Intelligent sprinkler control method for road sanitation

Abstract

The present application relates to the field of program control technology, and in particular to a method for intelligent watering control for road sanitation. The method comprises the following steps: obtaining an image sequence of pedestrians on a predetermined watering path through a camera; judging whether the pedestrians are pulling their pets through a preset target recognition model according to the image sequence of the pedestrians; if there is a pedestrian pulling his pet, marking the pedestrian pulling the pet as a puller, and starting to execute the predetermined pre-watering control action in advance when approaching the puller, so as to reduce the interference of the pulled pet on the puller. The method for intelligent watering control for road sanitation provided by the present application can better avoid pedestrians on the road.

Description

Technical Field

[0001] The present application relates to the field of program control technology, and in particular to a method for controlling intelligent watering of road sanitation facilities. Background Art

[0002] To ensure pedestrian safety, road sanitation sprinkler trucks are typically equipped with cameras or sensors to detect pedestrians on the road ahead during watering operations. When a pedestrian is detected approaching, the truck automatically stops watering to avoid inconvenience or safety hazards. However, existing watering control methods primarily rely on identifying pedestrian positions, assuming that pedestrian behavior is predictable and controllable.

[0003] However, in real life, pedestrians may use leashes on the road to lead their pet dogs. Pet dogs' behavior is uncertain and easily stimulated by the external environment. When a sprinkler truck approaches, the alarm, the sound of water spraying, or the flow of water may startle the pet dog, causing it to suddenly change direction or speed. In this case, if the person pulling the dog avoids the normal pedestrian within the stop sprinkler area, the stop sprinkler area is small, and the pet dog may pull the pedestrian with the leash, causing the pedestrian to accidentally enter the sprinkler area. Or, the pedestrian may lose balance while trying to control the pet while avoiding the sprinkler area, resulting in non-contact accidents such as falls.

[0004] Therefore, the existing technology still has some problems, which makes it impossible to better avoid pedestrians during watering operations. Summary of the Invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a road sanitation intelligent sprinkler control method that can better avoid pedestrians on the road.

[0006] This application provides a road sanitation intelligent sprinkler control method, comprising the following steps:

[0007] Acquire an image sequence of pedestrians on a predetermined watering path through a camera;

[0008] Based on the image sequence of pedestrians on the road, a preset target recognition model is used to judge whether the pedestrians on the road are pulling the pet;

[0009] If there is a pedestrian on the road pulling the pet, the pedestrian pulling the pet is marked as the puller, and the predetermined pre-sprinkling control action is started in advance when approaching the puller to reduce the interference of the pulled pet on the puller.

[0010] Optionally, the following steps are also included:

[0011] Calculate the distance to the towing person to start watering in advance:

[0012] Obtaining a size ratio between the towing person and the towed pet, and calculating a pre-risk value based on the size ratio using a preset pre-risk value calculation function, wherein the pre-risk value calculation function is configured such that the closer the size of the towed pet is to the towing person, the higher the pre-risk value;

[0013] Based on the pre-risk value, a preset control watering distance calculation function is used to calculate the distance to the towing person at which controlled watering needs to be started in advance. The control watering distance calculation function is set so that the larger the pre-risk value, the larger the distance at which controlled watering needs to be started in advance.

[0014] The predetermined pre-sprinkling control action is started at the distance ahead of the towing person at which the water sprinkling control needs to be started.

[0015] Optionally, the body size ratio of the pulling person and the pulled pet is calculated by the following steps:

[0016] When a pulling person is detected, an image sequence of the pulling person in a first time window is acquired;

[0017] For each photo in the first time window, extract the outlines of the person pulling the pet and the person being pulled;

[0018] Calculate the outline area of ​​the person pulling the vehicle and the pet being pulled in each photo, and obtain the body ratio of the person pulling the vehicle and the pet being pulled using a preset body ratio calculation function;

[0019] The preset body shape ratio calculation function is:

[0020]

[0021] Where I is the total number of photos in the first time window, i is the i-th photo in the first time window, A(p,i) is the outline area of ​​the pulled pet in the i-th photo, and A(m,i) is the outline area of ​​the pulling person in the i-th photo;

[0022]

[0023] in, It is the average of the contour areas of the pulled pet in all photos within the entire first time window.

[0024] Optionally, the following steps are also included:

[0025] The predetermined pre-sprinkling control action includes an interference enhancement phase and an interference reduction phase. When the predetermined pre-sprinkling control action is started, the interference enhancement phase of a predetermined duration is first entered. During the interference enhancement phase, the interference stimulus to the outside during the sprinkling is enhanced. After exiting the interference enhancement phase, the interference reduction phase is entered to reduce the interference stimulus to the outside during the sprinkling until the position of the tractor is reached.

[0026] Based on the visible light image sequence of the towing person and the pre-set risk value when executing the predetermined pre-sprinkling control action, the distance required to control the sprinkling after the towing person is calculated:

[0027] During the interference enhancement phase, based on the visible light image sequence of the pulling person when the predetermined pre-sprinkling control action is executed, the posture change of the pulling person is obtained through a preset posture recognition model to determine whether to exit the interference enhancement phase;

[0028] According to the length of the interference enhancement phase, the pre-risk value is changed by a preset post-risk value calculation function to obtain a post-risk value, so that the longer the interference enhancement phase is, the lower the post-risk value obtained;

[0029] According to the post-risk value, the distance at which watering needs to be controlled after the person is pulled is calculated using a preset watering distance calculation function;

[0030] The interference reduction stage is maintained until the distance after the tractor is away from the tractor and the water sprinkling needs to be controlled, and then the interference reduction stage is exited.

[0031] Optionally, the preset posture recognition model is trained by the following steps:

[0032] Constructing the posture recognition model framework, which includes an input layer, a skeleton point feature extraction layer, a feature integration layer, a convolutional neural network layer and an output layer;

[0033] The input layer is used to receive the visible light image of the traction person after entering the interference enhancement stage;

[0034] The skeleton feature extraction layer is a preset skeleton key point extraction algorithm, which is used to receive the data output by the input layer and calibrate the skeleton key points of the towed person in the visible light image of the towed person. The skeleton key points include shoulders, elbows and legs;

[0035] The feature integration layer is used to create a sliding input window of a preset size to receive the input of the skeleton point feature extraction layer within a preset time period to form a skeleton point feature change sequence for external output;

[0036] The convolutional neural network layer is used to receive the skeleton point feature change sequence transmitted by the feature integration layer, perform data processing on the skeleton point feature change sequence, and then output it externally;

[0037] The output layer is used to obtain the output of the convolutional neural network layer, process the output of the convolutional neural network layer and output it externally;

[0038] Collect image sequences of multiple people pulling pets in different postures, calibrate whether their pulling postures are unbalanced, and obtain a training set for training the posture recognition model;

[0039] The posture recognition model framework is used as a network framework, image sequences of different postures of a person pulling a pet are used as input, and whether the pulling posture is unbalanced is used as a label, so as to train a posture recognition model.

[0040] Optionally, the preset target recognition model is trained by the following steps:

[0041] Collect multiple images of people pulling pets and pedestrians without pulling pets as a target recognition training set, and annotate each image in the target recognition training set to determine whether the person is pulling a pet.

[0042] The convolutional neural network is used as the network framework, the images of the target recognition training set are used as input, and whether the pet is being pulled is used as the label to train the target recognition model.

[0043] The technical solution provided by this application has the following advantages compared with the existing technology:

[0044] One of its beneficial effects is described as follows: the intelligent watering method provided by this application uses a camera to capture a sequence of images of pedestrians along a predetermined watering path during the watering process. This sequence of images is then analyzed using a preset target recognition model to determine whether the pedestrian is pulling a pet. When a pedestrian pulling a pet is detected, the pedestrian is marked as the pulling person. When the watering vehicle approaches the pulling person, pre-defined pre-sprinkling control actions are initiated, including deceleration, stopping watering, or suspending warning sounds. This minimizes the disruption of the watering operation to the pulled pet, thereby reducing the pet's uncertain behavior caused by the stimulation.

[0045] Therefore, the present application reduces the impact of the uncertainty caused by pets on the sprinkler operation and pedestrian safety by identifying pedestrians who are pulling pets and taking sprinkler control actions in advance to reduce the possibility of pet stress. Because the behavior of pets, especially dogs, is uncertain, they are easily stimulated by the external environment, such as the sound of sprinkler vehicles, sprinkler actions or warning signals, which can cause pets to be frightened and pull pedestrians through the leash. This may cause pedestrians to accidentally enter the sprinkler area or lose balance in the process of trying to control the pet, causing non-contact accidents such as falls. The existing technology is only based on the identification of pedestrian positions, and it assumes that pedestrian behavior is predictable and controllable, and cannot effectively deal with the behavioral uncertainty caused by pets. The present application fully considers the uncertainty of human behavior caused by the combination of pets and people pulling them. By reducing the stimulation of sprinkler operations on pets, it avoids pets pulling pedestrians into the sprinkler area after being frightened or causing other safety hazards, thereby improving the safety of sprinkler operations.

[0046] Therefore, the road sanitation intelligent sprinkler control method provided in this application can better avoid pedestrians on the road.

[0047] The second beneficial effect is that, because pet dogs have different body sizes, larger dogs are more likely to interfere with their owners, especially when stimulated by external factors, and are more likely to pull their owners with the leash, causing them to lose balance or accidentally enter the sprinkler area. The degree of interference is related to the size of both the pet dog and the owner. When the size of the pet dog approaches or exceeds that of the owner, the owner's control ability will be further reduced. This application considers the size factors of the pet dog and its owner, determines the size ratio, and then calculates the pre-risk value to obtain the distance at which the sprinkler control needs to be started in advance, so that the sprinkler vehicle can adjust the sprinkler control intensity according to the actual situation. For larger pet dogs, the sprinkler vehicle will start the sprinkler control action at a farther distance in advance, giving the pet a longer time window to adapt, thereby reducing the possibility of the pet engaging in uncertain behavior and reducing interference with the person pulling the dog, thereby preventing possible non-contact accidents. By comprehensively considering the size of the pet and the owner, this application improves the safety and reliability of the sprinkler operation.

[0048] The third beneficial effect is discussed below: To calculate the body size ratio, a sequence of images of the person pulling the pet is first acquired within a first time window. For each image within this first time window, the outlines of the person pulling the pet and their pet are extracted to calculate their respective outline areas. Subsequently, the present application uses a weighted average method to comprehensively calculate the body size ratios in each image based on a preset body size ratio calculation function to obtain a final body size ratio. The weight coefficient is determined by the ratio of the pet's outline area in each image to the average of the pet's outline areas across all images within the time window. This calculation method assigns higher weights to images with larger outline areas and focuses on image ratios where the pet appears larger. This effectively eliminates area measurement errors caused by the different angles and postures of the person pulling the pet, ensuring the stability and accuracy of the body size ratio calculation. In this way, the present application can more accurately assess the body size ratio between the person pulling the pet, thereby more appropriately determining the pre-risk value and, consequently, obtaining a more appropriate distance for initiating controlled watering.

[0049] The fourth beneficial effect is that pets, especially dogs, generally have different personalities and levels of training. If the watering range is determined solely based on the pet's size, the watering stop range may be too large, thereby reducing the efficiency of the watering operation. Therefore, when the sprinkler vehicle approaches the towing person and the pet, the present application further analyzes the towing person's visible light image sequence using a preset posture recognition model to obtain posture changes of the towing person, thereby determining the pet dog's personality, behavior pattern, and adaptability, and thus adjusting the subsequent watering stop range.

[0050] When the sprinkler vehicle enters the predetermined pre-sprinkler control action phase, it first enters the interference enhancement phase, which enhances the external interference stimulus emitted by the sprinkler, such as increasing the warning volume or frequency. At this time, the posture recognition model monitors the changes in the towing person's posture in real time to determine whether there are abnormal conditions such as imbalance caused by the pet's behavior. If the towing person's posture is stable and the pet's behavior is stable, the system exits the interference enhancement phase after a predetermined period of time and enters the interference reduction phase. Based on the duration of the interference enhancement phase, the pre-risk value is adjusted using the preset post-risk value calculation function to obtain the post-risk value. The longer the interference enhancement phase, the lower the uncertainty of the pet, the lower the post-risk value, and the shorter the distance the sprinkler vehicle needs to continue to control the sprinkler after passing the towing person.

[0051] Conversely, if the driver's posture is detected to be unstable, indicating unstable pet behavior, the system immediately exits the interference enhancement phase and enters the interference reduction phase. The shorter the duration of the interference enhancement phase, the greater the uncertainty of the pet, and the higher the post-risk value, which increases the subsequent controlled watering distance. Through this dynamic adjustment, the sprinkler vehicle can dynamically determine the appropriate stopping range based on the pet's personality and behavior patterns, thereby maximizing watering efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flow chart of the intelligent watering control method for road sanitation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The technical solution in this application will be described below with reference to the accompanying drawings.

[0054] The following description sets forth many specific details to facilitate a thorough understanding of the present application. However, the present application may also be implemented in other ways than those described herein. It is apparent that the embodiments described in the specification are only some of the embodiments of the present application, not all of them. It should be noted that the embodiments of the present application and the features therein may be combined with each other unless there is a conflict.

[0055] Reference Figure 1 , the present application provides a road sanitation intelligent sprinkler control method, comprising the following steps:

[0056] S101: Acquire an image sequence of pedestrians on a predetermined watering path through a camera.

[0057] Specifically, the camera takes photos of the road next to the watering path that is to be traveled at intervals of a preset time, thereby obtaining an image sequence of pedestrians on the road along the predetermined watering path.

[0058] S102: Based on the image sequence of pedestrians on the road, a preset target recognition model is used to determine whether the pedestrians on the road are pulling a pet.

[0059] Specifically, the preset target recognition model is trained through the following steps:

[0060] Collect multiple images of people pulling pets and pedestrians without pulling pets as a target recognition training set, and annotate each image in the target recognition training set to determine whether the person is pulling a pet.

[0061] The convolutional neural network is used as the network framework, the images of the target recognition training set are used as input, and whether the pet is being pulled is used as the label to train the target recognition model.

[0062] Specifically, the target recognition model is used to perform target recognition on each newly acquired image in the image sequence of pedestrians on the road, so as to distinguish and identify whether a pedestrian is pulling a pet.

[0063] S103: If there is a pedestrian on the road who is pulling the pet, the pedestrian pulling the pet is marked as the pulling person, and the distance to the pulling person to start controlling the watering in advance is calculated.

[0064] Specifically, calculate the distance to the towing person to start watering in advance:

[0065] Obtaining a size ratio between the towing person and the towed pet, and calculating a pre-risk value based on the size ratio using a preset pre-risk value calculation function, wherein the pre-risk value calculation function is configured such that the closer the size of the towed pet is to the towing person, the higher the pre-risk value;

[0066] According to the pre-risk value, the distance to the towing person that needs to be controlled for starting watering in advance is calculated by a preset control watering distance calculation function. The setting of the control watering distance calculation function is such that the larger the value of the pre-risk value, the larger the distance to be controlled for starting watering in advance.

[0067] Specifically, in the embodiment of the present application, the pre-risk value calculation function is:

[0068]

[0069] in, is the pre-risk value, It is a first empirical parameter preset artificially, and B is the body size ratio of the person pulling the pet to the person being pulled.

[0070] The control watering distance calculation function is:

[0071]

[0072] in, To control the watering distance, It is the second artificially preset empirical parameter. is the risk value, which is used to bring in the pre-risk value or post-risk value. Based on the control distance.

[0073] It should be noted that in other embodiments, those skilled in the art should realize that based on the design concept of the pre-risk value and the control watering distance calculation function, the specific forms of the pre-risk value calculation function and the control watering distance calculation function can have more than one variant, and their variant forms can also achieve the same technical effect. Therefore, the scope of protection requested by this application should not be limited to the specific calculation formula proposed in the embodiments of this application.

[0074] Specifically, the body size ratio of the pulling person and the pulled pet is calculated by the following steps:

[0075] When a pulling person is detected, an image sequence of the pulling person in a first time window is acquired;

[0076] For each photo in the first time window, the outlines of the person pulling the pet are extracted.

[0077] After the target recognition model in this application determines the area where the pulling person and the pulled pet are located, the contours of the pulling person and the pulled pet in the area are extracted using the Canny edge detection algorithm to obtain the contours of the pulling person and the pulled pet.

[0078] In other embodiments, based on further improvement in accuracy, the instance segmentation model Mask R-CNN can be used, but the training of this model requires a large amount of training data. The Mask R-CNN model construction and its training process belong to the prior art, and its training process and model construction are not described in detail here. If this technology is adopted, the target recognition model can be replaced with the Mask R-CNN instance segmentation model, so as to achieve the technical effects of target recognition and contour segmentation at the same time.

[0079] The outline areas of the towing person and the pet being towed in each photo are calculated, and the body ratio of the towing person and the pet being towed is obtained using a preset body ratio calculation function.

[0080] There are many existing technologies that can be used to calculate the contour area. In the embodiment of the present application, a pixel counting method is used to obtain the area of ​​the contour, which will not be described in detail here.

[0081] The preset body shape ratio calculation function is:

[0082]

[0083] Where I is the total number of photos in the first time window, i is the i-th photo in the first time window, A(p,i) is the outline area of ​​the pulled pet in the i-th photo, and A(m,i) is the outline area of ​​the pulling person in the i-th photo;

[0084]

[0085] in, It is the average of the contour areas of the pulled pet in all photos within the entire first time window.

[0086] S104: When approaching the towing person, the predetermined pre-sprinkling control action is started in advance to reduce the interference of the towed pet on its towing person.

[0087] Specifically, when the sprinkler truck is at a distance from the towing person at which the sprinkler truck needs to start controlling the sprinkler in advance, the sprinkler truck performs a predetermined pre-sprinkling control action.

[0088] The distance between the sprinkler truck and the towing person can be obtained by using a distance sensor on the sprinkler truck or binocular vision to measure the distance, but these are existing technologies in this field and are means that technicians in this field can choose according to actual conditions, so they will not be described in detail here.

[0089] The predetermined pre-sprinkler control action includes an interference enhancement stage and an interference reduction stage. When the predetermined pre-sprinkler control action begins to be executed, the interference enhancement stage of a predetermined duration is first entered. In the interference enhancement stage, the interference stimulus emitted to the outside during sprinkling is enhanced. After exiting the interference enhancement stage, the interference reduction stage is entered to reduce the interference stimulus emitted to the outside during sprinkling until the position of the tractor is reached.

[0090] Specifically, the actions performed in the interference enhancement stage are: increasing the water pressure during watering, increasing the warning volume, and other behaviors to enhance the interference stimulation emitted by the watering to the outside.

[0091] Specifically, the actions performed in the interference reduction stage are: reducing the speed of the sprinkler truck, stopping watering, turning off the warning sound, and other actions to reduce the interference stimulation caused by the sprinkler to the outside world.

[0092] S105: Calculate the distance required to control the watering after the towing person passes by based on the visible light image sequence of the towing person and the pre-set risk value when the pre-set pre-watering control action is executed:

[0093] During the interference enhancement phase, based on the visible light image sequence of the pulling person when the predetermined pre-sprinkling control action is executed, the posture change of the pulling person is obtained through a preset posture recognition model to determine whether to exit the interference enhancement phase;

[0094] According to the length of the interference enhancement phase, the pre-risk value is changed by a preset post-risk value calculation function to obtain a post-risk value, so that the longer the interference enhancement phase is, the lower the post-risk value obtained;

[0095] According to the post-risk value, the distance at which the watering needs to be controlled after the person is pulled is calculated using a preset watering distance calculation function.

[0096] The post-risk value calculation function is:

[0097]

[0098] in, is the post-risk value, For the scheduled duration, The actual duration of the interference enhancement phase, It is an artificially set post-risk value base.

[0099] Based on the design concept of the post-risk value calculation function, the specific form of the post-risk value calculation function can have more than one variant, and its variant form can also achieve the same technical effect. Therefore, the scope of protection requested by this application should not be limited to the specific calculation formula proposed in the embodiment of this application.

[0100] Specifically, the preset posture recognition model is trained through the following steps:

[0101] Constructing the posture recognition model framework, which includes an input layer, a skeleton point feature extraction layer, a feature integration layer, a convolutional neural network layer and an output layer;

[0102] The input layer is used to receive the visible light image of the traction person after entering the interference enhancement stage;

[0103] The skeleton feature extraction layer is a preset skeleton key point extraction algorithm, which is used to receive the data output by the input layer and calibrate the skeleton key points of the towed person in the visible light image of the towed person. The skeleton key points include shoulders, elbows and legs;

[0104] Specifically, the skeleton key point extraction algorithm is the OpenPose algorithm or the AlphaPose algorithm. In other embodiments, other posture estimation algorithms can also be used to extract skeleton key points.

[0105] However, it should be noted that even if the embodiments of this application do not improve the algorithm itself, they do suggest the need for technical improvements at least at the shoulder, elbow, and leg key points. This is because when a person pulls a pet, the angle of the pulling hand and the extent of the body's forward and backward lean are strongly correlated with whether the person's posture is unbalanced.

[0106] The feature integration layer is used to create a sliding input window of a preset size to receive the input of the skeleton point feature extraction layer within a preset time period to form a skeleton point feature change sequence for external output;

[0107] This preset size is a manually set value, usually set to 3-6.

[0108] The convolutional neural network layer is used to receive the skeleton point feature change sequence transmitted by the feature integration layer, perform data processing on the skeleton point feature change sequence, and then output it externally;

[0109] The output layer is used to obtain the output of the convolutional neural network layer, process the output of the convolutional neural network layer and output it externally;

[0110] Collect image sequences of multiple people pulling pets in different postures, calibrate whether their pulling postures are unbalanced, and obtain a training set for training the posture recognition model;

[0111] It should be noted that the number of images in the image sequence of different postures is preferably consistent with the preset size mentioned above.

[0112] The posture recognition model framework is used as a network framework, image sequences of different postures of a person pulling a pet are used as input, and whether the pulling posture is unbalanced is used as a label, so as to train a posture recognition model.

[0113] When the traction posture is determined to be unbalanced, a signal is sent to end the interference enhancement phase, so that the watering behavior immediately enters the interference reduction phase, and then the post-risk value is obtained through the post-risk value calculation function.

[0114] Substitute the obtained post-risk value into the control watering distance calculation function to obtain the distance that needs to be controlled for watering after the person is pulled.

[0115] S106: Based on the obtained distance for controlling watering after the person has been pulled, the watering control action is continued within the distance after the person has been pulled.

[0116] Specifically, the interference reduction stage is maintained until the sprinkler truck moves to a distance beyond which the sprinkler truck needs to control the sprinkler after passing the towing person, so that the sprinkler truck continues the sprinkler operation.

[0117] The technical solution provided by the embodiments of the present application has the following advantages compared with the prior art:

[0118] One of its beneficial effects is described as follows: the intelligent watering method provided by this application uses a camera to capture a sequence of images of pedestrians along a predetermined watering path during the watering process. This sequence of images is then analyzed using a preset target recognition model to determine whether the pedestrian is pulling a pet. When a pedestrian pulling a pet is detected, the pedestrian is marked as the pulling person. When the watering vehicle approaches the pulling person, pre-defined pre-sprinkling control actions are initiated, including deceleration, stopping watering, or suspending warning sounds. This minimizes the disruption of the watering operation to the pulled pet, thereby reducing the pet's uncertain behavior caused by the stimulation.

[0119] Therefore, the present application reduces the impact of the uncertainty caused by pets on the sprinkler operation and pedestrian safety by identifying pedestrians who are pulling pets and taking sprinkler control actions in advance to reduce the possibility of pet stress. Because the behavior of pets, especially dogs, is uncertain, they are easily stimulated by the external environment, such as the sound of sprinkler vehicles, sprinkler actions or warning signals, which can cause pets to be frightened and pull pedestrians through the leash. This may cause pedestrians to accidentally enter the sprinkler area or lose balance in the process of trying to control the pet, causing non-contact accidents such as falls. The existing technology is only based on the identification of pedestrian positions, and it assumes that pedestrian behavior is predictable and controllable, and cannot effectively deal with the behavioral uncertainty caused by pets. The present application fully considers the uncertainty of human behavior caused by the combination of pets and people pulling them. By reducing the stimulation of sprinkler operations on pets, it avoids pets pulling pedestrians into the sprinkler area after being frightened or causing other safety hazards, thereby improving the safety of sprinkler operations.

[0120] Therefore, the road sanitation intelligent sprinkler control method provided in this application can better avoid pedestrians on the road.

[0121] The second beneficial effect is explained as follows: since pet dogs come in different sizes, larger dogs are more likely to interfere with their owners, especially when stimulated by external factors. They are more likely to pull their owners with the leash, causing them to lose balance or accidentally enter the sprinkler area. The degree of interference is related to the size of both the pet dog and the owner. When the pet dog's size approaches or exceeds that of the owner, the owner's control ability will be further reduced. This application considers the size factors of the pet dog and its owner, determines the size ratio, and then calculates the pre-risk value to obtain the distance at which the sprinkler control needs to be started in advance, so that the sprinkler vehicle can adjust the range of the sprinkler control according to the actual situation. For larger pet dogs, the sprinkler vehicle will start the sprinkler control action at a farther distance in advance, giving the pet a longer time window to adapt, thereby reducing the possibility of the pet engaging in uncertain behavior and reducing interference with the person pulling the dog, thereby preventing possible non-contact accidents. By comprehensively considering the size of the pet and the owner, this application improves the safety and reliability of the sprinkler operation.

[0122] The third beneficial effect is discussed below: To calculate the body size ratio, a sequence of images of the person pulling the pet is first acquired within a first time window. For each image within this first time window, the outlines of the person pulling the pet and their pet are extracted to calculate their respective outline areas. Subsequently, the present application uses a weighted average method to comprehensively calculate the body size ratios in each image based on a preset body size ratio calculation function to obtain a final body size ratio. The weight coefficient is determined by the ratio of the pet's outline area in each image to the average of the pet's outline areas across all images within the time window. This calculation method assigns higher weights to images with larger outline areas and focuses on image ratios where the pet appears larger. This effectively eliminates area measurement errors caused by the different angles and postures of the person pulling the pet, ensuring the stability and accuracy of the body size ratio calculation. In this way, the present application can more accurately assess the body size ratio between the person pulling the pet, thereby more appropriately determining the pre-risk value and, consequently, obtaining a more appropriate distance for initiating controlled watering.

[0123] The fourth beneficial effect is that pets, especially dogs, generally have different personalities and training levels. If the watering distance is determined solely based on the pet's size, the watering stop range may be too large, thereby reducing the efficiency of the watering operation. Therefore, when the watering vehicle approaches the towing person and the pet, the present application further analyzes the towing person's visible light image sequence using a preset posture recognition model to obtain posture changes of the towing person, thereby determining the pet dog's personality, behavior pattern, and adaptability, and thus adjusting the subsequent watering stop range.

[0124] When the sprinkler vehicle enters the predetermined pre-sprinkler control action phase, it first enters the interference enhancement phase, which enhances the external interference stimulus emitted by the sprinkler, such as increasing the warning volume or frequency. At this time, the posture recognition model monitors the changes in the towing person's posture in real time to determine whether there are any abnormalities such as imbalance caused by the pet's behavior. If the towing person's posture is stable and the pet's behavior is stable, the towing person will exit the interference enhancement phase after a predetermined period of time and enter the interference reduction phase. According to the duration of the interference enhancement phase, the pre-risk value is adjusted using the preset post-risk value calculation function to obtain the post-risk value. The longer the interference enhancement phase, the lower the uncertainty of the pet, the lower the post-risk value, and the shorter the distance the sprinkler vehicle needs to stop sprinkling after passing the towing person.

[0125] Conversely, if the driver's posture is detected to be unstable, indicating unstable pet behavior, the system immediately exits the interference enhancement phase and enters the interference reduction phase. The shorter the duration of the interference enhancement phase, the greater the uncertainty of the pet, and the higher the post-risk value, which increases the subsequent controlled watering distance. Through this dynamic adjustment, the sprinkler vehicle can dynamically determine the appropriate stopping range based on the pet's personality and behavior patterns, thereby maximizing watering efficiency.

[0126] It should be noted that, in this document, relational terms such as "first" and "second" are used solely to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. Furthermore, the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article, or device comprising the element. Furthermore, in the description of the embodiments of this application, unless otherwise specified, " / " represents or. For example, A / B can represent either A or B. "And / or" herein is merely a description of an associative relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, in the description of the embodiments of the present application, “plurality” refers to two or more than two.

[0127] The foregoing description is intended only to provide specific embodiments of the present application, which will enable those skilled in the art to understand and implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments described herein, but is intended to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A road sanitation intelligent watering control method, characterized in that: The following steps are involved: Acquire an image sequence of pedestrians on a predetermined watering path through a camera; Based on the image sequence of pedestrians on the road, a preset target recognition model is used to judge whether the pedestrians on the road are pulling the pet; If there is a pedestrian pulling a pet, the pedestrian pulling the pet is marked as the puller, and the predetermined pre-sprinkling control action is executed in advance when approaching the puller, so as to reduce the interference of the pulled pet on the puller; The following steps are also included: Calculate the distance to the tractor to start watering in advance: Obtaining a body size ratio between the towing person and the towed pet, and calculating a pre-risk value according to the body size ratio by using a preset pre-risk value calculation function, wherein the pre-risk value calculation function is set so that the closer the body size of the towed pet is to the body size of the towing person, the higher the pre-risk value; According to the pre-risk value, the distance to the tractor that needs to be controlled for watering in advance is calculated by a preset control watering distance calculation function, and the control watering distance calculation function is set so that the larger the value of the pre-risk value is, the larger the distance that needs to be controlled for watering in advance is; The predetermined pre-sprinkling control action is started at the distance ahead of the towing person at which the pre-sprinkling control is required; The predetermined pre-sprinkler control action includes an interference enhancement phase and an interference reduction phase. When the predetermined pre-sprinkler control action is started, the interference enhancement phase of a predetermined duration is first entered. In the interference enhancement phase, the interference stimulus to the outside during the sprinkling is enhanced. After exiting the interference enhancement phase, the interference reduction phase is entered to reduce the interference stimulus to the outside during the sprinkling until the position of the tractor is reached. According to the visible light image sequence of the tractor when executing the predetermined pre-sprinkling control action and the pre-risk value, the distance to be controlled for sprinkling after the tractor is calculated: In the interference enhancement stage, according to the visible light image sequence of the tractor when executing the predetermined pre-sprinkling control action, the posture change of the tractor is obtained through a preset posture recognition model to determine whether to exit the interference enhancement stage at present; According to the length of the interference enhancement phase, the pre-risk value is changed by a preset post-risk value calculation function to obtain a post-risk value, so that the longer the interference enhancement phase is, the lower the post-risk value obtained is; According to the post-risk value, the distance at which watering needs to be controlled after the person is pulled is calculated by a preset watering control distance calculation function; The interference reduction stage is maintained until the distance after the tractor leaves the tractor and the water sprinkling needs to be controlled, and then the interference reduction stage is exited.

2. The road sanitation intelligent sprinkler control method according to claim 1 is characterized in that: The body size ratio of the pulling person and the pulled pet is calculated by the following steps: When the pulling person is detected, an image sequence of the pulling person in a first time window is acquired; For each photo in the first time window, extract the outlines of the person pulling the pet; Calculate the area of ​​the outline of the towing person and the towed pet in each photo, and obtain the body size ratio of the towing person and the towed pet by using a preset body size ratio calculation function; The preset body shape ratio calculation function is: Where I is the total number of photos in the first time window, i is the i-th photo in the first time window, A(p,i) is the outline area of ​​the pulled pet in the i-th photo, and A(m,i) is the outline area of ​​the pulling person in the i-th photo; in, It is the average of the contour areas of the pulled pet in all photos within the entire first time window.

3. The road sanitation intelligent sprinkler control method according to claim 1 is characterized in that: The preset posture recognition model is trained by the following steps: Constructing the posture recognition model framework, the posture recognition model framework includes an input layer, a skeleton point feature extraction layer, a feature integration layer, a convolutional neural network layer and an output layer; An input layer, for receiving the visible light image of the traction person after entering the interference enhancement stage; The skeleton point feature extraction layer is a preset skeleton key point extraction algorithm, which is used to receive the data output by the input layer and calibrate the skeleton key points of the tractor in the visible light image of the tractor, and the skeleton key points include shoulders, elbows and legs; The feature integration layer is used to create a sliding input window of a preset size, which is used to receive the input of the bone point feature extraction layer within a preset size time to form a bone point feature change sequence for external output; The convolutional neural network layer is used to receive the skeleton point feature change sequence transmitted by the feature integration layer, perform data processing on the skeleton point feature change sequence and then output it externally; The output layer is used to obtain the output of the convolutional neural network layer, process the output of the convolutional neural network layer and output it externally; Collect image sequences of multiple people pulling pets in different postures, calibrate whether their pulling postures are unbalanced, and obtain a training set for training a posture recognition model; The posture recognition model framework is used as a network framework, image sequences of different postures of a person pulling a pet are used as input, and whether the pulling posture is unbalanced is used as a label, so as to train a posture recognition model.

4. The road sanitation intelligent sprinkler control method according to claim 1 is characterized in that: The preset target recognition model is trained by the following steps: Collect multiple images of people towing pets and pedestrians on the road without towing pets as a target recognition training set, and annotate whether the person in each image in the target recognition training set is towing a pet; The convolutional neural network is used as the network framework, the pictures of the target recognition training set are used as input, and whether the pet is being pulled is used as the label, so as to train and obtain the target recognition model.

Images