Control method for road cleaning vehicle, road cleaning vehicle and processor

Abstract

The invention discloses a control method for a road cleaning vehicle, the road cleaning vehicle and a processor, and belongs to the technical field of road cleaning vehicles. The method comprises the steps that in the operation process of the road cleaning vehicle, an environment image of the surrounding environment of the road cleaning vehicle is acquired; the environment image is divided into a plurality of areas, and each area is provided with different water outlet strategies for controlling the water spraying device; detecting whether target objects exist in the plurality of areas, wherein the target objects comprise pedestrians; and when it is detected that the target object exists, the area, which has the target object and is closest to the road cleaning vehicle, in the multiple areas serves as the target area, and the water outlet strategy of the water spraying device matched with the target area is executed. The spraying distance of the water spraying device can be automatically controlled, intelligent control over the water spraying device is achieved, a driver does not need to distract attention to observe the road condition, and the operation safety can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of road cleaning vehicles, and in particular to a control method for a road cleaning vehicle, a road cleaning vehicle and a processor. Background Art

[0002] With the acceleration of urbanization, the use of road cleaning vehicles has become more and more common in order to ensure the cleanliness of urban roads. However, due to the large range of hedging operations of road cleaning vehicles, it is easy for sewage to splash onto pedestrians or motor vehicles that cannot avoid it during operation, thus causing disputes. In response to this, the driver of the cleaning vehicle will manually open and close the hedging switch by actively observing the conditions on both sides of the road. However, due to the complex operating road conditions, the driver needs to pay attention to the conditions on both sides of the road at all times, which distracts the driver's attention and easily causes traffic accidents. Therefore, the existing technology has the problem of low safety. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a control method for a road cleaning vehicle, a road cleaning vehicle, a processor, and a machine-readable storage medium, so as to solve the problem of low security in the prior art.

[0004] In order to achieve the above-mentioned purpose, a first aspect of an embodiment of the present application provides a control method for a road cleaning vehicle, wherein the road cleaning vehicle includes a water spraying device, and the control method includes:

[0005] During the operation of the road cleaning vehicle, an environmental image of the surrounding environment of the road cleaning vehicle is obtained;

[0006] The environment image is divided into multiple areas, and different water discharge strategies for controlling the water spray device are configured for the multiple areas, wherein the water discharge strategies include controlling the water spray device to stop spraying water or adjusting the spray distance of the water spray device;

[0007] Detect whether there are target objects in multiple areas, including pedestrians;

[0008] When the presence of a target object is detected, an area among the multiple areas where the target object exists and which is closest to the road cleaning vehicle is taken as the target area, and a water discharge strategy of the water spraying device matching the target area is executed.

[0009] In an embodiment of the present application, dividing the environmental image into multiple areas includes: determining a geographic division threshold based on the maximum spray distance of the water spray device; converting the image coordinates of each point in the environmental image into geographic coordinates, and determining the lateral distance between each point in the image and the water spray device based on the geographic coordinates, the lateral distance being the distance perpendicular to the body direction of the road cleaning vehicle; dividing the environmental image into multiple areas based on the lateral distance and the geographic division threshold.

[0010] In an embodiment of the present application, the geographic division threshold includes a first geographic division threshold, multiple areas include the first area, the lateral distance between any point in the first area and the road cleaning vehicle is less than or equal to the first geographic division threshold, and the water output strategy matched by the first area is to control the water spraying device to stop spraying water.

[0011] In an embodiment of the present application, the geographic division threshold includes a first geographic division threshold and a second geographic division threshold, the second geographic division threshold is greater than the first geographic division threshold, the multiple areas include the second area, the lateral distance between any point in the second area and the road cleaning vehicle is greater than the first geographic division threshold and less than the second geographic division threshold, and the water output strategy matched by the second area is to adjust the spray distance of the water spray device to a preset spray distance.

[0012] In an embodiment of the present application, the environmental image includes a first environmental image and a second environmental image, the first environmental image and the second environmental image respectively include images of the road environment on the first side and the second side of the body of the road cleaning vehicle, the water spraying device includes a first water spraying device and a second water spraying device respectively arranged on the first side and the second side, and the control method also includes: controlling the first water spraying device according to the first environmental image; and controlling the second water spraying device according to the second environmental image.

[0013] In an embodiment of the present application, a monocular camera is provided on the road cleaning vehicle. In a direction perpendicular to the chassis of the road cleaning vehicle, the monocular camera is higher than the water spraying device, and the projection of the monocular camera coincides with the projection of the water spraying device. The monocular camera is used to collect environmental images of the surrounding environment of the road cleaning vehicle and to measure the distance to the target object in the environmental image.

[0014] A second aspect of an embodiment of the present application provides a processor configured to execute the control method for a road cleaning vehicle according to the above.

[0015] A third aspect of an embodiment of the present application provides a road cleaning vehicle, which includes: a water spraying device; and the above-mentioned processor.

[0016] In an embodiment of the present application, the road cleaning vehicle also includes: a monocular camera that communicates with the processor, wherein the monocular camera is higher than the water spraying device in a direction perpendicular to the chassis of the road cleaning vehicle, and the monocular camera overlaps with the projection of the water spraying device, and is used to collect an environmental image of the surrounding environment of the road cleaning vehicle and measure the distance to the target object in the environmental image.

[0017] A fourth aspect of an embodiment of the present application provides a machine-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the above-mentioned control method for a road cleaning vehicle is implemented.

[0018] In the above technical solution, the road cleaning vehicle includes a water spraying device. During the operation of the road cleaning vehicle, an environmental image of the surrounding environment of the road cleaning vehicle is obtained, and then the environmental image is divided into multiple areas, and different water discharge strategies for controlling the water spraying device are configured for the multiple areas respectively. The water discharge strategy includes controlling the water spraying device to stop spraying water or adjusting the spraying distance of the water spraying device. Furthermore, it is detected whether there are target objects in multiple areas, and the target objects include pedestrians. When the target objects are detected, the area in the multiple areas where the target objects exist and is closest to the road cleaning vehicle is taken as the target area, and the water discharge strategy of the water spraying device matching the target area is executed. The present application can divide the environmental image into multiple areas that match the corresponding water discharge strategies. When the area where the target object is located is detected, the spraying distance of the water spraying device is automatically controlled by the corresponding water discharge strategy, thereby realizing intelligent control of the water spraying device. There is no need for the driver to distract his attention to observe the road conditions, which is conducive to improving operation safety.

[0019] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0021] Figure 1 A schematic flow chart of a control method for a road cleaning vehicle provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of area division provided for a specific embodiment of the present application;

[0023] Figure 3 A schematic diagram of the principle of monocular ranging using a camera provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0025] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0026] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0027] Figure 1 The following is a flow chart of a control method for a road cleaning vehicle provided in an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a control method for a road cleaning vehicle, the road cleaning vehicle includes a water spraying device, and the control method is applied to a processor as an example for description. The control method may include the following steps:

[0028] Step S101 : acquiring an environmental image of the surrounding environment of the road cleaning vehicle during the operation of the road cleaning vehicle.

[0029] Step S102, dividing the environment image into multiple areas, and configuring different water discharge strategies for controlling the water spray device for each of the multiple areas, wherein the water discharge strategies include controlling the water spray device to stop spraying water or adjusting the spray distance of the water spray device.

[0030] Step S103: Detect whether there are target objects in multiple areas, where the target objects include pedestrians.

[0031] Step S104: when it is detected that there is a target object, an area in the multiple areas where the target object exists and which is closest to the road cleaning vehicle is taken as a target area, and a water discharge strategy of a water spraying device matching the target area is executed.

[0032] In the embodiments of the present application, the road cleaning vehicle includes a cleaning and washing vehicle, a road cleaning vehicle or a road watering vehicle. At present, the road cleaning vehicle generally uses a centrifugal watering pump to extract clean water from a water tank, which is pressurized by the centrifugal pump to form a pressure water source, and is transported to a water spraying device such as a duckbill nozzle, a hedging cone nozzle and a watering fan nozzle through a pipeline to achieve the purpose of cleaning the road. Hedging operation is the main operation mode of the cleaning vehicle, and the purpose is to wash the dirt and garbage in the middle of the road to the lanes on both sides of the road. In this way, the road sweeper only needs to clean the lanes on both sides in the future, thereby improving the operation efficiency of the road sweeper. However, due to the large hedging operation range of the road cleaning and washing vehicle, sewage is easy to splash onto pedestrians or non-motorized vehicles, thereby causing flying. In this regard, the driver is often required to pay attention to the situation on both sides at all times and manually control the opening and closing of the water spraying device, which distracts the driver's attention and easily causes traffic accidents. In this regard, the embodiment of the present application provides a control method for a road cleaning vehicle to achieve automatic control of the water spraying device, thereby improving safety.

[0033] Specifically, during the operation of the road cleaning vehicle, the processor can obtain the environmental image of the surrounding environment of the road cleaning vehicle in real time. The environmental image can be collected by the image acquisition device installed around the body of the road cleaning vehicle and sent to the processor, and the shooting range of the image acquisition device is greater than the maximum range of the water spray of the road cleaning vehicle. Further, in order to realize the automatic control of the water spraying device, the embodiment of the present application can divide the environmental image into multiple areas in advance based on the risk of being splashed by sewage, and configure different water outlet strategies for controlling the water spraying device for different areas according to the risk. It can be understood that the environmental image includes multiple areas, and the risk of the target object being splashed by sewage when it is in different areas is different. Among them, the target objects mainly include pedestrians. Since some non-motor vehicles are also in an unobstructed state during driving, there is also a risk of being splashed by sewage. Therefore, the target object can also include the driver of the non-motor vehicle.

[0034] Furthermore, the processor can detect whether there is a target object in the environment image through a target detection algorithm, and determine whether the target object is in any of the above multiple areas according to the position of the target object in the environment image. In one example, when the target object is not detected in the environment image or the target object is not in any of the above multiple areas, it means that there is no risk of splashing sewage onto pedestrians or non-motor vehicles at this time, and the processor can keep the current control parameters unchanged and continue to control the operation of the water spraying device.

[0035] In another example, when a target object is detected in the above multiple areas in the environment image, considering that the target object detected in the image may exist across areas, the processor may take the area in the multiple areas where the target object exists and is closest to the road cleaning vehicle as the target area, and then execute the water discharge strategy of the water spraying device configured in the target area to prevent sewage from splashing onto the target object. The water discharge strategy includes controlling the water spraying device to stop spraying water or adjusting the spraying distance of the water spraying device.

[0036] The traditional method only includes two control strategies: turning on and off the water spray device. When the risk of the target object being splashed is small, directly turning off the water spray device will shorten the operation time of the road cleaning vehicle and affect the operation efficiency. However, the embodiment of the present application configures different water output strategies for different areas, and then controls the operation of the water spray device according to the water output strategy of the target area where the target object is located, which is conducive to achieving targeted control. Compared with the traditional control method, the control method used in the embodiment of the present application is more flexible and is conducive to ensuring the operation time of the road cleaning vehicle.

[0037] In the above technical solution, the road cleaning vehicle includes a water spraying device. During the operation of the road cleaning vehicle, an environmental image of the surrounding environment of the road cleaning vehicle is obtained, and then the environmental image is divided into multiple areas, and different water discharge strategies for controlling the water spraying device are configured for the multiple areas respectively. The water discharge strategy includes controlling the water spraying device to stop spraying water or adjusting the spraying distance of the water spraying device. Furthermore, it is detected whether there are target objects in multiple areas, and the target objects include pedestrians. When the target objects are detected, the area in the multiple areas where the target objects exist and is closest to the road cleaning vehicle is taken as the target area, and the water discharge strategy of the water spraying device matching the target area is executed. The present application can divide the environmental image into multiple areas that match the corresponding water discharge strategies. When the area where the target object is located is detected, the spraying distance of the water spraying device is automatically controlled by the corresponding water discharge strategy, thereby realizing intelligent control of the water spraying device. There is no need for the driver to distract his attention to observe the road conditions, which is conducive to improving operation safety.

[0038] The technical solution of the present application directly divides the area in the image, and then detects whether there are pedestrians in the area. Since there is no need to obtain the precise position of pedestrians, it is only necessary to determine whether there are pedestrians in the calibration area. Therefore, a low-precision distance detection device can be used to implement the anti-misspray control of the water spray device, which is beneficial to reduce the system cost. In addition, the embodiment of the present application does not need to collect the distance between all pedestrians and vehicles, and only considers pedestrians in the calibration area, thereby reducing the consumption of computer resources caused by calculating the distance between all pedestrians and vehicles, which is beneficial to reducing system energy consumption.

[0039] In an embodiment of the present application, dividing the environmental image into multiple areas includes: determining a geographic division threshold based on the maximum spray distance of the water spray device; converting the image coordinates of each point in the environmental image into geographic coordinates, and determining the lateral distance between each point in the image and the water spray device based on the geographic coordinates, the lateral distance being the distance perpendicular to the body direction of the road cleaning vehicle; dividing the environmental image into multiple areas based on the lateral distance and the geographic division threshold.

[0040] It can be understood that according to the maximum spraying distance of the water spraying device, combined with operational experience or test data, the risk of being splashed by sewage at different distances can be determined, and then the geographical division threshold can be determined. The geographical division threshold refers to the critical value of the lateral distance corresponding to the different risk sizes of being splashed by sewage in the direction perpendicular to the body of the road cleaning vehicle. It can be understood that the geographical division threshold can include multiple thresholds of different sizes. Each point in the environmental image corresponds to a certain geographical location in the actual scene. Based on the corresponding geographical location, the actual distance between any point in the environmental image and the water spraying device of the road cleaning vehicle can be determined, including the lateral distance. Furthermore, based on the geographical division threshold, the environmental image can be divided into multiple areas according to the lateral distances corresponding to each point in the environmental image. Provide data support for subsequent judgments.

[0041] In one example, the actual distance between any point in the environmental image and the water spraying device of the road cleaning vehicle also includes the longitudinal distance, which is the distance parallel to the body direction of the road cleaning vehicle. Considering that the risk of the target object being splashed by sewage is different when it is at different longitudinal distances, the processor can divide the environmental image into regions based on the geographical division threshold according to the lateral distance and longitudinal distance corresponding to each point in the environmental image to obtain multiple regions. This is conducive to improving the subsequent control accuracy.

[0042] In an embodiment of the present application, the geographic division threshold includes a first geographic division threshold, multiple areas include the first area, the lateral distance between any point in the first area and the road cleaning vehicle is less than or equal to the first geographic division threshold, and the water output strategy matched by the first area is to control the water spraying device to stop spraying water.

[0043] Specifically, the first geographic division threshold is a critical value for dividing a high-risk splashing area, and the first area refers to a high-risk splashing area, that is, objects in this area are at high risk of being splashed by sewage. It can be understood that the first area in the environmental image can be determined according to the first geographic division threshold. In one example, the first area is an area formed by a plurality of points in the environmental image whose corresponding lateral distances are less than or equal to the first geographic division threshold, that is, the lateral distance between any point in the first area and the road cleaning vehicle is less than or equal to the first geographic division threshold.

[0044] In another example, the first area can be divided based on the longitudinal distance, and the first geographic division threshold can include a first lateral distance threshold and a first longitudinal distance threshold. The first area is an area formed by multiple points in the environmental image whose corresponding lateral distance is less than or equal to the first lateral distance threshold, and whose longitudinal distance is less than or equal to the first longitudinal distance threshold, that is, the lateral distance between any point in the first area and the road cleaning vehicle is less than or equal to the first lateral distance threshold, and the longitudinal distance is less than or equal to the first longitudinal distance threshold.

[0045] Furthermore, since the first area is a high-risk area for splashing, in order to prevent splashing on pedestrians, the water outlet strategy matched in the first area is to control the water spraying device to stop spraying water. In other words, when it is detected that the target object is in the first area, it means that the target object will definitely be splashed by sewage, and the processor can immediately control the water spraying device to stop spraying water. In this way, it can effectively prevent sewage from continuously splashing on the target object, or water sprayed by the water spraying device from spraying on the target object, thereby ensuring the safety of the target object.

[0046] In an embodiment of the present application, the geographic division threshold includes a first geographic division threshold and a second geographic division threshold, the second geographic division threshold is greater than the first geographic division threshold, the multiple areas include the second area, the lateral distance between any point in the second area and the road cleaning vehicle is greater than the first geographic division threshold and less than the second geographic division threshold, and the water output strategy matched by the second area is to adjust the spray distance of the water spray device to a preset spray distance.

[0047] Specifically, the second geographic division threshold is a critical value for dividing the splashing medium risk area, and the second area refers to the splashing medium risk area, that is, objects in this area may be splashed by sewage. It can be understood that the second area in the environmental image can be determined according to the first geographic division threshold. In one example, the second area is an area formed by multiple points in the environmental image whose corresponding lateral distances are greater than the first geographic division threshold and less than the second geographic division threshold, that is, the lateral distance between any point in the first area and the road cleaning vehicle is greater than the first geographic division threshold and less than the second geographic division threshold.

[0048] In another example, the second area can be divided in combination with the longitudinal distance, the first geographic division threshold can include the first lateral distance threshold and the first longitudinal distance threshold, and the second geographic division threshold can include the second lateral distance threshold and the second longitudinal distance threshold. Then the second area is an area formed by multiple points in the environment image whose corresponding lateral distance is greater than the first lateral distance threshold and less than the second lateral distance threshold, and whose longitudinal distance is greater than the first longitudinal distance threshold and less than the second longitudinal distance threshold, that is, the lateral distance between any point in the first area and the road cleaning vehicle is greater than the first lateral distance threshold and less than the second lateral distance threshold, and the longitudinal distance is greater than the first longitudinal distance threshold and less than the second longitudinal distance threshold.

[0049] Further, the water outlet strategy matched by the second area is to adjust the spray distance of the water spray device to the preset spray distance. When it is detected that the target area where the target object is located is the second area, it means that the target object may be splashed by sewage. At this time, the spray distance of the water spray device can be adjusted to the preset spray distance to prevent the target object from being splashed. The processor can adjust the valve opening of the water outlet of the water spray device to change the water outlet valve amount of the water spray device, thereby adjusting the water spray distance of the water spray device. In one example, the second area can be further divided to obtain multiple sub-areas, and the water reduction amount corresponding to different sub-areas is different. For example, the second area includes a first sub-area and a second sub-area, and a first preset water outlet amount and a second preset water outlet amount are set correspondingly, and the second preset water outlet amount is greater than the first preset water outlet amount. When the target object is in the first sub-area, it is necessary to reduce the water significantly to reduce the water outlet of the water spray device to the first preset water outlet amount. When the target object is in the second sub-area, it is possible to reduce the water slightly to reduce the water outlet of the water spray device to the second preset water outlet amount. In this way, the water output of the water spraying device can be flexibly adjusted to ensure the operation time of the road cleaning vehicle while preventing splashing onto the target object.

[0050] Figure 2 A schematic diagram of area division provided in a specific embodiment of the present application. In a specific embodiment of the present application, Figure 2 As shown, the environment image can be divided into multiple areas based on the lateral distance, including a first area and a second area, the first area is a water stop area, and the second area is a water reduction area. Among them, the second area includes a first sub-area and a second sub-area, the water output control strategy corresponding to the first sub-area is a large water reduction, and the water output control strategy corresponding to the second sub-area is a small water reduction. In this way, the water output of the water spraying device can be flexibly adjusted to ensure the operation time of the road cleaning vehicle, while achieving the effect of preventing splashing to the target object.

[0051] In an embodiment of the present application, the environmental image includes a first environmental image and a second environmental image, the first environmental image and the second environmental image respectively include images of the road environment on the first side and the second side of the body of the road cleaning vehicle, the water spray device includes a first water spray device and a second water spray device respectively arranged on the first side and the second side, and the control method also includes: controlling the first water spray device according to the first environmental image; and controlling the second water spray device according to the second environmental image.

[0052] It can be understood that water spray devices are provided on both sides of the body of the road cleaning vehicle, namely, a first water spray device and a second water spray device. Since the road conditions on both sides of the road cleaning vehicle are not exactly the same, in order to ensure the operating efficiency of the road cleaning vehicle, the water spray devices on both sides can be controlled separately by independent control. Specifically, based on the control method for the road cleaning vehicle provided in the above embodiment, the first water spray device is controlled according to the first environmental image, and the second water spray device is controlled according to the second environmental image. In this way, the operating efficiency of the road cleaning vehicle can be guaranteed.

[0053] In an embodiment of the present application, a monocular camera is provided on the road cleaning vehicle. In a direction perpendicular to the chassis of the road cleaning vehicle, the monocular camera is higher than the water spraying device, and the projection of the monocular camera coincides with the projection of the water spraying device. The monocular camera is used to collect environmental images of the surrounding environment of the road cleaning vehicle and to measure the distance to the target object in the environmental image.

[0054] Specifically, the traditional method usually uses a binocular camera to capture images, which is costly, and it requires huge computing power to establish a coordinate system and calculate the distance, and the price of the corresponding processor is also high. The embodiment of the present application uses a monocular camera to capture the environmental image of the surrounding environment of the road cleaning vehicle, and the monocular camera is set directly above the water spraying device. The projections of the two in the vertical direction overlap, which is more conducive to camera calibration and the measurement process is simpler. Combined with the control method for a road cleaning vehicle provided in the embodiment of the present application, it is possible to reduce system costs while ensuring high reliability.

[0055] In a specific embodiment, the lateral distance and the longitudinal distance of each point in the environment image may be determined by using a camera monocular distance measurement method. Figure 3 The schematic diagram of the principle of monocular ranging of a camera provided in the embodiment of the present application. Figure 3As shown, assuming that there is a pedestrian in the environment image, and the pedestrian is on the ground, its grounding point Q must be on the ground. Then the depth of point Q can be solved. In the process of monocular ranging, point Q on the actual object corresponds to point Q' on the imaged picture, and the distance from point Q' to point O1 along the y-axis is O1P'. This distance O1P' is divided by the y-axis pixel focal length fy (in pixels), and then arctan is calculated to obtain angle b'. P' is the projection of Q' on the y-axis of the image coordinate system, angle b'=arctan(O1P' / f), angle b'=angle b, angle c=angle a+angle b, angle a can be obtained by camera calibration. After the camera is installed, the fixed angle a value can be calibrated, OP=H / sin(c), OD=OP*cos(b), and OD is the value of the target pedestrian in the Z direction in the camera coordinate system. Further, based on the above calculation results, combined with the relative position information of the camera and the sprinkler, the lateral distance and longitudinal distance of the pedestrian can be determined. Similarly, the horizontal and vertical distances of each point in the environmental image can be determined. Compared with traditional radar or binocular ranging, monocular ranging has a simpler and lighter hardware configuration, which can effectively reduce the manufacturing cost of the system and provide a more competitive advantage for the promotion and application of intelligent road cleaning vehicles.

[0056] In a specific embodiment of the present application, a control strategy for continuous pedestrians is proposed. The control strategy for continuous pedestrians is to solve a series of problems that may be caused by traditional processing methods, such as frequent switching of electromagnetic water valves leading to shortened life and poor cleaning effect. By using queues to store distance control parameters and comprehensively processing the results of a continuous period of time, a control strategy that can be more stable and efficient in practical applications is proposed.

[0057] First, the system records the detection results of each pedestrian distance and stores them in the memory in the form of a queue. This design can retain certain historical information and ensure that continuous pedestrian detection results are saved in a timely manner. The queue-based storage ensures that new detection results can be continuously updated without losing previous data, providing a data basis for subsequent comprehensive processing.

[0058] Secondly, by comprehensively processing the distance control parameters over a period of time, a more stable control strategy can be obtained. This comprehensive processing can be done in the form of mode or average to ensure that the control strategy is more representative. This design effectively avoids the frequent switching of water valves in traditional methods, reduces the workload of electromagnetic water valves, and prolongs their service life.

[0059] In the specific implementation, special consideration is given to continuous pedestrian scenes, such as busy areas such as bus stops. By comprehensively processing the results over a period of time, the system can automatically adapt to different pedestrian densities to ensure that the sprinkler works more stably in areas with high pedestrian flow. This is important for ensuring that the sprinkler sprays water evenly in areas with heavy pedestrian traffic, preventing the frequent water valve switching from damaging the water valve, and improving the environmental cleaning effect.

[0060] By comprehensively processing the results over a continuous period of time, the smart sprinkler can maintain a constant water spray distance in scenes with continuous pedestrians. This can not only effectively avoid the problem of frequent opening and closing of the water valve, but also maintain a certain consistency of water flow during the water spraying process, improving the cleaning effect. Especially in areas such as public transportation stations, this stable water spraying characteristic can better ensure the safety of pedestrians and ensure that the operation of the sprinkler can achieve the expected effect in various environments.

[0061] Through the innovative design of the control strategy for continuous pedestrians, the smart sprinkler truck can better cope with complex scenarios in practical applications, improve the stability and life of the system, and ensure the safety of pedestrians and maximize the environmental cleaning effect. This method has significant practicality and advancement in the pedestrian detection system of the smart sprinkler truck, providing a more intelligent and reliable solution for urban environmental management.

[0062] In a specific embodiment of the present application, an image processing method for snowy weather is proposed. In the case where the camera is dirty or has water droplets, especially in snowy weather, image processing technology is used to filter the image, aiming to improve the stability and reliability of pedestrian detection. Considering the limited hardware resources, a lightweight image processing method can be used to ensure the efficient operation of the system in a low computing power environment.

[0063] Considering that the camera may be affected by dirt in snowy weather, resulting in reduced image quality, this embodiment introduces image dirt removal technology, which can use traditional image processing methods, such as median filtering, mean filtering, etc., to eliminate noise and dirt in the image and improve image clarity.

[0064] In order to cope with the situation of weak light and reduced image contrast in snowy days, an environment adaptive contrast enhancement method can also be introduced. This method can adjust according to the local lighting conditions of the image, improve the image contrast, and make the features of pedestrians more obvious. In a low computing power environment, some simple and effective contrast enhancement algorithms can be selected, such as histogram equalization or adaptive histogram equalization.

[0065] Due to the limitation of hardware resources, it is crucial to select image processing algorithms with high real-time performance and low computational complexity. When removing raindrops, dirt and contrast enhancement from camera images, a lightweight network structure or simple image processing method is selected to ensure that image processing tasks can be completed in real time and efficiently on the edge computing box.

[0066] In order to adapt to different weather and road conditions, the system should have the ability to monitor the environment in real time and be able to dynamically adjust image processing parameters. By monitoring the camera image quality and ambient light information in real time, the system can adaptively select appropriate image processing algorithms and parameters to ensure the stability and accuracy of pedestrian detection.

[0067] Through the above-mentioned image processing innovations, we have used advanced image processing technology under limited hardware resources to improve the robustness and performance of the smart sprinkler truck pedestrian detection system for special conditions in snowy weather, ensuring that the system can work stably and reliably in various complex environments.

[0068] The embodiment of the present application further provides a processor configured to execute the control method for a road cleaning vehicle according to the above-mentioned implementation.

[0069] An embodiment of the present application further provides a road cleaning vehicle, which includes: a water spraying device; and the processor in the above embodiment.

[0070] In the embodiment of the present application, the water spray device includes a first water spray device and a second water spray device respectively arranged on a first side and a second side of a body of the road cleaning vehicle.

[0071] In a specific embodiment, in order to detect omnidirectional target objects, two cameras can be installed on the left and right sides of the flushing valve of the road cleaning vehicle to achieve all-round monitoring of the surrounding environment. This structural design takes into account that the sprinkler truck may adopt different hedging positions in actual operation, such as front hedging, middle hedging and rear hedging. In order to adapt to these different operating scenarios, we design a mounting bracket on each side of the vehicle just above the hedging position for flexible installation of cameras. This is conducive to improving the omnidirectional perception capability of the system. The cameras on the left and right sides are responsible for monitoring the conditions on both sides of the sprinkler truck's driving path, so that the system can fully cover the entire surrounding environment. Such a layout not only ensures all-round detection of pedestrians, but also effectively reduces blind spots and improves the accuracy and reliability of detection.

[0072] In an embodiment of the present application, the road cleaning vehicle also includes: a monocular camera that communicates with the processor, wherein the monocular camera is higher than the water spraying device in a direction perpendicular to the chassis of the road cleaning vehicle, and the monocular camera overlaps with the projection of the water spraying device, and is used to collect an environmental image of the surrounding environment of the road cleaning vehicle and measure the distance to the target object in the environmental image.

[0073] An embodiment of the present application further provides a machine-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the control method for a road cleaning vehicle in the above-mentioned embodiment is implemented.

[0074] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0075] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0078] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0079] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0080] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0081] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0082] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A control method for a road cleaning vehicle, characterized in that: The road cleaning vehicle includes a water spraying device, and the control method includes: During the operation of the road cleaning vehicle, acquiring an environmental image of the surrounding environment of the road cleaning vehicle; Dividing the environment image into a plurality of regions, and configuring different water discharge strategies for controlling the water spray device for the plurality of regions, respectively, wherein the water discharge strategies include controlling the water spray device to stop spraying water or adjusting the spray distance of the water spray device; Detecting whether there are target objects in the multiple areas, wherein the target objects include pedestrians; When the target object is detected, an area among the multiple areas where the target object is present and closest to the road cleaning vehicle is taken as a target area, and a water discharge strategy of the water spraying device matching the target area is executed.

2. The control method according to claim 1, characterized in that: Dividing the environment image into a plurality of regions comprises: determining a geographic division threshold based on a maximum spray distance of the water spray device; Converting the image coordinates of each point in the environment image into geographic coordinates, and determining the lateral distance between each point in the image and the water spray device according to the geographic coordinates, wherein the lateral distance is a distance perpendicular to the body direction of the road cleaning vehicle; The environment image is divided into a plurality of regions according to the lateral distance and the geographic division threshold.

3. The control method according to claim 2, characterized in that: The geographic division threshold includes a first geographic division threshold, the multiple areas include a first area, a lateral distance between any point in the first area and the road cleaning vehicle is less than or equal to the first geographic division threshold, and a water output strategy matched by the first area is to control the water spraying device to stop spraying water.

4. The control method according to claim 2, characterized in that: The geographic division threshold includes a first geographic division threshold and a second geographic division threshold, the second geographic division threshold is greater than the first geographic division threshold, the multiple areas include a second area, the lateral distance between any point in the second area and the road cleaning vehicle is greater than the first geographic division threshold and less than the second geographic division threshold, and the water output strategy matched by the second area is to adjust the spray distance of the water spray device to a preset spray distance.

5. The control method according to any one of claims 1 to 4, characterized in that: The environment image includes a first environment image and a second environment image, the first environment image and the second environment image respectively include images of road environments on a first side and a second side of a body of the road cleaning vehicle, the water spray device includes a first water spray device and a second water spray device respectively arranged on the first side and the second side, and the control method further includes: controlling the first water spraying device according to the first environment image; and The second water spraying device is controlled according to the second environment image.

6. The control method according to any one of claims 1 to 4, characterized in that: The road cleaning vehicle is provided with a monocular camera. In a direction perpendicular to the chassis of the road cleaning vehicle, the monocular camera is higher than the water spray device, and the projection of the monocular camera coincides with that of the water spray device. The monocular camera is used to collect an environmental image of the surrounding environment of the road cleaning vehicle and to measure the distance to a target object in the environmental image.

7. A processor, characterized in that: The method is configured to execute the control method for a road cleaning vehicle according to any one of claims 1 to 6.

8. A road cleaning vehicle, characterized in that: The road cleaning vehicle comprises: water sprinklers; and A processor according to claim 7.

9. The road cleaning vehicle according to claim 8, characterized in that: The road cleaning vehicle also includes: A monocular camera is in communication with the processor, wherein the monocular camera is higher than the water spray device in a direction perpendicular to the chassis of the road cleaning vehicle, and the projection of the monocular camera and the water spray device overlap, and is used to collect an environmental image of the surrounding environment of the road cleaning vehicle and measure the distance to the target object in the environmental image.

10. A machine-readable storage medium storing a program or an instruction, characterized in that: When the program or the instruction is executed by a processor, the control method for a road cleaning vehicle according to any one of claims 1 to 6 is implemented.

Images