Pet defecation behavior supervision method, device and system

Abstract

The invention belongs to the technical field of smart communities, and particularly relates to a pet defecation behavior supervision method, device and system, and the method comprises the steps: recognizing smell data collected by a smell sensor, and triggering an infrared sensor associated with the smell sensor to collect an infrared image when the smell is recognized to be abnormal; analyzing the infrared image to obtain a smell source type, and when the smell source type is a living body, obtaining a color image when the infrared image is collected from the image collector; inputting the smell data, the infrared image and the color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result; when the defecation behavior recognition result is that the pet defecation behavior exists, pet defecation reminding information is sent out. The community pet defecation behavior can be intelligently supervised, and the problems that in the prior art, a pet defecation behavior recognition method is high in false alarm rate and low in accuracy are solved.

Description

Technical Field

[0001] This article relates to the field of smart community technology, and in particular to a method, device and system for monitoring pet defecation behavior. Background Art

[0002] With the rapid development of urbanization, community members have higher requirements for the community environment. For example, community members hope that the community has a clean and tidy environment. However, there is a phenomenon of community members adopting pets, and there is a problem of uncivilized defecation when pets go out. Due to the uneven quality of pet owners, some pet owners fail to consciously clean up pet feces, resulting in pet defecation behavior affecting environmental hygiene. At the same time, pet feces may carry some viruses and bacteria, and may also pose a certain threat to human health.

[0003] In the prior art, the method for identifying the defecation behavior of pets includes: capturing the defecation behavior of pets through a camera, and then analyzing the captured image to identify the defecation and urination of the pets. Once the identification is successful, the pattern recognition module will further analyze the type of defecation and urination of the pets, such as urine, feces, etc.

[0004] However, the pet defecation behavior recognition method based on camera images has the problems of high false alarm rate and low accuracy. For example, when other objects are similar to pet excrement, they may be mistakenly identified as pet excrement, resulting in false alarms. For example, in poor lighting conditions or when objects are obstructed by hair, it may be difficult to accurately identify pet excrement. Summary of the invention

[0005] The present invention provides a pet defecation behavior monitoring method, device and system, which are used to solve the technical problems of high false alarm rate and low accuracy in the prior art pet defecation behavior recognition method.

[0006] In order to solve the above technical problems, the first aspect of this invention provides a method for monitoring pet defecation behavior, which is applied to a community, wherein a plurality of odor sensors, a plurality of infrared sensors and a plurality of image collectors are arranged in the community, and each odor sensor is associated with at least one infrared sensor, and the method comprises:

[0007] Identify the odor data collected by the odor sensor, and when an abnormal odor is identified, trigger the infrared sensor associated with the odor sensor to collect an infrared image;

[0008] Analyze the infrared image to obtain the type of odor source, and when the type of odor source is a living body, obtain a color image when the infrared image is collected from the image collector;

[0009] Inputting the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result, wherein the defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes the odor data, infrared image and color image acquired at the same time;

[0010] When the defecation behavior recognition result is that the pet has defecation behavior, a pet defecation reminder message is issued.

[0011] As a further embodiment of the present invention, the pet defecation behavior sample and the pet non-defecation behavior sample determination process include:

[0012] Determine the time period when pets defecate on various roads within the community;

[0013] According to the time period information of the pet defecating on each road in the community, multiple sets of data are collected, wherein each set of data includes odor data, infrared images and color images obtained at the same time;

[0014] For each group of data, the odor data in the group of data is analyzed to determine whether the odor is abnormal: if the odor is abnormal, the infrared image is identified to determine whether there is a living thing; if there is a living thing, the label of the group of data is set to a pending label; if there is no living thing, the label of the group of data is set to no pet excretion behavior; if the odor is normal, the label of the group of data is set to no pet excretion behavior;

[0015] The data of the pending label is sent to the user terminal, so that the user can label the data of the pending label through the user terminal.

[0016] As a further embodiment of the present invention, after identifying the presence of pet defecation behavior, the method further includes:

[0017] Tracking dynamic objects and identifying the types of dynamic objects in color images acquired by the image collector;

[0018] If the dynamic object includes a pet and a person, determining a suspected association relationship between the pet and the person according to the dynamic object tracking result;

[0019] The suspected association relationship is searched from the historical association library, and if the search is successful, a reminder message is sent to the person in the suspected association relationship.

[0020] As a further embodiment of the present invention, determining the suspected association relationship between the pet and the person according to the dynamic object tracking result includes:

[0021] Each pet and person in the tracking result is formed into a pending association group. The number of times the pending association group is collected is determined based on the color images collected by other image collectors in the Internet of Things. When the number is greater than a predetermined value, it is determined that the pets and people in the pending association group have a suspected association relationship.

[0022] As a further embodiment of this invention, the pet defecation behavior supervision method further includes:

[0023] If the search for the suspected association relationship in the historical association library fails, the number of times and positions of the pets in the suspected association relationship are counted based on the color images collected by the image collector in the Internet of Things;

[0024] Based on the number and location of pet appearances in the suspected association relationship, an inspection task is generated and issued.

[0025] As a further embodiment of this invention, the process of establishing the historical association library includes:

[0026] Obtain color images collected by an image collector in the Internet of Things within a preset time period;

[0027] Analyzing feature information in the color image collected within a first predetermined time period;

[0028] For each color image collected within the first predetermined time period, analyzing whether the feature information of the color image contains animal feature information and human feature information, and if so, retaining the color image;

[0029] Analyzing whether the animal and the person in the retained image have an association relationship, and if so, establishing an association relationship between the animal feature information and the person feature information;

[0030] The historical association library is composed of the association relationships between the plurality of animal characteristic information and the human characteristic information.

[0031] As a further embodiment of the present invention, after identifying the presence of pet defecation behavior, the method further includes:

[0032] The duration of the abnormal odor detected by the odor sensor is counted, and when the duration reaches a predetermined time, a cleaning reminder message is issued.

[0033] As a further embodiment of this invention, after the pet defecation reminder message is issued, the following steps are also included:

[0034] The number of reminders for the same pet within the second predetermined time period is counted, and when the number of reminders exceeds the predetermined number, a ticket instruction for the person associated with the pet is sent to the property management system.

[0035] The second aspect of the present invention provides a pet defecation behavior monitoring device, which is applied to a community, wherein a plurality of odor sensors, a plurality of infrared sensors, and a plurality of image collectors are arranged in the community, and each odor sensor is associated with at least one infrared sensor, and the device comprises:

[0036] A detection module, used to identify odor data of the odor sensor, and trigger the infrared sensor associated with the odor sensor to collect infrared images when an abnormal odor is identified;

[0037] An analysis module, used for analyzing the infrared image to obtain the type of odor source, and when the type of the odor source is a living body, obtaining a color image when the infrared image is collected from the image collector;

[0038] A recognition module, used for inputting the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result, wherein the defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes the odor data, infrared image and color image acquired at the same time;

[0039] The alarm module is used to issue a pet defecation reminder message when the defecation behavior recognition result is that the pet has defecation behavior.

[0040] The third aspect of the present invention provides a pet defecation behavior supervision system, which is applied to the community, and the system comprises:

[0041] A plurality of odor sensors, a plurality of infrared sensors, a plurality of image collectors and a processor, wherein the processor is connected to the odor sensors, the infrared sensors and the image collectors, and each odor sensor is associated with at least one infrared sensor:

[0042] The odor sensor is used to collect odor data;

[0043] The processor is used to identify the odor data, and when an abnormal odor is identified, trigger the infrared sensor associated with the odor sensor to collect an infrared image; analyze the infrared image to obtain the type of odor source, and when the odor source type is a living body, obtain the color image of the infrared image when it is collected from the image collector; input the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result; when the defecation behavior recognition result is that the pet has defecation behavior, issue a pet defecation reminder message;

[0044] The defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes odor data, infrared images and color images acquired at the same time.

[0045] The fourth aspect of this document provides a computer device, including a memory, a processor, and a computer program stored on the memory, and when the computer program is run by the processor, it executes instructions of the pet defecation behavior monitoring method described in any of the aforementioned embodiments.

[0046] A fifth aspect of the present invention provides a computer storage medium having a computer program stored thereon, which, when executed by a processor of a computer device, executes instructions of the method for supervising the defecation behavior of a pet as described in any of the aforementioned embodiments.

[0047] A sixth aspect of the present invention is a computer program product, which includes a computer program. When the computer program is run by a processor of a computer device, it executes instructions of the pet defecation behavior monitoring method described in any of the aforementioned embodiments.

[0048] The pet defecation behavior monitoring method, device and system provided in this paper, by identifying the odor data collected by the odor sensor, determines whether the odor data is abnormal, and if the odor data is abnormal, triggers the infrared sensor associated with the odor sensor to collect infrared images; analyzes the infrared image to obtain the odor source type, when the odor source type is a living body, obtains the color image when the infrared image is collected from the image collector; inputs the odor data, infrared image and color image into the pre-trained defecation behavior recognition model to obtain the pet defecation behavior recognition result; when the defecation behavior recognition result is that the pet defecation behavior exists, a pet defecation reminder message is issued. This paper analyzes whether the odor data collected by the odor sensor is abnormal in real time. If the odor is abnormal, further analyzes whether the infrared image collected by the infrared sensor contains a living body, thereby reducing the false alarm rate generated by only identifying the color image, and triggers the infrared image when the odor is abnormal, which can reduce the monitoring computing power. At the same time, the odor data, infrared image and color image are input into the pre-trained defecation behavior recognition model together, enriching the feature information and improving the model recognition accuracy and efficiency.

[0049] In order to make the above and other purposes, features and advantages of this article more obvious and easy to understand, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of this article or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of this article. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1The structural diagram of the pet defecation behavior monitoring system in the embodiment of this article is shown;

[0052] Figure 2 A first flow chart of the pet defecation behavior monitoring method according to the embodiment of this invention is shown;

[0053] Figure 3 A flowchart showing a process of determining a pet defecation behavior sample and a pet non-defecation behavior sample in an embodiment of this invention;

[0054] Figure 4 A second flow chart of the method for supervising pet defecation behavior according to an embodiment of the present invention is shown;

[0055] Figure 5 A flowchart of determining a suspected association relationship between a pet and a person in an embodiment of this invention is shown;

[0056] Figure 6 A third flow chart of the pet defecation behavior monitoring method according to the embodiment of this invention is shown;

[0057] Figure 7 A flowchart showing the process of establishing a historical association library in the embodiment of this invention is shown;

[0058] Figure 8 A fourth flow chart of the pet defecation behavior monitoring method according to the embodiment of this invention is shown;

[0059] Fig. 9 A fifth flow chart of the pet defecation behavior monitoring method according to the embodiment of this invention is shown;

[0060] Fig.10 The structural diagram of the pet defecation behavior monitoring device according to the embodiment of this invention is shown;

[0061] Fig.11 A structural diagram of a computer device according to an embodiment of this invention is shown.

[0062] Description of the accompanying symbols:

[0063] 101. Odor sensor;

[0064] 102. Infrared sensor;

[0065] 103. Image collector;

[0066] 104. Processor;

[0067] 1010. Detection module;

[0068] 1020. Analysis module;

[0069] 1030, identification module;

[0070] 1040, alarm module;

[0071] 1102. Computer equipment;

[0072] 1104. Processor;

[0073] 1106. Memory;

[0074] 1108. Driving mechanism;

[0075] 1110, input / output module;

[0076] 1112. Input device;

[0077] 1114. Output device;

[0078] 1116. Presentation equipment;

[0079] 1118. Graphical user interface;

[0080] 1120. Network interface;

[0081] 1122. Communication link;

[0082] 1124. Communication bus. DETAILED DESCRIPTION

[0083] The following will be combined with the drawings in the embodiments of this article to clearly and completely describe the technical solutions in the embodiments of this article. Obviously, the described embodiments are only part of the embodiments of this article, not all of the embodiments. Based on the embodiments of this article, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this article.

[0084] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0085] This specification provides method operation steps as described in the embodiments or flow charts, but more or fewer operation steps may be included based on routine or non-creative work. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the system or device product is executed in practice, it can be executed in the order of the method shown in the embodiments or the drawings or in parallel.

[0086] It should be noted that the pet defecation behavior supervision method, device and system in this article can be used in the field of smart communities, and can also be used in any field other than the field of smart communities. The application field of the pet defecation behavior supervision method, device and system in this article is not limited.

[0087] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments of this specification comply with the relevant provisions of national laws and regulations.

[0088] It should be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0089] In one embodiment of the present invention, a pet defecation behavior monitoring system is provided to solve the technical problems of high false alarm rate and low accuracy in the prior art pet defecation behavior recognition method.

[0090] Specifically, Figure 1 As shown, the pet defecation behavior monitoring system includes:

[0091] A plurality of odor sensors 101 , a plurality of infrared sensors 102 , a plurality of image collectors 103 and a processor 104 . The processor 104 is connected to the odor sensors 101 , the infrared sensors 102 and the image collectors 103 . Each odor sensor 101 is associated with at least one infrared sensor 102 .

[0092] The odor sensor 101 collects odor data and transmits it to the processor 104 for identification;

[0093] When the processor 104 identifies an abnormal odor, the infrared sensor 102 collects an infrared image and transmits it to the processor 104 for identification, while the image collector 103 collects a color image;

[0094] When the processor 104 recognizes a living body based on the infrared image, it obtains the color image captured by the image collector 103, and inputs the odor data, infrared image and color image into the pre-trained defecation behavior recognition model for recognition; when the defecation behavior recognition model recognizes it as a pet's defecation behavior, it issues a pet defecation reminder message.

[0095] Specifically, multiple odor sensors are arranged in the community, and each odor sensor can be associated with one or more infrared sensors to collect infrared images of one or more ranges around the odor sensor, and one or more image collectors can also be arranged around the odor sensor to collect color images of one or more ranges around the odor sensor. The processor can be set in a computer device in a property management room, or in an embedded device with a control function. The processor can also include multiple processors, each of which is a processor of a different device. For example, a processor is set in the odor sensor, and the odor sensor is connected to the infrared sensor, which is not limited in this article.

[0096] The odor sensor collects odor data once every predetermined time. The predetermined time can be set by the user and is not limited in this article.

[0097] The processor can process the odor data, extract the characteristics of the odor data, such as peak value, average value, standard deviation, frequency component, etc., and compare it with the odor data collected over a long period of time in an environment without abnormal odors in the community. If there is a significant difference, it is considered to be an abnormal odor. At this time, the infrared sensor is triggered to collect infrared images and transmit them to the processor for identification. At the same time, the image collector collects color images.

[0098] The processor can process the infrared image, extract infrared image features, such as temperature distribution, hot spot location and intensity, etc., detect whether there is a specific area in the infrared image with a temperature higher than the surrounding environment temperature. If so, it is considered that there is a living body. The shape contour of the infrared image can also be extracted and the shape contour is classified. The classification method can be a simple rule matching, or a decision tree, K-nearest neighbor and other machine learning algorithms, combined with temperature difference detection and classification algorithms to determine whether there is a living body. If there is a living body, the processor obtains the color image collected by the image collector, and inputs the odor data, infrared image and color image into the pre-trained defecation behavior recognition model for recognition. The defecation behavior recognition model can be a machine learning algorithm or a deep learning algorithm, which is not limited in this article.

[0099] This embodiment realizes intelligent supervision of the defecation behavior of pets in the community. By judging the odor data collected by the odor sensor, if there is abnormal odor data, the infrared sensor is triggered to collect infrared images and the image collector is triggered to collect color images, thereby reducing the operating cost. At the same time, when there is an abnormal odor, the infrared image is used to judge whether there is a living body. When there is a living body, the defecation behavior recognition model is triggered for recognition, thereby reducing invalid recognition of the model. The odor data, infrared image and color image are combined and input into the pre-trained defecation behavior recognition model for recognition, which enriches the feature information and improves the model recognition accuracy, thereby solving the problems of high false alarm rate and low accuracy in the pet defecation behavior recognition method.

[0100] In some embodiments of the present invention, a method for identifying pet defecation behavior is also provided. Figure 2 As shown, pet defecation behavior supervision methods include:

[0101] Step 210, identifying the odor data collected by the odor sensor, and triggering the infrared sensor associated with the odor sensor to collect an infrared image when an abnormal odor is identified;

[0102] Step 220, analyzing the infrared image to obtain the type of the odor source, and when the type of the odor source is a living body, obtaining a color image when the infrared image is collected from the image collector;

[0103] Step 230, input the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result.

[0104] The defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes odor data, infrared images, and color images acquired at the same time;

[0105] Step 240: When the defecation behavior identification result indicates that the pet has defecation behavior, a pet defecation reminder message is issued.

[0106] In the above step 230, the defecation behavior model is trained by training samples collected in advance in the community. Pet non-defecation behavior samples also include collected images similar to various shapes such as pets and pet feces. In specific implementations, pet defecation behavior samples and non-defecation behavior samples meet a certain ratio, such as 3:7, which can be set according to actual conditions. The defecation behavior model recognition results are the presence of pet defecation behavior and the absence of pet defecation behavior. For example, 1 indicates the presence of pet defecation behavior, and 0 indicates the absence of pet defecation behavior.

[0107] This embodiment realizes intelligent supervision of the defecation behavior of pets in the community. By judging the odor data collected by the odor sensor, if there is abnormal odor data, the infrared sensor is triggered to collect infrared images and the image collector is triggered to collect color images, thereby reducing the operating cost. At the same time, when there is an abnormal odor, the infrared image is used to judge whether there is a living body. When there is a living body, the defecation behavior recognition model is triggered for recognition, thereby reducing invalid recognition of the model. The odor data, infrared image and color image are combined and input into the pre-trained defecation behavior recognition model for recognition, which enriches the feature information and improves the model recognition accuracy, thereby solving the problems of high false alarm rate and low accuracy in the pet defecation behavior recognition method.

[0108] In one embodiment of this invention, Figure 3As shown, the process of determining the pet defecation behavior samples and pet non-defecation behavior samples for modeling includes:

[0109] Step 310, determining the time period information of the pet defecating on each road in the community;

[0110] Step 320, collecting multiple sets of data based on the time period information of the pet defecating on each road in the community, wherein each set of data includes odor data, infrared images, and color images acquired at the same time;

[0111] Step 330, for each set of data, analyzing the odor data in the set of data to determine whether the odor is abnormal, if not, setting the label of the set of data as no pet excretion behavior, if yes, executing step 340;

[0112] Step 340, identifying the infrared image to determine whether there is a living thing, if not, setting the label of the group of data as no pet excretion behavior, if so, setting the label of the group of data as a pending label;

[0113] Step 350 , sending the data of the pending label to the user terminal, so that the user can label the data of the pending label through the user terminal.

[0114] Specifically, in the above step 310, the sanitation conditions of various roads in the community can be recorded by video recording, and the time periods when pets defecate are concentrated can be counted. The time periods when pets defecate are concentrated can also be counted by interviewing cleaning staff or other staff.

[0115] When the above step 320 is implemented, the number of groups of collected data can be determined based on the frequency of the pet's historical defecation counted in each time period. For example, the greater the frequency, the greater the possibility of defecation behavior, and the larger the number of corresponding groups of collected data.

[0116] In the above step 330, by extracting odor data features, such as peak value, average value, standard deviation, frequency component, etc., and comparing with odor data collected over a long period of time in an environment without abnormal odors in the community, if there is a significant difference, it is considered to be an abnormal odor.

[0117] In the above step 340, the infrared image is identified to determine whether there is a temperature characteristic of a living thing, for example, whether the temperature is between 37° C. and 39° C. If so, it is determined that there is a living thing.

[0118] In the above step 350, the user tags the pending tag data to further determine whether there is pet defecation. This step can avoid recognition errors, for example, recognizing abnormal odors from other areas, and at the same time, the infrared image contains pedestrians or animals that may pass by.

[0119] This embodiment divides pet defecation behavior samples and pet non-defecation behavior samples to determine a training set for training a defecation behavior recognition model.

[0120] In one embodiment of this invention, Figure 4 As shown, after identifying the presence of pet defecation behavior, it also includes:

[0121] Step 410, after the defecation behavior recognition result is that the pet has defecation behavior, the dynamic object is tracked and the type of the dynamic object is identified in the color image collected by the image collector;

[0122] Step 420: If the dynamic object includes a pet and a person, a suspected association relationship between the pet and the person is determined based on the dynamic object tracking result;

[0123] Step 430, searching the suspected association relationship from the historical association library, and if the search is successful, sending a reminder message to the person in the suspected association relationship.

[0124] Specifically, in the above step 410, when the defecation behavior recognition result is that the pet has defecation behavior, the image collector continuously collects multiple color images of the target area at time intervals, tracks dynamic objects and identifies the type of dynamic objects based on the collected multiple color images, and the target area is the area displayed by the first color image collected by the triggering image collector. The tracking of dynamic objects can use existing algorithms, and the present invention does not limit this.

[0125] In step 420, when the pet and the person both appear in the tracking screen during the tracking time period, it is considered that the person may be the owner of the pet and has a suspected association relationship.

[0126] In step 430, the characteristic relationship between the pet and the owner is stored in the historical association library. The historical association library can be determined by the relationship between the pet and the owner registered in the property.

[0127] After identifying the defecation behavior of the pet, this embodiment tracks the pet and the person in the color image, thereby locking the target pet and the person, providing a basis for triggering an alarm.

[0128] In one embodiment of this invention, Figure 5 As shown, the above step 420 determines the suspected association relationship between the pet and the person according to the dynamic object tracking result, including:

[0129] Step 510, forming each pet and person in the tracking result into a pending association group, and determining the number of times the pending association group is collected according to the color images collected by other image collectors in the Internet of Things;

[0130] Step 520: When the number is greater than a predetermined value, it is determined that there is a suspected association relationship between the pet and the person in the pending association group.

[0131] Specifically, in the above step 510, each pet and person in the tracking result is formed into a pending association group. If there is a one-to-many, many-to-one, or many-to-many situation of pets and people, multiple pending association groups are formed, and the number of times collected in the multiple pending association groups is determined according to the color images collected by other image collectors in the Internet of Things;

[0132] In the above step 520, when the number is greater than a predetermined value, it is determined that the pet and the person in the pending association group have a suspected association relationship. If the pet corresponds to multiple possible suspected association relationships, the multiple possible suspected association relationships are sorted according to the number of times. Among the multiple possible suspected association relationships, the pet and the person in the multiple possible suspected association relationships corresponding to the maximum number of times are determined to have a suspected association relationship. The predetermined value can be determined according to the detection accuracy, and the present invention does not specifically limit this.

[0133] In one embodiment of this invention, Figure 6 As shown, the above step 430 searches for the suspected association relationship from the historical association library, and further includes:

[0134] Step 440: if the search for the suspected association relationship in the historical association library fails, the number of times and positions of the pets in the suspected association relationship are counted based on the color image collected by the image collector in the Internet of Things;

[0135] Step 450: Generate and issue a patrol task based on the number of times and positions of the pets in the obtained suspected association relationship.

[0136] Specifically, in the above step 450, according to the number of times and locations of pets appearing in the suspected association relationship, a patrol task is generated and issued, and the patrol task can be issued to the community security personnel, who will conduct patrols according to the number of times and locations of pets appearing. Through patrols, targets (such as wild cats and dogs) can be expelled or captured, thereby purifying the community environment and improving the living / working experience of community personnel.

[0137] In one embodiment of this invention, Figure 7 As shown in the figure, the process of establishing the historical association library includes:

[0138] Step 710, obtaining a color image collected by an image collector in the Internet of Things within a preset time period;

[0139] Step 720, analyzing feature information in the color image collected within a first predetermined time period;

[0140] Step 730, for each color image collected within the first predetermined time period, analyzing whether the feature information of the color image contains animal feature information and human feature information, and if so, retaining the color image;

[0141] Step 740, analyzing whether the animal and the person in the retained image have an association relationship, and if so, establishing an association relationship between the animal feature information and the person feature information;

[0142] Step 750: A history association library is formed by association relationships between a plurality of the animal feature information and the human feature information.

[0143] Specifically, in the above step 710, the estimated time period is determined by the time period information of the pet defecating on each road in the community. The start time, collection duration, collection interval, etc. of the estimated time period are determined based on the time period information of the pet defecating on each road in the community.

[0144] The feature information in step 720 includes object information, person information and animal information.

[0145] In step 730, the animal feature information may be the animal's outline, hair, color, etc., and the human feature information may be the human face, body shape, etc. If the feature information includes the animal feature information and the human feature information, the color image is retained.

[0146] In step 740, it is analyzed whether the animals and people in the retained images have an association relationship. The administrator may conduct a preliminary screening and record the information after the preliminary screening, or contact the owner for confirmation and then record the information, and establish an association relationship between the animal feature information and the human feature information.

[0147] This embodiment can improve the efficiency of determining the relationship between pets and people through automation.

[0148] In one embodiment of this invention, Figure 8 As shown, after the pet defecation reminder message is issued, it also includes:

[0149] Step 250, counting the duration of the abnormal odor detected by the odor sensor, and when the duration reaches a predetermined time, issuing a cleaning reminder message.

[0150] Specifically, in the above step 250, the cleaning reminder information includes the cleaning task type, the employee number of the available cleaning staff, the cleaning operation time, the cleaning operation location, the cleaning tools required, etc.

[0151] This embodiment determines the cleaning status of pet feces by detecting the duration of the odor, and then promptly issues a cleaning reminder to clean the pet feces in time.

[0152] In one embodiment of this invention, Fig. 9As shown, after the pet defecation reminder message is issued, it also includes:

[0153] Step 260, counting the number of reminders for the same pet within the second predetermined time period, and when the number of reminders exceeds the predetermined number, sending a ticket instruction for the person associated with the pet to the property management system.

[0154] Specifically, in the above step 260, the second predetermined time period and the number of reminders can be set by the user, which is not limited herein.

[0155] This embodiment counts the number of pet reminders and issues punishment measures to the pet owner, thereby regulating the behavior of the pet owner.

[0156] Based on the same inventive concept, this article also provides a pet defecation behavior monitoring device, as described in the following embodiments. Since the principle of the pet defecation behavior monitoring device to solve the problem is similar to the pet defecation behavior monitoring method, the implementation of the device can refer to the pet defecation behavior monitoring method, and the repeated parts will not be repeated.

[0157] Specifically, Fig.10 As shown, the pet defecation behavior monitoring device includes:

[0158] The detection module 1010 is used to identify the odor data of the odor sensor, and when an abnormal odor is identified, trigger the infrared sensor associated with the odor sensor to collect an infrared image;

[0159] The analysis module 1020 is used to analyze the infrared image to obtain the type of the odor source, and when the type of the odor source is a living body, obtain the color image when the infrared image is collected from the image collector;

[0160] The recognition module 1030 is used to input the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result, wherein the defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes the odor data, infrared image and color image acquired at the same time;

[0161] The alarm module 1040 is used to issue a pet defecation reminder message when the defecation behavior recognition result is that the pet has defecation behavior.

[0162] This embodiment realizes intelligent supervision of the defecation behavior of pets in the community. By judging the odor data collected by the odor sensor, if there is abnormal odor data, the infrared sensor is triggered to collect infrared images and the image collector is triggered to collect color images, thereby reducing the operating cost. At the same time, when there is an abnormal odor, the infrared image is used to judge whether there is a living body. When there is a living body, the defecation behavior recognition model is triggered for recognition, thereby reducing invalid recognition of the model. The odor data, infrared image and color image are combined and input into the pre-trained defecation behavior recognition model for recognition, which enriches the feature information and improves the model recognition accuracy, thereby solving the problems of high false alarm rate and low accuracy in the pet defecation behavior recognition method.

[0163] The pet defecation behavior monitoring method, device and system provided in this article judge the data collected by the odor sensor and infrared sensor in turn, and only input the suspected pet defecation behavior into the pre-trained defecation behavior recognition model, which greatly reduces the frequency of calling model recognition and reduces the operating cost. By combining odor data, infrared images and color images for model training and recognition, the feature information is enriched, thereby improving the model recognition accuracy.

[0164] In one embodiment of the present invention, a computer device is also provided for implementing the method described in any of the above embodiments, such as Fig.11 The schematic diagram of the structure of the node of the embodiment of this article is shown. In this embodiment, the structure of the node in the side chain network and the node in the main chain network is described, which may include a relay node, a decision maker node or other functional nodes. The node is referred to as a computer device in this embodiment. The computer device 1102 may include one or more processors 1104, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The computer device 1102 may also include any memory 1106, which is used to store any kind of information such as code, settings, data, etc. Non-limiting, for example, the memory 1106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 1102. In one case, when the processor 1104 executes an associated instruction stored in any memory or a combination of memories, the computer device 1102 can perform any operation of the associated instruction. The computer device 1102 also includes one or more drive mechanisms 1108 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0165] The computer device 1102 may also include an input / output module 1110 (I / O) for receiving various inputs (via input devices 1112) and for providing various outputs (via output devices 1114). A specific output mechanism may include a presentation device 1116 and an associated graphical user interface 1118 (GUI). In other embodiments, the input / output module 1110 (I / O), input device 1112, and output device 1114 may not be included, and the computer device 1102 may be used as a computer device in a network. The computer device 1102 may also include one or more network interfaces 1120 for exchanging data with other devices via one or more communication links 1122. One or more communication buses 1124 couple the components described above together.

[0166] The communication link 1122 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 1122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0167] Corresponds to Figure 1-Figure 8 The method in this article also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are executed.

[0168] The embodiment of the present invention also provides a computer readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the following Figures 1 to 8 The method shown.

[0169] It should be understood that in the various embodiments of this document, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0170] It should also be understood that in the embodiments of this article, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0171] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this article.

[0172] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0173] In the several embodiments provided herein, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0174] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this article.

[0175] In addition, each functional unit in each embodiment of this invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.

[0176] If the 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 a computer-readable storage medium. Based on this understanding, the technical solution of this article is essentially 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of this article. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0177] Specific embodiments are used in this article to illustrate the principles and implementation methods of this article. The description of the above embodiments is only used to help understand the methods and core ideas of this article. At the same time, for general technicians in this field, according to the ideas of this article, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on this article.

Claims

1. A method for monitoring pet defecation behavior, characterized in that: Applied to a community, wherein a plurality of odor sensors, a plurality of infrared sensors, and a plurality of image collectors are arranged in the community, and each odor sensor is associated with at least one infrared sensor, the method comprises: Identify the odor data collected by the odor sensor, and when an abnormal odor is identified, trigger the infrared sensor associated with the odor sensor to collect an infrared image; Analyze the infrared image to obtain the type of odor source, and when the type of odor source is a living body, obtain a color image when the infrared image is collected from the image collector; Inputting the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result, wherein the defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes the odor data, infrared image and color image acquired at the same time; When the defecation behavior recognition result is that the pet has defecation behavior, a pet defecation reminder message is issued.

2. The pet defecation behavior monitoring method according to claim 1, characterized in that: The process of determining the pet defecation behavior sample and the pet non-defecation behavior sample includes: Determine the time period when pets defecate on various roads within the community; According to the time period information of the pet defecating on each road in the community, multiple sets of data are collected, wherein each set of data includes odor data, infrared images and color images obtained at the same time; For each group of data, the odor data in the group of data is analyzed to determine whether the odor is abnormal: if the odor is abnormal, the infrared image is identified to determine whether there is a living thing; if there is a living thing, the label of the group of data is set to a pending label; if there is no living thing, the label of the group of data is set to no pet excretion behavior; if the odor is normal, the label of the group of data is set to no pet excretion behavior; The data of the pending label is sent to the user terminal, so that the user can label the data of the pending label through the user terminal.

3. The pet defecation behavior monitoring method according to claim 1, characterized in that: After identifying the presence of pet defecation behavior, it also includes: Tracking dynamic objects and identifying the types of dynamic objects in color images acquired by the image collector; If the dynamic object includes a pet and a person, determining a suspected association relationship between the pet and the person according to the dynamic object tracking result; The suspected association relationship is searched from the historical association library, and if the search is successful, a reminder message is sent to the person in the suspected association relationship.

4. The pet defecation behavior monitoring method according to claim 3, characterized in that: Determine the suspected association relationship between the pet and the person according to the dynamic object tracking result, including: Each pet and person in the tracking result is formed into a pending association group. The number of times the pending association group is collected is determined based on the color images collected by other image collectors in the Internet of Things. When the number is greater than a predetermined value, it is determined that the pets and people in the pending association group have a suspected association relationship.

5. The pet defecation behavior monitoring method according to claim 3, characterized in that: The method further comprises: If the search for the suspected association relationship in the historical association library fails, the number of times and positions of the pets in the suspected association relationship are counted based on the color images collected by the image collector in the Internet of Things; Based on the number and location of pet appearances in the suspected association relationship, an inspection task is generated and issued.

6. The pet defecation behavior monitoring method according to claim 3, characterized in that: The process of establishing the historical association library includes: Obtain color images collected by an image collector in the Internet of Things within a preset time period; Analyzing feature information in the color image collected within a first predetermined time period; For each color image collected within the first predetermined time period, analyzing whether the characteristic information of the color image contains animal characteristic information and human characteristic information, and if so, retaining the color image; Analyze whether the animals and people in the retained images have a correlation relationship, and if so, establish a correlation relationship between the animal feature information and the human feature information; The historical association library is composed of the association relationships between the plurality of animal characteristic information and the human characteristic information.

7. The pet defecation behavior monitoring method according to claim 1, characterized in that: After identifying the presence of pet defecation behavior, it also includes: The duration of the abnormal odor detected by the odor sensor is counted, and when the duration reaches a predetermined time, a cleaning reminder message is issued.

8. The pet defecation behavior monitoring method according to claim 1, characterized in that: After sending a pet defecation reminder message, it also includes: The number of reminders for the same pet within the second predetermined time period is counted, and when the number of reminders exceeds the predetermined number, a ticket instruction for the person associated with the pet is sent to the property management system.

9. A pet defecation behavior monitoring device, characterized in that: Applied to a community, wherein a plurality of odor sensors, a plurality of infrared sensors, and a plurality of image collectors are arranged in the community, each odor sensor is associated with at least one infrared sensor, and the device comprises: A detection module, used to identify the odor data collected by the odor sensor, and trigger the infrared sensor associated with the odor sensor to collect infrared images when an abnormal odor is identified; An analysis module, used for analyzing the infrared image to obtain the type of odor source, and when the type of the odor source is a living body, obtaining a color image when the infrared image is collected from the image collector; A recognition module, used for inputting the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result, wherein the defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes the odor data, infrared image and color image acquired at the same time; The alarm module is used to issue a pet defecation reminder message when the defecation behavior recognition result is that the pet has defecation behavior.

10. A pet defecation behavior monitoring system, characterized in that: Applied to the community, the system includes: A plurality of odor sensors, a plurality of infrared sensors, a plurality of image collectors and a processor, wherein the processor is connected to the odor sensors, the infrared sensors and the image collectors, and each odor sensor is associated with at least one infrared sensor; The odor sensor is used to collect odor data; The processor is used to identify the odor data, and when an abnormal odor is identified, trigger the infrared sensor associated with the odor sensor to collect an infrared image; analyze the infrared image to obtain the type of odor source, and when the odor source type is a living body, obtain the color image of the infrared image when it is collected from the image collector; input the odor data, infrared image and color image into a pre-trained defecation behavior recognition model to obtain a pet defecation behavior recognition result; when the defecation behavior recognition result is that the pet has defecation behavior, issue a pet defecation reminder message; The defecation behavior recognition model is trained based on historical pet defecation behavior samples and pet non-defecation behavior samples, and each behavior sample includes odor data, infrared images, and color images acquired at the same time.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor of a computer device, the method according to any one of claims 1 to 8 is implemented.

13. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor of a computer device, the method according to any one of claims 1 to 8 is implemented.

Images