Disclosure of Invention
The invention aims to provide an automatic parking method and device for a balance car in a narrow space, which can improve the running safety of the balance car in the narrow space.
The purpose of the invention is realized by the following technical scheme:
according to one aspect of the invention, the invention discloses an automatic parking method of a balance car in a narrow space, which comprises the following steps:
judging the entrance of the narrow space through image recognition;
measuring the distance between every two obstacles around after entering a narrow space;
if each interval is larger than a first preset value; and controlling the balance car to stop running and ejecting the bracket or the auxiliary wheel.
Further, the method for judging the entrance into the narrow space comprises the following steps:
continuously capturing an entrance outline pattern of a narrow space through a camera;
and when the entrance contour completely disappears from the picture, judging that the balance car enters the narrow space.
When a driver prepares to enter narrow spaces such as subways and elevators, the driver can travel towards the entrance direction of the narrow spaces, so that the contour pattern of the entrance can be continuously captured, the contour pattern is larger and tends to the edge of the camera viewing frame more and disappears completely when entering the narrow spaces, and whether the driver enters the narrow spaces can be accurately judged based on the characteristic.
Further, the method for judging the narrow space entering further comprises the steps of detecting an infrared signal;
when the entrance contour completely disappears from the picture and the infrared signal is detected, the balance car is judged to enter the narrow space.
The door of the entry in many narrow spaces has infrared light curtain, avoids pressing from both sides wounded people, consequently, when the driver passes through the entry, just can sense infrared signal, combines aforementioned pattern recognition, can more accurate judgement driver whether get into narrow space.
Further, the method also comprises the step of counting the people flow in real time:
when the balance car is in a state of stopping running and popping up the bracket or the auxiliary wheel; opening a front camera of the balance car;
measuring and calculating people flow data;
and when the people flow data is lower than a second preset value, starting the balance car to enter a static balance state.
Narrow spaces such as elevator, subway, its transit time is limited, and the time of opening door, lift-cabin door at every turn all is shorter, and this technical scheme can start in advance when narrow space people are less for the balance car gets into static balanced state, and the balance car neither can influence other people like this, can withdraw rapidly when the driver leaves narrow space again, the guarantee efficiency of passing.
Further, the method for measuring and calculating people stream data comprises the following steps:
measuring and calculating the distance data between the balance car and each person around the balance car;
and obtaining people stream data by averaging all the interval data.
When the stream of people reduces, people in the narrow space can pull open the distance with other people automatically because of instinct, and the interval between people can be enlarged promptly, otherwise, the interval reduces. Therefore, the people flow change trend can be accurately estimated by measuring and calculating the distance, and the state of the static balance vehicle can be maintained as long as the distance is generally large and the balance vehicle has a certain moving space, so that the distance data can not only reflect the people flow change trend, but also be key data required by the safe driving of the balance vehicle.
Further, the method for measuring and calculating people stream data comprises the following steps:
counting the number of people around the balance car according to image comparison;
and obtaining the people flow data according to the variation trend of the number of people.
The image comparison can directly obtain the number of people around, and the change trend of the people flow is judged more accurately.
Further, the method further comprises:
judging the movement state of the barrier;
when the barrier is in a static state, shooting a picture of the barrier, identifying the characteristics of the object in a networking manner, and planning a detour route according to an identification result; when the obstacle is in motion, the speed is reduced or the operation is suspended.
When a driver walks in a narrow space, people and articles always keep in a static state, and the other part of people are in a flowing state when going in and out of the narrow space, so that a lot of difficulties are caused to driving of the balance car. By adopting the technical scheme, the obstacles can be automatically identified through the computer, the optimal coping strategy is calculated according to the obstacles of different types and the motion states thereof, and unnecessary conflicts caused by artificial misjudgment are avoided.
Further, the object characteristics comprise property information, height information or width information, and the balance car plans a detour route according to the property information, the height information or the width information. The object properties mainly refer to soft and hard data of objects, and some articles, such as sponges and grass piles, are high in degree, but the balance car can directly cross the objects. But the articles with the same height can be bypassed if the bricks are replaced. Secondly, when the object is relatively low, it can be pressed through directly, and when the object is relatively high, it needs to go around. Furthermore, the width of the object determines the length of the line which needs to be bypassed, for example, the obstacle is a brick, the width is very short, the balance car can be easily bypassed after being deviated in advance, for example, the obstacle is wood, the road is blocked, and the road needs to be searched again or the driver is prompted to walk across.
Further, the object characteristics include character information, height information, and width information;
when the character information is rigid and the height exceeds a first threshold value, planning a detour route according to the width information; or the character information is flexible, the height exceeds a second threshold value, and a detour route is planned according to the width information; the second threshold is greater than the first threshold.
The object characteristics include attribute information; if the attribute information is animal or human, reducing the speed or suspending the operation, and sending out alarm information; and when the obstacle is detected to be free from avoidance in the preset time, planning a detour route. Some items, such as sponges and grass heaps, while relatively tall, may be passed directly over the balance car. But the articles with the same height can be bypassed if the bricks are replaced. Animals and people have motility, even if the animals and the people are in a static state during identification, the animals and the people can still give an alarm in the modes of loudspeakers, indicator lights and the like to remind people to give way. The method reduces the calculation amount of the planned route on one hand, and reduces lane changing on the other hand, thereby being beneficial to driving safety.
Further, the method for reducing the speed or suspending the operation when the obstacle is in the moving state comprises the following steps:
measuring the distance between the balance car and the barrier; when the obstacle is still positioned on the normal driving route and the distance is smaller than a third threshold value, reducing the running speed of the balance vehicle; when the barrier is still positioned on the normal driving route and the distance is smaller than a fourth threshold value, controlling the balance car to stop running; when the obstacle deviates from the normal driving route, controlling the balance car to accelerate until the initial speed before acceleration is recovered after the obstacle is crossed; the fourth threshold is less than the third threshold.
And further, when the shape information is flexible and the height is less than or equal to a second threshold value, the balance car is controlled to cross over the top of the obstacle.
Further, the method for judging the movement state of the obstacle comprises the following steps:
shooting pictures of the obstacles at preset time intervals;
comparing the positions of the obstacles in any two pictures, and judging the obstacles to be static if the positions are the same; otherwise, the movement is judged.
According to another aspect of the present invention, there is disclosed an automatic parking apparatus of a balance car in a narrow space, comprising:
means for determining an entrance of the narrow space by image recognition;
means for measuring the spacing of each obstacle around the perimeter after entering the confined space;
for if each pitch is greater than a first preset value; and the device controls the balance car to stop running and ejects the bracket or the auxiliary wheel.
Compared with the prior art, the invention has the technical effects that: the balance car judges the entrance of the narrow space through image identification, and the area where the balance car is about to enter is judged in advance by utilizing a mature image identification technology so as to formulate a corresponding coping strategy. After entering narrow spaces such as subways and elevators, drivers need to find places and place, and proper foot placement points are kept at certain intervals with obstacles such as people and objects around. Whether the current position of the balance car can be used as an ideal foot-landing point or not can be judged by measuring the distance between every two barriers around. After a proper foot drop point is found, the balance car is controlled to stop running and pop up the bracket or the auxiliary wheel, so that the balance car can stably and quietly stay in place, and the risk of rubbing with other people is avoided.
Detailed Description
The invention discloses an automatic parking method of a balance car in a narrow space, which comprises the following steps:
s11, judging the entrance of the narrow space through image recognition;
s12, measuring the distance between every two obstacles around after entering a narrow space;
s13, if each interval is larger than a first preset value;
and S14, controlling the balance car to stop running and ejecting the bracket or the auxiliary wheel.
According to another aspect of the present invention, there is disclosed an automatic parking apparatus of a balance car in a narrow space, comprising:
means for determining an entrance of the narrow space by image recognition;
means for measuring the spacing of each obstacle around the perimeter after entering the confined space;
for if each pitch is greater than a first preset value; and the device controls the balance car to stop running and ejects the bracket or the auxiliary wheel.
The balance car judges the entrance of the narrow space through image identification, and the area where the balance car is about to enter is judged in advance by utilizing a mature image identification technology so as to formulate a corresponding coping strategy. After entering narrow spaces such as subways and elevators, drivers need to find places and place, and proper foot placement points are kept at certain intervals with obstacles such as people and objects around. Whether the current position of the balance car can be used as an ideal foot-landing point or not can be judged by measuring the distance between every two barriers around. After a proper foot drop point is found, the balance car is controlled to stop running and pop up the bracket or the auxiliary wheel, so that the balance car can stably and quietly stay in place, and the risk of rubbing with other people is avoided. The patent of the applicant's prior application has already proposed a balance car with a bracket or an auxiliary wheel, and the details thereof are not repeated herein.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
In this context, a mobile intelligent terminal (such as a smart phone, a tablet computer, a wearable device, or smart glasses), a computer, an AI (artificial intelligence), a robot, a VR (virtual reality), an AR (augmented reality), a smart home device, or a smart industrial control device, etc. may execute a predetermined process such as numerical calculation and/or logic calculation by running a predetermined program or instruction, and may include a processor and a memory, where the processor executes a persistent instruction pre-stored in the memory to execute the predetermined process, or the processor executes the predetermined process by hardware such as an ASIC, an FPGA, or a DSP, or a combination of the two. Computer devices include, but are not limited to, servers, personal computers, laptops, tablets, smart phones, and the like.
Network devices include, but are not limited to, a single network server, a server group of multiple network servers, or a Cloud of numerous computers or network servers based on Cloud Computing (Cloud Computing), which is one type of distributed Computing, a super virtual computer consisting of a collection of loosely coupled computers. Wherein the computer device can be operated alone to implement the invention, or can be accessed to a network and implement the invention through interoperation with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.
It should be noted that the user equipment, the network device, the network, etc. are only examples, and other existing or future computer devices or networks may also be included in the scope of the present invention, and are included by reference.
The methods discussed below, some of which are illustrated by flow diagrams, may be implemented by hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to perform the necessary tasks may be stored in a machine or computer readable medium such as a storage medium. The processor(s) may perform the necessary tasks.
Specific structural and functional details disclosed herein are merely representative and are provided for purposes of describing example embodiments of the present invention. The present invention may, however, be embodied in many alternate forms and should not be construed as limited to only the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element may be termed a second element, and, similarly, a second element may be termed a first element, without departing from the scope of example embodiments. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. In contrast, when an element is referred to as being "directly connected" or "directly coupled" to another element, there are no intervening elements present. Other words used to describe the relationship between elements (e.g., "between" versus "directly between", "adjacent" versus "directly adjacent to", etc.) should be interpreted in a similar manner.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
The invention will be further described with reference to the accompanying figures 1 and 2 and preferred embodiments.
The automatic parking method of the balance car in the narrow space disclosed by the embodiment comprises the following steps:
judging the entrance of the narrow space through image recognition;
measuring the distance between every two obstacles around after entering a narrow space;
if each interval is larger than a first preset value; and controlling the balance car to stop running and ejecting the bracket or the auxiliary wheel.
Distance description of the embodiment two methods for judging entering narrow space
Method 1
Continuously capturing an entrance outline pattern of a narrow space through a camera;
and when the entrance contour completely disappears from the picture, judging that the balance car enters the narrow space.
When a driver prepares to enter narrow spaces such as subways and elevators, the driver can travel towards the entrance direction of the narrow spaces, so that the contour pattern of the entrance can be continuously captured, the contour pattern is larger and tends to the edge of the camera viewing frame more and disappears completely when entering the narrow spaces, and whether the driver enters the narrow spaces can be accurately judged based on the characteristic.
Method two
Detecting an infrared signal on the basis of the first method;
when the entrance contour completely disappears from the picture and the infrared signal is detected, the balance car is judged to enter the narrow space.
The door of the entry in many narrow spaces has infrared light curtain, avoids pressing from both sides wounded people, consequently, when the driver passes through the entry, just can sense infrared signal, combines aforementioned pattern recognition, can more accurate judgement driver whether get into narrow space.
Optionally, the method further includes the step of counting people flow in real time:
when the balance car is in a state of stopping running and popping up the bracket or the auxiliary wheel; opening a front camera of the balance car;
measuring and calculating people flow data;
and when the people flow data is lower than a second preset value, starting the balance car to enter a static balance state.
Narrow spaces such as elevator, subway, its transit time is limited, and the time of opening door, lift-cabin door at every turn all is shorter, and this technical scheme can start in advance when narrow space people are less for the balance car gets into static balanced state, and the balance car neither can influence other people like this, can withdraw rapidly when the driver leaves narrow space again, the guarantee efficiency of passing.
The embodiment discloses two methods for measuring and calculating people stream data.
The first is a scheme with pitch measurement, which includes:
measuring and calculating the distance data between the balance car and each person around the balance car;
and obtaining people stream data by averaging all the interval data.
When the stream of people reduces, people in the narrow space can pull open the distance with other people automatically because of instinct, and the interval between people can be enlarged promptly, otherwise, the interval reduces. Therefore, the people flow change trend can be accurately estimated by measuring and calculating the distance, and the state of the static balance vehicle can be maintained as long as the distance is generally large and the balance vehicle has a certain moving space, so that the distance data can not only reflect the people flow change trend, but also be key data required by the safe driving of the balance vehicle.
The second is a scheme with image contrast, which includes:
counting the number of people around the balance car according to image comparison;
and obtaining the people flow data according to the variation trend of the number of people.
The image comparison can directly obtain the number of people around, and the change trend of the people flow is judged more accurately.
Optionally, the parking method in a narrow space is improved, and the passing method is further optimized. Referring to fig. 2, specifically, the following steps are included:
judging the movement state of the barrier;
when the barrier is in a static state, shooting a picture of the barrier, identifying the characteristics of the object in a networking manner, and planning a detour route according to an identification result; when the obstacle is in motion, the speed is reduced or the operation is suspended.
When a driver walks in a narrow space, people and articles always keep in a static state, and the other part of people are in a flowing state when going in and out of the narrow space, so that a lot of difficulties are caused to driving of the balance car. By adopting the technical scheme, the obstacles can be automatically identified through the computer, the optimal coping strategy is calculated according to the obstacles of different types and the motion states thereof, and unnecessary conflicts caused by artificial misjudgment are avoided.
Optionally, the object characteristics include property information, height information, or width information, and the balance car plans the detour route according to the property information, the height information, or the width information. The object properties mainly refer to soft and hard data of objects, and some articles, such as sponges and grass piles, are high in degree, but the balance car can directly cross the objects. But the articles with the same height can be bypassed if the bricks are replaced. Secondly, when the object is relatively low, it can be pressed through directly, and when the object is relatively high, it needs to go around. Furthermore, the width of the object determines the length of the line which needs to be bypassed, for example, the obstacle is a brick, the width is very short, the balance car can be easily bypassed after being deviated in advance, for example, the obstacle is wood, the road is blocked, and the road needs to be searched again or the driver is prompted to walk across.
Optionally, the object characteristics include property information, height information, and width information;
when the character information is rigid and the height exceeds a first threshold value, planning a detour route according to the width information; or the character information is flexible, the height exceeds a second threshold value, and a detour route is planned according to the width information; the second threshold is greater than the first threshold.
Similarly, some articles, such as sponges and grass heaps, although relatively tall, may be passed directly over the balance car. But the articles with the same height can be bypassed if the bricks are replaced.
Optionally, the object characteristics include attribute information; if the attribute information is animal or human, reducing the speed or suspending the operation, and sending out alarm information; and when the obstacle is detected to be free from avoidance in the preset time, planning a detour route. Animals and people have motility, even if the animals and the people are in a static state during identification, the animals and the people can still give an alarm in the modes of loudspeakers, indicator lights and the like to remind people to give way. The method reduces the calculation amount of the planned route on one hand, and reduces lane changing on the other hand, thereby being beneficial to driving safety.
Optionally, when the obstacle is in a moving state, the method of reducing the speed or suspending the operation includes:
measuring the distance between the balance car and the barrier; when the obstacle is still positioned on the normal driving route and the distance is smaller than a third threshold value, reducing the running speed of the balance vehicle; when the barrier is still positioned on the normal driving route and the distance is smaller than a fourth threshold value, controlling the balance car to stop running; when the obstacle deviates from the normal driving route, controlling the balance car to accelerate until the initial speed before acceleration is recovered after the obstacle is crossed; the fourth threshold is less than the third threshold.
Optionally, when the shape information is flexible and the height is less than or equal to the second threshold, the balance car is controlled to cross over the top of the obstacle.
Optionally, the method for determining the motion state of the obstacle includes:
shooting pictures of the obstacles at preset time intervals;
comparing the positions of the obstacles in any two pictures, and judging the obstacles to be static if the positions are the same; otherwise, the movement is judged.
As another embodiment of the present invention, the present invention discloses an automatic parking device of a balance car in a narrow space, including:
the judgment device 1: an entrance for judging a narrow space by image recognition;
the measuring device 2: the device is used for measuring the distance between every two obstacles around after entering a narrow space;
the control device 3: for if each pitch is greater than a first preset value; and controlling the balance car to stop running and ejecting the bracket or the auxiliary wheel.
The automatic parking device can be used for realizing the automatic parking method of the balance car in a narrow space.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.