Disclosure of Invention
In view of the above, the invention provides a sprinkling control method, a sprinkling control system and an intelligent sprinkling truck, which accurately predict the time when a pedestrian enters a sprinkling range by combining image and radar information, automatically control the intelligent sprinkling truck to stop sprinkling before the time is reached, avoid sprinkling to the pedestrian, intelligently control sprinkling, and reduce the labor intensity of a driver.
In order to achieve the above purpose, the invention provides the following specific technical scheme:
a watering control method is applied to a watering control system in an intelligent watering cart, and comprises the following steps:
collecting images in front of the intelligent watering cart and echo information of a radar in the running process of the intelligent watering cart;
identifying whether a pedestrian exists in the acquired image;
under the condition that a pedestrian exists in the acquired image, whether the pedestrian enters the spraying range of the intelligent watering cart in the future is determined according to the echo information of the radar;
if the pedestrian enters the spraying range in the future, predicting the moment when the pedestrian enters the spraying range;
and controlling the intelligent watering cart to stop spraying before the moment when the pedestrians enter the spraying range.
Optionally, the identifying whether a pedestrian exists in the acquired image includes:
and calling a pre-constructed pedestrian recognition model to recognize whether pedestrians exist in the acquired image.
Optionally, the determining, according to the echo information of the radar, whether the pedestrian will enter the spraying range of the intelligent watering cart in the future includes:
determining the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time according to the echo information of the radar at the adjacent sampling time;
determining the moving direction and the moving speed of the pedestrian relative to the intelligent watering cart according to the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time;
determining whether the pedestrian will enter the spray range in the future based on the moving direction and the moving speed of the pedestrian relative to the intelligent sprinkler.
Optionally, the determining the time when the pedestrian enters the spraying range includes:
according to the relative distance between the pedestrian and the intelligent watering cart at the current sampling moment and the moving speed of the pedestrian relative to the intelligent watering cart, the moment when the pedestrian enters the spraying range is calculated.
Optionally, the determining the time when the pedestrian enters the spraying range further includes:
updating the moment when the pedestrian enters the spraying range at each sampling moment;
the pedestrian that updates after detecting the relative distance of pedestrian and intelligent watering lorry is less than preset distance or current sampling moment and current sampling moment gets into under the condition that the length of time between the moment of spraying the scope is less than preset length of time, get into the pedestrian after the current sampling moment update the moment of spraying the scope is confirmed as final pedestrian and gets into the moment of spraying the scope.
Optionally, after controlling the intelligent sprinkler to stop spraying, the method further includes:
detecting whether a pedestrian has left the spray range;
and under the condition that the pedestrian is detected to leave the spraying range, controlling the intelligent watering cart to continue spraying.
A sprinkler control system comprising: the system comprises a visual identification system, a data processing unit and an upper-mounted controller;
the visual identification system is used for acquiring images in front of the intelligent watering cart and echo information of the radar in the running process of the intelligent watering cart;
the data processing unit is used for identifying whether pedestrians exist in the acquired image; under the condition that a pedestrian exists in the acquired image, whether the pedestrian enters the spraying range of the intelligent watering cart in the future is determined according to the echo information of the radar; if the pedestrian enters the spraying range in the future, predicting the moment when the pedestrian enters the spraying range;
and the loading controller is used for controlling the intelligent watering cart to stop spraying before the pedestrian enters the spraying range.
Optionally, the data processing unit includes:
and the pedestrian identification subunit is used for calling a pre-constructed pedestrian identification model and identifying whether a pedestrian exists in the acquired image.
Optionally, the data processing unit includes:
the encounter prediction subunit is used for determining the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time according to the echo information of the radar at the adjacent sampling time; determining the moving direction and the moving speed of the pedestrian relative to the intelligent watering cart according to the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time; determining whether the pedestrian will enter the spray range in the future based on the moving direction and the moving speed of the pedestrian relative to the intelligent sprinkler.
Optionally, the data processing unit includes:
and the encounter time prediction subunit is used for calculating the time when the pedestrian enters the spraying range according to the relative distance between the pedestrian and the intelligent watering cart at the current sampling time and the moving speed of the pedestrian relative to the intelligent watering cart.
Optionally, the data processing unit includes:
the meeting time predicting subunit is used for calculating the time when the pedestrian enters the spraying range according to the relative distance between the pedestrian and the intelligent watering cart at the current sampling time and the moving speed of the pedestrian relative to the intelligent watering cart; updating the moment when the pedestrian enters the spraying range at each sampling moment; the pedestrian that updates after detecting the relative distance of pedestrian and intelligent watering lorry is less than preset distance or current sampling moment and current sampling moment gets into under the condition that the length of time between the moment of spraying the scope is less than preset length of time, get into the pedestrian after the current sampling moment update the moment of spraying the scope is confirmed as final pedestrian and gets into the moment of spraying the scope.
Optionally, the data processing unit further includes:
the pedestrian detection subunit is used for detecting whether a pedestrian leaves the spraying range or not and triggering the upper-mounted controller under the condition that the pedestrian is detected to leave the spraying range;
the upper controller is further used for controlling the intelligent watering cart to continue spraying when the pedestrian detection subunit detects that the pedestrian leaves the spraying range.
An intelligent watering cart, comprising: the water pump motor and the sprinkling control system disclosed by the embodiment;
the rotating speed of the water pump motor is controlled by the sprinkling control system;
the vision system in the watering control system comprises: image acquisition devices and radar.
Optionally, the radar includes: millimeter-wave radar and ultrasonic radar.
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a sprinkling control method, which is characterized in that an image in front of an intelligent sprinkler and echo information of a radar are collected in the driving process of the intelligent sprinkler, whether a pedestrian enters a sprinkling range of the intelligent sprinkler in the future is accurately predicted according to the echo information of the radar under the condition that the pedestrian is identified in the collected image, the moment when the pedestrian enters the sprinkling range is accurately predicted under the condition that the pedestrian enters the sprinkling range in the future, the intelligent sprinkler is controlled to stop sprinkling before the moment, the phenomenon that the pedestrian is sprinkled by the sprinkler due to untimely operation of a driver is avoided, meanwhile, the sprinkling of the sprinkler is automatically controlled, the labor intensity of the driver is reduced, the driver is enabled to drive the sprinkler intensively, and the driving safety is improved.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention discloses a watering control method, which is applied to a watering control system in an intelligent watering cart, wherein the watering control system comprises a visual identification system, a data processing unit and an upper controller, the visual identification system comprises image acquisition equipment and a radar, the moment when a pedestrian enters a spraying range is predicted by combining image and radar echo information in the driving process of the intelligent watering cart, the intelligent watering cart is controlled to stop spraying before the moment, the phenomenon that the pedestrian is sprayed by the watering cart due to untimely operation of a driver is avoided, meanwhile, the labor intensity of the driver is reduced by automatically controlling the spraying of the watering cart, the driver is enabled to drive the watering cart intensively, and the driving safety is improved.
Specifically, referring to fig. 1, the watering control method disclosed in this embodiment includes the following steps:
s101: collecting images in front of the intelligent watering cart and echo information of a radar in the running process of the intelligent watering cart;
specifically, utilize the image acquisition equipment among the visual identification system in the intelligence watering lorry to gather the image in intelligence watering lorry the place ahead to utilize the radar among the visual identification system to gather the echo information of radar.
In order to increase the detection range of the radar, the radar in the vision recognition system may be a millimeter wave radar, in order to reduce the cost, the radar in the vision recognition system may be an ultrasonic radar, and further, in order to meet the requirements of the detection range and low cost, the millimeter wave radar and the ultrasonic radar may be used in combination in the vision recognition system.
S102: identifying whether a pedestrian exists in the acquired image;
optionally, a pre-constructed pedestrian recognition model is called, and whether a pedestrian exists in the acquired image is recognized.
The pedestrian recognition model is obtained by training a machine learning model by using a training sample marked whether to be a pedestrian, and the machine learning model can be a BP neural network model, a convolutional neural network model and the like, and is not specifically limited herein.
In order to improve the recognition accuracy of the pedestrian recognition model, it is necessary to expand the training samples and add pedestrian image samples of various scenes and various actions to the training sample set.
S103: under the condition that a pedestrian exists in the acquired image, whether the pedestrian enters the spraying range of the intelligent watering cart in the future is determined according to the echo information of the radar;
referring to fig. 2, the present embodiment discloses a method for determining whether a pedestrian will enter a spraying range of an intelligent watering cart in the future, which specifically includes the following steps:
s201: determining the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time according to the echo information of the radar at the adjacent sampling time;
s202: determining the moving direction and the moving speed of the pedestrian relative to the intelligent watering cart according to the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time;
specifically, according to the relative distance of pedestrian and intelligent watering lorry at adjacent sampling moment, if this relative distance is more and more littleer, then the moving direction for pedestrian on intelligent watering lorry is opposite with the moving direction of intelligent watering lorry, if this relative distance is more and more big, then the moving direction for pedestrian on intelligent watering lorry is the same with the moving direction of intelligent watering lorry.
The difference between the relative distance of pedestrian and the intelligence watering lorry at adjacent sampling moment divides the sampling interval, obtains the moving speed for the intelligence watering lorry pedestrian.
S203: based on the moving direction and moving speed of the pedestrian relative to the intelligent sprinkler, whether the pedestrian will enter the spraying range in the future is determined.
Based on relative to the intelligent watering cart, if the moving direction of the pedestrian is opposite to the moving direction of the intelligent watering cart, it is determined that the pedestrian will enter the spraying range in the future.
S104: if the pedestrian will enter the spraying range in the future, predicting the moment when the pedestrian enters the spraying range;
according to the relative distance between the pedestrian and the intelligent watering cart at the current sampling moment and the moving speed of the pedestrian relative to the intelligent watering cart, the moment when the pedestrian enters the spraying range is calculated.
Specifically, the relative distance of pedestrian and intelligent watering lorry at present sampling moment divides with the removal speed for intelligent watering lorry pedestrian, obtains that the pedestrian gets into the required length of time of spraying the scope, adds the pedestrian with present sampling moment again and gets into the required length of time of spraying the scope, obtains the moment that the pedestrian got into the spraying scope.
S105: before the pedestrian enters the moment of spraying the scope, control intelligent watering lorry and stop spraying.
It can be understood that, at each sampling time, a time when a pedestrian enters the spraying range is calculated, and if the speed of the pedestrian or the intelligent sprinkler changes, the time when the pedestrian enters the spraying range at each sampling time may be different, and because the sampling interval is very short, for example, 1 millisecond, in order to be able to control the intelligent sprinkler to stop spraying before the time when the pedestrian enters the spraying range, please refer to fig. 3, another spraying control method is disclosed in this embodiment, which specifically includes the following steps:
s301: collecting images in front of the intelligent watering cart and echo information of a radar in the running process of the intelligent watering cart;
s302: identifying whether a pedestrian exists in the acquired image;
s303: under the condition that a pedestrian exists in the acquired image, whether the pedestrian enters the spraying range of the intelligent watering cart in the future is determined according to the echo information of the radar;
s304: if the pedestrian will enter the spraying range in the future, predicting the moment when the pedestrian enters the spraying range;
s305: judging whether the relative distance between the pedestrian and the intelligent watering cart is smaller than a preset distance;
if the relative distance between the pedestrian and the intelligent watering cart is not less than the preset distance, returning to execute S301;
if the relative distance between the pedestrian and the intelligent sprinkler is smaller than the preset distance, executing S306: determining the moment when the pedestrian enters the spraying range after the current sampling moment is updated as the final moment when the pedestrian enters the spraying range;
s307: before the pedestrian enters the moment of spraying the scope, control intelligent watering lorry and stop spraying.
Optionally, whether the time when the pedestrian enters the spraying range after the current sampling time is updated is determined as the final time when the pedestrian enters the spraying range may be determined by judging whether the time between the current sampling time and the time when the pedestrian enters the spraying range after the current sampling time is updated is less than the preset time.
Further, after control intelligence watering lorry stopped spraying, the control system that sprinkles whether the pedestrian has left the spraying scope in real time detection, under the condition that detects the pedestrian and has left the spraying scope, control intelligence watering lorry and continue to spray.
The method for detecting whether the pedestrian leaves the spraying range includes various methods, for example, the time when the pedestrian leaves the spraying range is calculated according to the relative distance between the pedestrian and the intelligent sprinkler at the current sampling time, the length of the intelligent sprinkler and the moving speed of the pedestrian relative to the intelligent sprinkler, and the intelligent sprinkler is controlled to continuously spray after the time is reached. Whether the pedestrian leaves the spraying range or not can be judged through image acquisition equipment and/or radars on two sides of the intelligent watering cart.
Based on the foregoing embodiment, the present embodiment discloses a watering control system, and please refer to fig. 4, the watering control system includes: a vision recognition system 401, a data processing unit 402, and a loading controller 403;
the visual recognition system 401 is used for acquiring images in front of the intelligent watering cart and echo information of the radar in the driving process of the intelligent watering cart;
the data processing unit 402 is used for identifying whether a pedestrian exists in the acquired image; under the condition that a pedestrian exists in the acquired image, whether the pedestrian enters the spraying range of the intelligent watering cart in the future is determined according to the echo information of the radar; if the pedestrian enters the spraying range in the future, predicting the moment when the pedestrian enters the spraying range;
and the upper controller 403 is used for controlling the intelligent watering cart to stop spraying before the time when the pedestrian enters the spraying range.
Optionally, the data processing unit 402 includes:
and the pedestrian identification subunit is used for calling a pre-constructed pedestrian identification model and identifying whether a pedestrian exists in the acquired image.
Optionally, the data processing unit 402 includes:
the encounter prediction subunit is used for determining the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time according to the echo information of the radar at the adjacent sampling time; determining the moving direction and the moving speed of the pedestrian relative to the intelligent watering cart according to the relative distance between the pedestrian and the intelligent watering cart at the adjacent sampling time; determining whether the pedestrian will enter the spray range in the future based on the moving direction and the moving speed of the pedestrian relative to the intelligent sprinkler.
Optionally, the data processing unit 402 includes:
and the encounter time prediction subunit is used for calculating the time when the pedestrian enters the spraying range according to the relative distance between the pedestrian and the intelligent watering cart at the current sampling time and the moving speed of the pedestrian relative to the intelligent watering cart.
Optionally, the data processing unit 402 includes:
the meeting time predicting subunit is used for calculating the time when the pedestrian enters the spraying range according to the relative distance between the pedestrian and the intelligent watering cart at the current sampling time and the moving speed of the pedestrian relative to the intelligent watering cart; updating the moment when the pedestrian enters the spraying range at each sampling moment; the pedestrian that updates after detecting the relative distance of pedestrian and intelligent watering lorry is less than preset distance or current sampling moment and current sampling moment gets into under the condition that the length of time between the moment of spraying the scope is less than preset length of time, get into the pedestrian after the current sampling moment update the moment of spraying the scope is confirmed as final pedestrian and gets into the moment of spraying the scope.
Optionally, the data processing unit 402 further includes:
the pedestrian detection subunit is used for detecting whether a pedestrian leaves the spraying range or not and triggering the upper-mounted controller under the condition that the pedestrian is detected to leave the spraying range;
the upper controller 403 is further configured to control the intelligent watering cart to continue spraying when the pedestrian detection subunit detects that the pedestrian has left the spraying range.
The disclosed sprinkling control system of this embodiment, gather the image in intelligence watering lorry the place ahead and the echo information of radar at the in-process that traveles of intelligence watering lorry, under the condition of discerning the pedestrian in the image of gathering, whether the spraying scope that will get into the intelligence watering lorry in the future according to the echo information accuracy prediction of radar, and under the condition that will get into the spraying scope in the future of predicting the pedestrian, the accuracy prediction pedestrian gets into the moment of spraying the scope, stop spraying through controlling intelligent watering lorry before this moment, avoid driver's operation untimely to lead to the watering lorry to spray the emergence of pedestrian's phenomenon, spray through the automated control watering lorry simultaneously, reduce driver's intensity of labour, let driver's concentrated watering driving, the security of driving is improved.
This embodiment also discloses an intelligence watering lorry, please refer to fig. 5, and this intelligence watering lorry includes: the water pump motor 200 and the watering control system 100 disclosed in the above embodiments;
the rotating speed of the water pump motor 200 is controlled by the sprinkling control system 100;
the vision system in the watering control system comprises: image acquisition devices and radar.
Optionally, the radar includes: millimeter-wave radar and ultrasonic radar.
The disclosed intelligence watering lorry of this embodiment is through being equipped with watering control system on intelligent watering lorry, by the rotational speed of watering control system control water pump motor, before watering control system got into the moment of spraying the scope at the pedestrian, and automatic control water pump motor made intelligent watering lorry stop watering, and after watering control system left the spraying scope at the pedestrian, automatic control water pump motor made intelligent watering lorry continue watering. Avoid the driver to operate the emergence that leads to the watering lorry to spray pedestrian's phenomenon in time untimely, simultaneously through the spraying of automated control watering lorry, reduce driver's intensity of labour, let the driver concentrate on driving the watering lorry, improve the security of driving.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments can be combined arbitrarily, and the features described in the embodiments in the present specification can be replaced or combined with each other in the above description of the disclosed embodiments, so that those skilled in the art can implement or use the present application.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.