 321 externally using the display screen 31.

[0119] Specifically, the individual information and behavior state information of the fish can be dynamically displayed through the transparent display screen 31. For example, the display screen 31 can be fixed on the outer surface of one side of the aquarium 111, taking into account the observation of the anchor box 32 of the target object 321 and the state of the fish in the aquarium 111. By dynamically displaying externally through the display screen 31, on the one hand, it can facilitate viewers to understand the characteristic information of the target object 321 at any time to increase the viewing interest; on the other hand, it can facilitate managers to timely understand the behavior state of the target object 321, so as to timely obtain the health status and abnormal behaviors of the target object 321 and thus take corresponding measures in a timely manner.

[0120] To solve the above technical problems, the present application also provides a target detection and control system 100.

[0121] Please refer to Figures 8 to 10 , Figure 8 which is a connection block diagram of the target detection and control system provided by an embodiment of the present application; Figure 9 which is a working process schematic diagram of the target detection and control system provided by an embodiment of the present application;Figure 10 It is a schematic diagram of an image enhancement processing flow provided by an embodiment of the present application.

[0122] Please refer to Figures 8 to 9 , the target detection and control system 100 provided by the present application includes an acquisition module 10, a processing module 20, and a control module 40. The acquisition module 10 is used to acquire image information within a preset environment range 11. The processing module 20 is used to detect and identify the image information to determine whether a target object 321 is included in the image information. The control module 40 is used to acquire the individual information and behavior state of the target object 321, and adjust or maintain the environmental information within the preset environment range 11 based on the behavior state of the target object 321.

[0123] Specifically, the acquisition module 10 may include an image acquisition device 12, and the image acquisition device 12 is used to capture and shoot dynamic images. For example, the image acquisition device 12 may be a conventional camera, an industrial camera, or other devices capable of implementing image acquisition functions. The processing module 20 may include a processor and a signal conversion and transmission device 22, etc. The processor may be an embedded processor 21, such as a computer, or a single-chip microcomputer that meets the requirements. The signal conversion and transmission device 22 depends on the specific situation, and either a wired or wireless transmission device can be used, such as RS485, COM, network cable, Bluetooth transmission, etc. The control module 40 may control the devices set within the preset environment range 11 to perform automated operations based on the processing results of the processing module 20, such as feeding or oxygen supply, etc. At the same time, the control module 40 may control the acquisition module 10 to acquire image information in real time and perform real-time monitoring of the target object 321.

[0124] Exemplarily, please refer to Figure 9 , for example, an oxygen supply device 42, an automatic feeding device 43, and a control device 41 may be set within the preset environment range 11. The control module 40 built in the control device 41 controls the oxygen supply device 42 and the automatic feeding device 43, so that when the target object 321 reaches a preset state and the number of target objects 321 reaching the preset state reaches a preset number, the oxygen supply device 42 is controlled to supply oxygen, or the feed is put through the automatic feeding device 43, etc.

[0125] In one embodiment, please refer to Figures 8 to 10 , the target detection and control system 100 provided by the present application may further include a display module 30, and the display module 30 is used to dynamically display the individual information and behavior state of the target object 321 externally.

[0126] Specifically, the display module 30 may include a display screen 31, a light source enhancement device 33, and a human-computer interaction device 34. The display screen 31 may specifically be a transparent display screen 31 to reduce the impact on a preset environment range 11 such as the aquarium 111. The embedded processor 21 is used to load an image processing model and call a target detection algorithm to detect and identify image information. The signal conversion and transmission device 22 is used to convert the result obtained by the embedded processor 21 into an electrical signal and send it to the display module 30, and then display the anchor box 32 and the corresponding text information 35, etc. on the transparent display screen 31. It can be understood that the text information 35 may include individual information such as the number, species, characteristics, and habits of the target object 321, as well as behavior status and abnormal information, etc.

[0127] The light source enhancement device 33 is arranged on the installation surface of the transparent display screen 31 and is used to improve the display brightness and clarity for external viewing.

[0128] Furthermore, the light source enhancement device 33 may be a lighting device installed at a fixed point within the preset environment range 11, a light bar installed along the edge of the installation surface, or a light source that irradiates from the outside of the preset environment range 11 into the inside of the preset environment range 11.

[0129] Enhancing the image can improve the robustness of the image processing model. Specific image enhancement means include but are not limited to color jitter, grayscale transformation, brightness transformation, adding noise, filtering processing, etc.

[0130] The human-computer interaction device 34 may be integrally provided with the display screen 31 or a control screen provided on one side of the display screen 31, which may include a plurality of control buttons (not shown in the figure), so that it can be used by viewers. For example, the viewer can select the target object 321 to be viewed on the human-computer interaction device 34, as well as the corresponding individual information and behavior status information of the target object 321, thereby enhancing the viewing experience.

[0131] It can be understood that through the control module 40 of the above target detection and control system 100 and the oxygen supply device 42, automatic feeding device 43, etc. controlled by it, an automated system 401 can be formed to automatically supply oxygen and automatically feed the target object 321. The image acquisition device 12, the embedded processor 21, and the signal conversion and transmission device 22 can form a monitoring system 101 to monitor the preset environment range 11 and the target object 321 in real time. The display screen 31, the light source enhancement device 33, and the human-computer interaction device 34 can form a display system 301 to display the objects monitored by the monitoring system 101, so as to achieve accurate, efficient monitoring and real-time display of the preset environment range 11 and the target object 321.

[0132] Exemplarily, the above technical solution of the present application combines machine vision target detection technology, automation technology, and transparent screen technology, and uses the aquarium 111 as a carrier to perform intelligent monitoring and automated feeding of fish information. By identifying the species, individuals, appearance characteristics, etc. of the fish in the aquarium 111, the anchor box 32 and display various information on the transparent screen provided on the aquarium 111 for viewing, observing, learning, and understanding the health status of the internal fish, etc.; and obtain the health status of the fish according to the target detection algorithm, send instructions to the lower computer, and control the specific execution mechanism to perform operations such as feeding, oxygenation, and turning on the light, so as to improve the monitoring accuracy of the fish in the aquarium 111; at the same time, it is convenient for observation and viewing.

[0133] The target detection and control method disclosed in the present application includes: acquiring image information within a preset environmental range; detecting and recognizing the image information to determine whether the image information contains a target object; in response to the target object being included within the preset environmental range, acquiring the individual information and behavior state of the target object; and adjusting or maintaining the environmental information within the preset environmental range based on the behavior state of the target object. The present application uses machine vision target detection technology to identify the image information within the preset environmental range to obtain the species, individuals, appearance characteristics, etc. of the target object within the preset environmental range, anchor box and display the individual information of the target object on the transparent display screen provided on the aquarium for viewing, observing, learning, and understanding the individual information of the target object. And obtain the health status of the fish according to the target detection algorithm, send instructions to the lower computer, and control the specific execution mechanism to perform operations such as feeding, oxygenation, and turning on the light, so as to realize intelligent monitoring and automated feeding of organisms within the preset environmental range, improve the monitoring accuracy of the target object; at the same time, it is convenient for observation and viewing.

[0134] Please refer to Figure 11 , Figure 11 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0135] The electronic device 200 may specifically include a processor 210 and a memory 220. The memory 220 is coupled to the processor 210.

[0136] The processor 210 is used to control the operation of the electronic device 200. The processor 210 may also be referred to as a CPU (Central Processing Unit, central processing unit). The processor 210 may be an integrated circuit chip with signal processing capabilities. The processor 210 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor 210 may also be any conventional processor, etc.

[0137] The memory 220 is used to store computer programs, which can be RAM, ROM, or other types of storage devices. Specifically, the memory may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In some embodiments, the non-transitory computer-readable storage media in the memory is used to store at least one program code.

[0138] The processor 210 is used to execute the computer programs stored in the memory 220 to implement the object detection and control method described in the embodiments of the object detection and control method of the present application.

[0139] In some embodiments, the electronic device 200 may further include: a peripheral device interface 230 and at least one peripheral device. The processor 210, the memory 220, and the peripheral device interface 230 may be connected through a bus or signal lines. Each peripheral device may be connected to the peripheral device interface 230 through a bus, signal lines, or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 240, a display screen 250, an audio circuit 260, and a power supply 270.

[0140] The peripheral device interface 230 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 210 and the memory 220. In some embodiments, the processor 210, the memory 220, and the peripheral device interface 230 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 210, the memory 220, and the peripheral device interface 230 can be implemented on a separate chip or circuit board, and this embodiment does not limit this.

[0141] The radio frequency circuit 240 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 240 communicates with the communication network and other communication devices through electromagnetic signals, and the radio frequency circuit 240 is the communication circuit of the electronic device 200. The radio frequency circuit 240 converts electrical signals into electromagnetic signals for transmission, or converts the received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 240 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, and so on. The radio frequency circuit 240 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, metropolitan area network, intranet, generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area network, and / or WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 240 may further include a circuit related to NFC (Near Field Communication), which is not limited in this application.

[0142] The display screen 250 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 250 is a touch display screen, the display screen 250 also has the ability to collect touch signals on or above the surface of the display screen 250. The touch signals can be input to the processor 210 for processing as control signals. At this time, the display screen 250 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, there may be one display screen 250, which is disposed on the front panel of the electronic device 200; in other embodiments, there may be at least two display screens 250, which are respectively disposed on different surfaces of the electronic device 200 or are in a foldable design; in other embodiments, the display screen 250 may be a flexible display screen, which is disposed on the curved surface or the folding surface of the electronic device 200. Even, the display screen 250 can be set to an irregular non-rectangular shape, that is, a special-shaped screen. The display screen 250 can be prepared using materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0143] The audio circuit 260 may include a microphone and a speaker. The microphone is used to collect sound waves of the user and the environment, and convert the sound waves into electrical signals for input to the processor 210 for processing, or input to the radio frequency circuit 240 to achieve voice communication. For the purpose of stereo collection or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the electronic device 200. The microphone may also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert the electrical signal from the processor 210 or the radio frequency circuit 240 into sound waves. The speaker may be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into audible sound waves, but also convert the electrical signal into inaudible sound waves for uses such as ranging. In some embodiments, the audio circuit 260 may further include a headphone jack.

[0144] The power supply 270 is used to supply power to each component in the electronic device 200. The power supply 270 may be alternating current, direct current, a disposable battery or a rechargeable battery. When the power supply 270 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charging technology.

[0145] For a detailed description of the functions and execution processes of each functional module or component in the embodiment of the electronic device 200 of the present application, reference may be made to the description in the embodiment of the object detection and control method of the present application above, and details are not repeated here.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed electronic device 200 and the object detection and control method may be implemented in other ways. For example, the embodiments of the electronic device 200 described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

[0147] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple 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.

[0148] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0149] Please refer to Figure 12 , Figure 12 which is a schematic block diagram of the structure of a computer-readable storage medium provided by an embodiment of the present application.

[0150] Refer to Figure 12 , when the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in the computer-readable storage medium 300. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions / computer programs for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical discs, as well as computer devices such as computers, mobile phones, laptop computers, tablet computers, cameras, etc. having the above storage media.

[0151] The description of the execution process of the program data in the computer-readable storage medium 300 can refer to the embodiments of the object detection and control method of the present application described above, and will not be repeated here.

[0152] The above are only the embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A target detection and control method, characterized in that, Including: Obtain image information within a preset environment range; Detect and recognize the image information to determine whether the image information contains a target object; In response to the target object being included within the preset environment range, obtain the individual information and behavior state of the target object; Based on the behavior state of the target object, adjust or maintain the environmental information within the preset environment range.

2. The method according to claim 1, wherein: Before obtaining the image information within the preset environment range, it includes: Establish an image processing model and train the image processing model; The obtaining of the image information within the preset environment range includes: Dynamically collect the image information within the preset environment range; The detecting and recognizing of the image information to determine whether the image information contains a target object includes: Input the image information into the image processing model; Use the image processing model to detect and recognize the image information to determine whether the target object is included within the preset environment range.

3. The method according to claim 2, wherein: The obtaining of the individual information and behavior state of the target object in response to the target object being included within the preset environment range includes: In response to the target object being included within the preset environment range, recognize the target object within the image information to obtain the individual information of the target object; Track the target object to obtain the behavior state of the target object.

4. The method according to claim 3, wherein: The adjusting or maintaining of the environmental information within the preset environment range based on the behavior state of the target object includes: In response to the behavior state of the target object reaching a preset condition, adjust the environmental information; otherwise, maintain the current environmental information; Wherein, the preset condition includes a preset state and a preset quantity; the preset state includes hunger, hypoxia, and illness; the preset quantity is 50% or more of the quantity of all the target objects.

5. The method according to claim 4, wherein: The adjusting of the environmental information in response to the behavior state of the target object reaching a preset condition includes: Classify the recognized target objects; Summarize the quantity of each type of target object according to the classified information; In response to the target object reaching a preset state and the quantity of the target objects reaching the preset state reaching the preset quantity, adjust the environmental information.

6. The method according to any one of claims 1 to 5, characterized in that, It further includes: Dynamically display the individual information and behavior state of the target object externally using a display screen.

7. A target detection and control system, characterized in that, Including: An obtaining module for obtaining image information within a preset environment range; A processing module for detecting and recognizing the image information to determine whether the image information contains a target object; A control module for obtaining the individual information and behavior state of the target object and adjusting or maintaining the environmental information within the preset environment range based on the behavior state of the target object.

8. The object detection and control system according to claim 7, wherein It further includes: A display module for dynamically displaying the individual information and behavioral status of the target object externally.

9. A container, characterized in that, The interior of the container has a first space that forms a preset environmental range containing multiple target objects; wherein, a partial area or the entire area of at least one side wall of the container is composed of a transparent display unit.

10. The container according to claim 9, wherein The container is a fish tank, an aquarium, a pet museum or a zoo.

11. An electronic device, characterized in that, Comprising: A processor; A memory connected to the processor for storing a computer program that can run on the processor; Wherein, when the processor executes the computer program, the method described in any one of claims 1 to 6 is implemented.

12. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the method described in any one of claims 1 to 6 is implemented.

Images