CN112753210A - Movable platform, control method thereof and storage medium - Google Patents
Movable platform, control method thereof and storage medium Download PDFInfo
- Publication number
- CN112753210A CN112753210A CN202080005304.0A CN202080005304A CN112753210A CN 112753210 A CN112753210 A CN 112753210A CN 202080005304 A CN202080005304 A CN 202080005304A CN 112753210 A CN112753210 A CN 112753210A
- Authority
- CN
- China
- Prior art keywords
- target
- movable platform
- target object
- distances
- distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/58—Means for changing the camera field of view without moving the camera body, e.g. nutating or panning of optics or image sensors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
A method of controlling a movable platform, the steps comprising: acquiring an image of a target object (S110); determining a target pixel point corresponding to a joint point of a target object in the image (S120); determining a target distance between the target object and the target object according to the pixel coordinate value of the target pixel point and the prior distance between the joint points of the target object (S130); the movable platform is controlled to move relative to the target object according to the target distance (S140). A target distance can be accurately determined, and a movable platform and a storage medium are provided.
Description
Technical Field
The present disclosure relates to the field of movable platforms, and in particular, to a movable platform, a control method thereof, and a storage medium.
Background
Images of the target may be captured by a camera on the movable platform as the movable platform moves relative to the target to determine the distance between the movable platform and the target. For example, according to the pinhole imaging principle, the object becomes larger in the image when the distance between the movable platform and the object becomes shorter, and the object becomes smaller in the screen when the distance between the movable platform and the object becomes longer, so that the distance between the movable platform and the object can be determined according to the size of the object in the image. For example, a target frame where the target is located in the image is detected, and the distance between the movable platform and the target is determined according to the size of the target frame and the prior size of the target.
However, when the posture of the target changes or a part of the target is blocked by the surrounding environment, the target frame is reduced. Therefore, the distance determined according to the size of the target frame in the image is far away from the real distance, and the movable platform can be inappropriately close to the target in a scene that the movable platform moves along with the target, so that the user experience is influenced, and the safety problem also exists.
Disclosure of Invention
Based on this, the embodiment of the application provides a movable platform, a control method thereof and a storage medium, which can solve the technical problems that the distance between the movable platform and a target cannot be accurately determined when the posture of the target changes or part of the target is blocked.
In a first aspect, an embodiment of the present application provides a method for controlling a movable platform, where the movable platform carries a shooting device; the method comprises the following steps:
acquiring an image obtained by shooting a target object by the shooting device;
determining a target pixel point corresponding to a joint point of the target object in the image;
determining a target distance between the movable platform and the target object according to the pixel coordinate value of the target pixel point in the image and the prior distance between the joint points of the target object;
and controlling the movable platform to move relative to the target object according to the target distance.
In a second aspect, embodiments of the present application provide a movable platform capable of carrying a camera, the movable platform comprising one or more processors, working individually or collectively, for performing the steps of:
acquiring an image obtained by shooting a target object by the shooting device;
determining a target pixel point corresponding to a joint point of the target object in the image;
determining a target distance between the movable platform and the target object according to the pixel coordinate value of the target pixel point in the image and the prior distance between the joint points of the target object;
and controlling the movable platform to move relative to the target object according to the target distance.
In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor is caused to implement the above-mentioned method.
The embodiment of the application provides a movable platform, a control method thereof and a storage medium, wherein a target pixel point corresponding to a joint point of a target object in an image is determined, and a target distance between the movable platform and the target object is determined according to a pixel coordinate value of the target pixel point in the image and a prior distance between the joint points of the target object, so that the posture change of the target object and the influence of shielding of the surrounding environment on target distance measurement can be avoided, and the accuracy and the safety of the control of the movable platform are improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure as claimed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a control method provided in an embodiment of the present application;
FIG. 2 is a schematic view of a scenario provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of a target object's joint provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of determining a target distance between a movable platform and a target object using triangulation principles provided by embodiments of the present application;
FIG. 5 is a diagram illustrating a filtering result of a first low-pass filter provided in an embodiment of the present application;
FIG. 6 is a diagram illustrating a filtering result of a second low-pass filter provided in an embodiment of the present application;
FIG. 7 is a schematic block diagram of a movable platform provided by an embodiment of the present application;
fig. 8 is a schematic block diagram of an unmanned aerial vehicle according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. 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 application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flow chart of a control method according to an embodiment of the present disclosure. The control method may be applied to a movable platform, and of course, may also be applied to a terminal device capable of communicating with the movable platform, or the control method may be performed by both the movable platform and the terminal device. The control method is used for determining the distance between the movable platform and the target object and controlling the movable platform to move according to the distance.
The terminal equipment can comprise at least one of a mobile phone, a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, wearable equipment, a remote controller and the like; the movable platform may comprise at least one of: cloud platform, unmanned vehicles or unmanned ships and light boats. Further, unmanned vehicles can be rotor-type unmanned aerial vehicles, such as quad-rotor unmanned aerial vehicles, hexa-rotor unmanned aerial vehicles, and octa-rotor unmanned aerial vehicles, and also can be fixed-wing unmanned aerial vehicles.
The present application mainly takes the control method applied in the movable platform as an example for explanation.
As shown in fig. 2, the movable platform 100 carries a camera 200, and the camera 200 can acquire an image of an object in a field of view, for example, an image of a person, an animal, a vehicle, a ship, or the like.
Specifically, one or more target objects 101 may be determined in the image captured by the capturing device 200, and optionally, the target object 101 may be, for example, a person, an animal, a vehicle, a ship, or the like.
As shown in fig. 1, the control method according to the embodiment of the present application includes steps S110 to S130.
And S110, acquiring an image obtained by shooting a target object by the shooting device.
For example, the movable platform 100 can determine the target object 101 in the image, for example, when a human body is detected in the image, the human body is determined as the target object 101; or when a plurality of human bodies are detected in the image, one or more of the human bodies may be determined as the target object 101.
For example, the movable platform 100 can send an image to the terminal device 300 communicatively connected to the movable platform 100, the terminal device 300 can display the image sent by the movable platform 100 and determine that an object corresponding to a selection operation is the target object 101 according to the selection operation of the user on the object in the image, and the terminal device 300 can send information of the target object 101 to the movable platform 100.
Illustratively, the terminal device 300 is carried by a user, and the movable platform 100 is capable of determining that the user of the orientation is the target object 101 by detecting the orientation of the terminal device 300.
And S120, determining a target pixel point corresponding to the joint point of the target object in the image.
Specifically, the joint points of the target object represent positions on the target object that are easier to recognize, and the distances between the joint points are specific, or the ranges of the distances are specific. Illustratively, a particular distance or a particular range of distances between different joint points may be referred to as a priori distances.
In some embodiments, the target object is a target person. The joint points of the target object comprise at least one of human skeleton joint points corresponding to a right shoulder, a right elbow, a right wrist, a left shoulder, a left elbow, a left wrist, a right hip, a right knee, a right ankle, a left hip, a left knee, a left ankle, a vertex and a neck.
Illustratively, the a priori distances between the target subject's joint points include at least one of a priori distances between shoulder elbows, between elbow wrists, between left and right shoulders, between shoulder hips, between hip knees, and between knee ankles.
For example, as shown in fig. 3, the a priori distance between the joint points of the target object may further include between the head and neck and between the neck and shoulder.
The priori distance between the shoulder elbows is the priori length of arm upside, and the priori distance between the elbow wrists is the priori length of arm downside, and the priori distance of controlling the shoulder is the priori width of shoulder, and the priori distance between the shoulder hips is the priori height of human upper part of the body, and the priori distance between the hip knees is the priori length of thigh, and the priori distance between the knee ankles is the priori length of shank.
Optionally, the a priori distances between the articulation points of the target object comprise a priori distances between different articulation points in a transverse direction of the target object and/or a priori distances between different articulation points in a longitudinal direction of the target object.
Illustratively, the a priori distance between the shoulder elbows may be 30 centimeters, the a priori distance between the elbow wrists may be 40 centimeters, the a priori distance between the hip knees may be 50 centimeters, and the a priori distance between the knee ankles may be 40 centimeters; illustratively, the a priori distance between the left and right shoulders may be 50 centimeters and the a priori distance between the left and right hips may be 50 centimeters.
In some other embodiments, the target object may be a vehicle, and the articulation point of the target object may include at least one of a window angle of a window, a center of a wheel hub, and a light of the vehicle.
Illustratively, when the target object is a vehicle, the prior distance between the joint points of the target object includes at least one of a prior distance between the centers of the front and rear hubs, a prior distance between the headlights on the two sides of the head, a prior distance between the headlights on the two sides of the tail, and the like.
In some embodiments, the target pixel points corresponding to the human bone joint points in the image may be determined by a human bone joint point detection algorithm. For example, the target pixel point corresponding to the joint point of the target object in the image may be determined through an image model-based algorithm and/or a deep learning-based algorithm. And determining target pixel points corresponding to the joint points of the target object in the image by regression through a machine learning method.
For example, the positions of target pixel points corresponding to a plurality of preset human body bone joint points in the image can be determined. For example, pixel coordinate values of target pixel points corresponding to human skeletal joint points of a right shoulder, a left shoulder, a right hip, a right knee, a right ankle, a left hip, a left knee and a left ankle are determined.
S130, determining a target distance between the movable platform and the target object according to the pixel coordinate value of a target pixel point in the image and the prior distance between the joint points of the target object.
In some embodiments, the target distance between the movable platform and the target object may be determined according to pixel coordinate values of target pixel points in the image and a priori distance between joint points of the target object by using a pinhole imaging principle. For example, the distance between the target pixel points may be determined according to pixel coordinate values of the target pixel points in the image, and then the target distance between the movable platform and the target object may be determined according to the distance between the target pixel points and the prior distance between the joint points of the target object.
In some embodiments, the target object is a target person. The distance between the target pixel points comprises the distance between one or more groups of target pixel points, for example, the distance between the target pixel points comprises at least one of the distances between target pixel points corresponding to a left shoulder and a left elbow, a right shoulder and a right elbow, a left elbow and a left wrist, a right elbow and a right wrist, a left shoulder and a right shoulder, a left shoulder and a left hip, a right shoulder and a right hip, a left hip and a left knee, a right hip and a right knee, a left knee and a left ankle, and a right knee and a right ankle.
Alternatively, the target pixels corresponding to the left shoulder and the left elbow may be regarded as one set of target pixels, and the target pixels corresponding to the right shoulder and the right elbow may be regarded as another set of target pixels.
For example, the distance between two target pixel points may be determined according to the difference between the pixel coordinate values of the two target pixel points. For example, the distance between the target pixel points corresponding to the left shoulder and the right shoulder may be determined according to a difference between the pixel coordinate value of the target pixel point corresponding to the right shoulder and the pixel coordinate value of the target pixel point corresponding to the left shoulder.
The target distance between the movable platform and the target object can be determined according to the distance between the target pixel points in the image. Specifically, the target distance between the movable platform and the target object may be determined according to the focal length of the photographing device, the distance between target pixel points in the image, and the prior distance between joint points of the target object.
In some embodiments, the triangulation principle may be used to determine the target distance between the movable platform and the target object according to the pixel coordinate values of the target pixel points in the image and the a priori distance between the joint points of the target object. Taking the joint points corresponding to the vertex and the neck as an example, please refer to fig. 4, where the position of the movable platform is point O, the joint point corresponding to the neck is point a, the joint point corresponding to the vertex is point B, the distance between points AB may be the prior distance between human heads and necks, an included angle between a connecting line AO between the point a and the movable platform and a connecting line BO between the point B and the movable platform is α, α may be obtained according to the internal parameters of the photographing device and the pixel coordinate values of the target pixel points corresponding to the point a and the point B, an included angle between the connecting line BO between the point B and the movable platform and the point AB is θ +90 °, and θ may be obtained according to the internal parameters of the photographing device and the pixel coordinate values of the target pixel points corresponding to the point B. Thus, the distance between the AOs can be obtained according to the trigonometric relation, and the distance between the AOs is taken as the target distance between the movable platform and the target object.
Determining the target distance between the movable platform and the target object according to the pixel coordinate values of the target pixel points corresponding to the other joint points and the prior distance between the joint points of the target object is similar to the above process, which is not repeated herein.
In some embodiments, the target distance between the movable platform and the target object may be determined according to one or more sets of pixel coordinate values of the target pixels and the a priori distances between the joint points corresponding to the sets of target pixels.
In some embodiments, the method further comprises: determining attributes of the target object; determining a priori distances between different joint points of the target object according to the attributes.
The target distance between the movable platform and the target object is determined according to the prior distance corresponding to the attribute of the target object, and the prior distance is closer to the actual condition of the target object, so that the target distance is more accurate.
For example, when the target object is a target person, the attribute of the target object includes at least one of the following: gender of the target object, whether it is an adult.
For example, when the attributes of the target object are different, the a priori distances between the corresponding different joint points may also be different. For example, the prior distance between the hip and the knee of the target object when the gender is male is larger than that when the gender is female; the target object is between the hip and knee in adults, and the prior distance between the knee and ankle is greater than in adults who are not.
Optionally, at least one articulation point is not at an end of the target object. For example, when the target object is a target person, at least one of the joints is not located on the head or foot of the target object. When the legs or the head of the target object are shielded by the surrounding environment, the target pixel point corresponding to the joint point and the pixel coordinate value of the target pixel point can still be determined, so that the target distance between the movable platform and the target object can be determined.
Specifically, as shown in fig. 3, although the posture of the target object is a sitting posture, the target pixel point corresponding to the human skeleton joint point in the image can be accurately detected; even if one part of the target object is shielded by the surrounding environment, the target pixel points corresponding to the human skeleton joint points of the part which is not shielded can still be determined.
By determining target pixel points corresponding to joint points of a target object in an image and determining a target distance between the movable platform and the target object according to pixel coordinate values of the target pixel points in the image, the attitude change of the target object and the influence of the shielding of the surrounding environment on the target distance measurement can be avoided, and the accuracy and the safety of the control of the movable platform are improved.
And S140, controlling the movable platform to move relative to the target object according to the target distance.
In some embodiments, said controlling said movable platform to move relative to said target object comprises: and planning a moving route of the movable platform and/or a shooting direction of the shooting device according to the target distance.
For example, the movable platform may be controlled to bypass or follow the target object according to the target distance. For example, if the current target distance is less than or equal to the preset distance threshold, the movable platform is controlled to move leftwards, rightwards or upwards to bypass, so that the movable platform is prevented from colliding the target object; meanwhile, the shooting direction of the shooting device can be adjusted, so that the shooting device keeps shooting the target object. For example, if the current target distance is greater than a specific distance, the movable platform is controlled to move towards the target object or accelerate to move towards the target object so as to follow the target object.
For example, when the target distance becomes larger, the target object may be determined to be far away from the movable platform, and then the movable platform may be controlled to move towards the target object or accelerate towards the target object; when the target distance becomes larger and the larger amplitude becomes larger, it can be determined that the target object is accelerating away from the movable platform, and then the movable platform can be controlled to accelerate to move towards the target object.
In some embodiments, said controlling said movable platform to move relative to said target object as a function of said target distance comprises: determining the position of a target object according to the shooting angle of the shooting device for shooting the target object and the target distance; and controlling the movable platform to move relative to the target object according to the position of the target object.
Illustratively, the shooting device is mounted on a tripod head, the tripod head is mounted on a movable platform, and the shooting angle of the shooting device for shooting the target object can be determined according to the posture of the tripod head. The position of the target object can be determined according to the shooting angle and the target distance of the target object in the shooting angle direction.
For example, the moving route of the movable platform and/or the photographing direction of the photographing apparatus may be planned according to the position of the target object. For example, the movable platform may be controlled to bypass or follow the target object according to the position of the target object.
For example, the motion state of the target object may be determined according to the position of the target object at different times, and the movable platform may be controlled to move relative to the target object according to the motion state of the target object.
In some embodiments, the target distance determined from the a priori distances between the joint points is a first target distance. And determining a second target distance between the movable platform and the target object according to the target frame where the target object is located.
Illustratively, the method further comprises: determining a target frame of the target object in the image; determining a second target distance between the movable platform and the target object according to the target frame.
As shown in fig. 3, the respective target frames of the two target objects are determined. Specifically, the target frame surrounds the periphery of the target object in the image. As shown in the left target frame of FIG. 3, the top end of the target frame abuts the top of the head of the target person, the bottom end abuts the bottom of the foot of the target person, the left end abuts the tip of the right foot of the target person, and the right end abuts the left elbow of the target person.
For example, a target box in which a target object is located in an image may be determined by a trained neural network model.
Illustratively, the determining a second target distance between the movable platform and the target object from the target box includes: and determining a second target distance between the movable platform and the target object according to the length of the target frame in a preset direction and the prior length of the target object in the preset direction.
For example, the length of the target frame in the preset direction is the height of the target frame, and the prior length of the target object in the preset direction is the height of the target object. For example, the prior length of the target object in the preset direction may be stored in advance in the movable platform and/or the terminal device communicatively connected to the movable platform; or the terminal device can determine the prior length of the target object in the preset direction according to the height setting operation of the user.
For example, a second target distance between the movable platform and the target object may be determined based on a height of the target frame in a vertical direction and a prior height of the target object.
Since the target object becomes larger in the image as the target distance between the movable platform and the target object is closer, the length of the target frame in the preset direction is larger, the target object becomes smaller in the image as the target distance between the movable platform and the target object is farther, and the length of the target frame in the preset direction is smaller, the target distance between the movable platform and the target object can be determined according to the length of the target frame in the preset direction. Likewise, the pinhole imaging principle or the triangulation principle may also be utilized, which is not described in detail herein.
In some embodiments, the method may further comprise: and determining the prior length of the target object in the preset direction according to the attribute of the target object.
The target distance between the movable platform and the target object is determined according to the prior length corresponding to the attribute of the target object, and the prior length is closer to the actual condition of the target object, so that the target distance is more accurate.
For example, when the target object is a target person, the attribute of the target object includes at least one of the following: gender of the target object, whether it is an adult.
When the postures of the target objects are different, the target frames determined in the images are also different. As shown in fig. 3, if the target object is in a sitting posture, the determined target frame is greatly different from the target frame when the target object is in a standing posture, for example, the height of the target frame is significantly small when the target object is in a sitting posture, the target distance determined according to the height of the target frame and the height of the target object is far from the real distance, and the movable platform may be improperly close to the target in a scene where the movable platform moves along with the target. When a portion of the target image is occluded by the surrounding environment, the height of the target frame is significantly smaller, and the target distance determined from the height of the target frame and the height of the target object is also far from the real distance.
In some embodiments, step S140 of controlling the movable platform to move relative to the target object according to the target distance includes: controlling the movable platform to move relative to the target object according to the first target distance and the second target distance.
For example, the second target distance may be checked according to the first target distance, and it may be prevented that the second target distance determined when the posture of the target object is changed or a part of the target object is blocked by the surrounding environment is deviated greatly, and the movable platform may be moved to the target improperly when the movable platform is controlled according to the second target distance.
For example, if the difference between the first target distance and the second target distance is large, it may be determined that the second target distance is unreliable, and the movable platform may not be controlled according to the second target distance.
In some embodiments, the number of the first target distances is plural, and a plurality of the first target distances are determined according to different a priori distances. In particular, the first target distances may be determined based on distances between the sets of target pixels and a priori distances between the corresponding joint points.
Illustratively, the controlling the movable platform to move relative to the target object based on the first target distance and the second target distance includes: determining a difference between a plurality of the first target distances and the second target distances; and when the difference value meets a preset condition, controlling the movable platform to move relative to the target object according to the second target distance.
For example, when a difference between a plurality of first target distances and a plurality of second target distances is smaller than a first difference threshold, it may be determined that the difference satisfies the preset condition, and the movable platform may be controlled to move relative to the target object according to the second target distance.
By checking the second target distance according to the plurality of first target distances, whether the second target distance is reliable can be determined more accurately.
Illustratively, the determining a plurality of differences between the first target distance and the second target distance includes: and eliminating abnormal values in the plurality of first target distances, and determining the difference value between the first target distance and the second target distance after the abnormal values are eliminated. Wherein a difference between the outlier and the first target distance other than the outlier is greater than a second difference threshold.
Specifically, in some scenarios, for example, due to the influence of the shooting direction or the posture of the target object, the first target distance cannot be accurately determined according to the pixel coordinate values of some target pixels, and for example, the deviation between the abnormal first target distance and other first target distances is large. By removing the abnormal value, the distance of the second target can be checked according to the accurate distance of the first target, and whether the distance of the second target is reliable or not can be determined more accurately.
In some embodiments, when the difference does not satisfy a preset condition, the movable platform may be controlled to move relative to the target object according to a plurality of the first target distances.
Illustratively, said controlling movement of said movable platform relative to said target object in accordance with a plurality of said first target distances comprises: determining an average value of the first target distances according to the first target distances; and controlling the movable platform to move relative to the target object according to the average value.
Specifically, when the difference values between the plurality of first target distances and the second target distance are all greater than a first difference threshold value, it may be determined that the second target distance determined according to the target frame is unreliable, and the movable platform is controlled to move relative to the target object according to an average value of the plurality of first target distances.
For example, an abnormal value in a plurality of first target distances may be eliminated, and an average value of the plurality of first target distances may be determined according to the first target distances after the abnormal value is eliminated. Specifically, the abnormal value may be a difference value greater than a preset threshold value from the first target distance other than the abnormal value.
By eliminating the abnormal value, the movable platform can be controlled according to the accurate first target distance.
In some embodiments, the second target distance is checked for consistency with the plurality of first target distances, e.g., the second target distance is compared to the first target distance. If the difference between most of the first target distance and the second target distance is not greater than the first difference threshold, it may be determined that the second target distance is normal; if the difference between most of the first target distances is less than the second difference threshold and the difference between these first target distances and the second target distances is greater than the first difference threshold, it may be determined that the second target distance is anomalous. The movable platform may be controlled according to the second target distance when the second target distance is normal, and may be controlled according to an average value of the first target distances or one of the first target distances, of which the difference between them is smaller than a second difference threshold value, when the second target distance is abnormal.
In some embodiments, the step of determining the second target distance between the movable platform and the target object according to the target frame may not be performed, and the movable platform may be controlled to move relative to the target object directly according to a plurality of the first target distances. For example, step S140 of controlling the movable platform to move relative to the target object according to the target distance includes: determining an average value of a plurality of target distances according to the plurality of target distances, namely a plurality of first target distances determined according to different prior distances; and controlling the movable platform to move relative to the target object according to the average value.
Illustratively, the determining an average value of a plurality of the target distances according to the plurality of the target distances comprises: rejecting outliers in a plurality of the target distances, a difference between the outliers and the target distances other than the outliers being greater than a third difference threshold; and determining the average value of the target distances according to the target distances after the abnormal values are eliminated.
Optionally, the first difference threshold, the second difference threshold, and the third difference threshold may be equal or unequal.
In some embodiments, the method further comprises: and carrying out filtering processing on the target distance.
Illustratively, the controlling the movable platform to move relative to the target object according to the target distance includes: and determining the position of the target object according to the target distance after the filtering processing.
For example, the target distance for filtering may be a first target distance, a second target distance, or an average of the first target distances after removing the abnormal value. For example, when the difference between the first target distances and the second target distances meets a preset condition, performing filtering processing on the second target distance; and when the difference value does not meet the preset condition, carrying out filtering processing on the average value of the plurality of first target distances.
In some scenes, the determined first target distance and the second target distance are not accurate enough due to factors such as light rays and shooting angles when the target object is shot, the determined target distance can be smoother through filtering, and the accuracy and the smoothness of the control of the movable platform can be improved conveniently.
Illustratively, the filtering the target distance includes: detecting an outlier in the target distance through a first low pass filter; filtering the target distance through a second low-pass filter to smooth the target distance; wherein a cut-off frequency of the first low-pass filter is lower than a cut-off frequency of the second low-pass filter.
Fig. 5 is a schematic diagram showing the detection of abnormal values in the target distances by the first low-pass filter, the dark curves in fig. 5 represent the target distances after the historical and current target distances are filtered by the first low-pass filter, the light curves distributed along the dark curves are the historical and current target distances before filtering, and the light curves in the boxes are the abnormal values detected by the first low-pass filter.
As shown in fig. 6, which is a schematic diagram of the target distance after the filtering process is performed on the historical and current target distances by the second low-pass filter, the light-colored curve along the dark-colored curve in fig. 6 represents the target distance after the filtering process by the second low-pass filter.
Specifically, referring to fig. 5 and 6, the filtering result of the first low-pass filter is smoother, but the detail information of the original data is lost; therefore, first, the position of the anomalous observation is detected using the first low-pass filter. The second low-pass filter can filter the original data without the abnormal value determined by the first low-pass filter, the smoothness of the filtering result of the second low-pass filter is between that of the original data and that of the data filtered by the first low-pass filter, most of the detail information of the original data can be reserved, and high-frequency noise can be removed.
In some embodiments, the outlier in the target distance may be detected by a plurality of first low pass filters whose cutoff frequencies sequentially increase. Abnormal values in the target distance can be detected more accurately, and the accuracy and the smoothness of the target distance after filtering processing are improved.
Illustratively, the filtering the target distance by the second low-pass filter includes: updating the outlier by the second low pass filter. And controlling the movable platform according to the updated target distance to prevent potential safety hazards caused by abnormal target distance.
Specifically, the updating the abnormal value by the second low-pass filter includes: and filtering other target distances except the abnormal value through the second low-pass filter to obtain the updated target distance at the abnormal value, so that the updated target distance corresponding to the abnormal value can be determined according to the historical target distance, and the movable platform can be controlled according to the accurate and updated target distance.
The abnormal value can be accurately positioned through the first low-pass filter with stronger filtering action, and the abnormal value can be updated and more detailed information can be reserved according to the filtering action of the second low-pass filter with weaker filtering action on the target distance, so that the control accuracy of the movable platform is improved.
Specifically, since the first low-pass filter and the second low-pass filter have different time lags, the filtered target distance can be time-synchronized according to the lag characteristics of the respective low-pass filters.
According to the control method of the movable platform, the target pixel points corresponding to the joint points of the target object in the image are determined, and the target distance between the movable platform and the target object is determined according to the pixel coordinate values of the target pixel points in the image, so that the target distance measurement can be prevented from being influenced by the posture change of the target object and the shielding of the surrounding environment, and the accuracy and the safety of the control of the movable platform are improved.
Referring to fig. 7, fig. 7 is a schematic block diagram of a movable platform 700 according to an embodiment of the present application. Illustratively, the movable platform 700 may include, for example, at least one of a pan-tilt, an unmanned aerial vehicle, an unmanned vehicle, or an unmanned boat. The unmanned aerial vehicle can be, for example, a rotary wing unmanned aerial vehicle, such as a quad-rotor unmanned aerial vehicle, a hexa-rotor unmanned aerial vehicle, an eight-rotor unmanned aerial vehicle, or a fixed wing unmanned aerial vehicle; the pan/tilt head includes, for example, a hand-held pan/tilt head, or a pan/tilt head that can be mounted on an unmanned aerial vehicle, an unmanned vehicle, or an unmanned boat.
Specifically, the movable platform 700 can mount a camera. Illustratively, the camera is mounted on a pan-tilt head, which is mounted on a movable platform 700 such as an unmanned aerial vehicle. Illustratively, the pan/tilt head includes at least one pivot structure, wherein the pivot structure may include at least one of a pivot structure corresponding to a yaw (yaw) axis, a pivot structure corresponding to a roll (roll) axis, and a pivot structure corresponding to a pitch (pitch) axis. Through the action of the rotating shaft structure, the posture of the shooting device can be stabilized, for example, the shooting direction of the shooting device is kept unchanged.
In particular, the movable platform 700 includes one or more processors 701.
In some embodiments, the movable platform 700 also includes memory 702.
Illustratively, the processor 701 and the memory 702 are connected by a bus 703, such as an I2C (Inter-integrated Circuit) bus.
Specifically, the Processor 701 may be a Micro-controller Unit (MCU), a Central Processing Unit (CPU), a Digital Signal Processor (DSP), or the like.
Specifically, the Memory 702 may be a Flash chip, a Read-Only Memory (ROM) magnetic disk, an optical disk, a usb disk, or a removable hard disk.
In particular, the one or more processors 701, working individually or collectively, are configured to perform the steps of the control method for a movable platform as described previously.
Illustratively, the processor 701 is configured to run a computer program stored in the memory 702 and to implement the aforementioned control method for the movable platform when executing the computer program.
Illustratively, the processor 701 is configured to run a computer program stored in the memory 702 and to implement the following steps when executing the computer program:
acquiring an image obtained by shooting a target object by the shooting device;
determining a target pixel point corresponding to a joint point of the target object in the image;
determining a target distance between the movable platform and the target object according to the pixel coordinate value of a target pixel point in the image and the prior distance between the joint points of the target object;
and controlling the movable platform to move relative to the target object according to the target distance.
The specific principle and implementation manner of the movable platform provided in the embodiment of the present application are similar to those of the control method of the movable platform in the foregoing embodiment, and are not described here again.
Referring to fig. 8, fig. 8 is a schematic block diagram of an unmanned aerial vehicle 800 according to an embodiment of the present application.
Specifically, the unmanned aerial vehicle 800 can be equipped with a camera. Illustratively, the camera is mounted on a pan-tilt head, which is mounted on the unmanned aerial vehicle 800.
Specifically, the UAV 800 includes one or more processors 801.
In some embodiments, unmanned aerial vehicle 800 also includes memory 802.
Illustratively, the processor 801 and the memory 802 are connected by a bus 803, such as an I2C (Inter-integrated Circuit) bus.
Specifically, the Processor 801 may be a Micro-controller Unit (MCU), a Central Processing Unit (CPU), a Digital Signal Processor (DSP), or the like.
Specifically, the Memory 802 may be a Flash chip, a Read-Only Memory (ROM) magnetic disk, an optical disk, a usb disk, or a removable hard disk.
The UAV 800 also includes a flight assembly 804, the flight assembly 804 being configured to fly.
In particular, the one or more processors 801, working individually or collectively, are configured to perform the steps of the control method for a movable platform as previously described.
Illustratively, the processor 801 is configured to run a computer program stored in the memory 802 and to implement the aforementioned control method for the movable platform when executing the computer program.
Illustratively, the processor 801 is configured to run a computer program stored in the memory 802, and when executing the computer program, to implement the following steps:
acquiring an image obtained by shooting a target object by the shooting device;
determining a target pixel point corresponding to a joint point of the target object in the image;
determining a target distance between the movable platform and the target object according to the pixel coordinate value of a target pixel point in the image and the prior distance between the joint points of the target object;
and controlling the movable platform to move relative to the target object according to the target distance.
The specific principle and implementation manner of the aircraft provided in the embodiment of the present application are similar to the control method of the movable platform in the foregoing embodiment, and details are not described here.
Embodiments of the present application also provide a computer-readable storage medium, which stores a computer program, where the computer program includes program instructions, and when the computer program is executed by a processor, the processor is enabled to implement the steps of the control method for a movable platform provided in the foregoing embodiments.
The computer readable storage medium may be any internal storage unit of a removable platform, such as an aircraft, for example, a hard disk or a memory of the removable platform, according to any of the previous embodiments. The computer readable storage medium may also be an external storage device of the removable platform, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the removable platform.
According to the movable platform, the aircraft and the computer readable storage medium provided by the embodiment of the application, the target pixel points corresponding to the joint points of the target object in the image are determined, and the target distance between the movable platform and the target object is determined according to the pixel coordinate values of the target pixel points in the image, so that the influence of the attitude change of the target object and the shielding of the surrounding environment on the target distance measurement can be avoided, and the accuracy and the safety of the control of the movable platform are improved.
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It should also be understood that the term "and/or" as used in this application and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (52)
1. A control method of a movable platform is characterized in that the movable platform carries a shooting device; the method comprises the following steps:
acquiring an image obtained by shooting a target object by the shooting device;
determining a target pixel point corresponding to a joint point of the target object in the image;
determining a target distance between the movable platform and the target object according to the pixel coordinate value of a target pixel point in the image and the prior distance between the joint points of the target object;
and controlling the movable platform to move relative to the target object according to the target distance.
2. The method of claim 1, wherein the target object is a target person, and the joint points comprise at least one of human skeletal joint points corresponding to a right shoulder, a right elbow, a right wrist, a left shoulder, a left elbow, a left wrist, a right hip, a right knee, a right ankle, a left hip, a left knee, a left ankle, a crown of a head, and a neck;
the prior distances between the joint points of the target object comprise at least one of the prior distances between shoulders and elbows, between elbows and wrists, between left shoulders, right shoulders, between shoulders and hips, between hips and knees and between knee ankles.
3. The method of claim 1, wherein determining the target distance between the movable platform and the target object according to the pixel coordinate values of the target pixel points in the image and the prior distance between the joint points of the target object comprises:
and determining the target distance between the movable platform and the target object according to the pixel coordinate values of target pixel points in the image and the prior distance between the joint points of the target object by using a small hole imaging principle or a triangulation principle.
4. The method according to any one of claims 1-3, further comprising:
determining attributes of the target object;
determining a priori distances between different joint points of the target object according to the attributes.
5. The method of claim 4, wherein the attributes of the target object comprise at least one of: gender of the target object, whether it is an adult.
6. The method of any one of claims 1-5, wherein the target distance is a first target distance, the method further comprising:
determining a target frame of the target object in the image;
determining a second target distance between the movable platform and the target object according to the target frame;
the controlling the movable platform to move relative to the target object according to the target distance comprises:
controlling the movable platform to move relative to the target object according to the first target distance and the second target distance.
7. The method of claim 6, wherein the number of the first target distances is plural, a plurality of the first target distances being determined according to different a priori distances, the controlling the movable platform to move relative to the target object according to the first target distances and the second target distances comprises:
determining a difference between a plurality of the first target distances and the second target distances;
when the difference value meets a preset condition, controlling the movable platform to move relative to the target object according to the second target distance;
and when the difference value does not meet the preset condition, controlling the movable platform to move relative to the target object according to the plurality of first target distances.
8. The method of claim 7, further comprising:
when the difference value between the first target distances and the second target distances is smaller than a first difference threshold value, determining that the difference value meets the preset condition.
9. The method of claim 7, wherein said controlling movement of said movable platform relative to said target object according to a plurality of said first target distances comprises:
determining an average value of the first target distances according to the first target distances;
and controlling the movable platform to move relative to the target object according to the average value.
10. The method of claim 9, wherein determining an average of a plurality of the first target distances from a plurality of the first target distances comprises:
rejecting abnormal values in a plurality of first target distances, wherein the difference value between the abnormal value and the first target distances except the abnormal value is larger than a preset threshold value;
and determining the average value of the first target distances according to the first target distances after the abnormal values are eliminated.
11. The method of claim 7, wherein determining a plurality of differences between the first target distance and the second target distance comprises:
rejecting outliers in the plurality of first target distances, wherein a difference between the outliers and the first target distances other than the outliers is greater than a second difference threshold;
and determining the difference value between the first target distance and the second target distance after the abnormal value is eliminated.
12. The method of claim 6, wherein said determining a second target distance between the movable platform and the target object from the target box comprises:
and determining a second target distance between the movable platform and the target object according to the length of the target frame in a preset direction and the prior length of the target object in the preset direction.
13. The method of claim 12, wherein determining a second target distance between the movable platform and the target object according to the length of the target frame in a preset direction and the a priori length of the target object in the preset direction comprises:
determining a second target distance between the movable platform and the target object according to the height of the target frame in the vertical direction and the prior height of the target object.
14. The method of claim 12, further comprising:
and determining the prior length of the target object in the preset direction according to the attribute of the target object.
15. The method of any one of claims 1-5, wherein the number of target distances is plural, a plurality of the target distances being determined according to different a priori distances, the controlling the movable platform to move relative to the target object according to the target distances comprising:
determining an average value of the target distances according to the target distances;
and controlling the movable platform to move relative to the target object according to the average value.
16. The method of claim 15, wherein determining an average of a plurality of the target distances from the plurality of target distances comprises:
rejecting outliers in a plurality of the target distances, a difference between the outliers and the target distances other than the outliers being greater than a third difference threshold;
and determining the average value of the target distances according to the target distances after the abnormal values are eliminated.
17. The method according to any one of claims 1-16, further comprising:
filtering the target distance;
the controlling the movable platform to move relative to the target object according to the target distance comprises:
and determining the position of the target object according to the target distance after the filtering processing.
18. The method of claim 17, wherein the filtering the target distance comprises:
detecting an outlier in the target distance through a first low pass filter;
filtering the target distance through a second low-pass filter to smooth the target distance;
wherein a cut-off frequency of the first low-pass filter is lower than a cut-off frequency of the second low-pass filter.
19. The method of claim 18, wherein the outlier in the target distance is detected by a plurality of first low pass filters whose cutoff frequencies increase sequentially.
20. The method according to claim 18 or 19, wherein the filtering the target distance by the second low-pass filter comprises:
updating the outlier by the second low pass filter.
21. The method of claim 20, wherein said updating the outlier with the second low pass filter comprises:
and filtering other target distances except the abnormal value through the second low-pass filter to obtain the updated target distance at the abnormal value.
22. The method of any one of claims 1-21, wherein at least one articulation point is not at an end of the target object.
23. The method of any one of claims 1-21, wherein said controlling the movable platform to move relative to the target object as a function of the target distance comprises:
determining the position of a target object according to the shooting angle of the shooting device for shooting the target object and the target distance;
and controlling the movable platform to move relative to the target object according to the position of the target object.
24. The method of any one of claims 1-23, wherein said controlling the movable platform to move relative to the target object comprises:
planning a movement route of the movable platform and/or a photographing direction of the photographing device.
25. The method of any one of claims 1-23, wherein said controlling the movable platform to move relative to the target object comprises:
and controlling the movable platform to bypass or follow the target object.
26. A movable platform capable of carrying a camera, the movable platform comprising one or more processors, working individually or collectively, for performing the steps of:
acquiring an image obtained by shooting a target object by the shooting device;
determining a target pixel point corresponding to a joint point of the target object in the image;
determining a target distance between the movable platform and the target object according to the pixel coordinate value of a target pixel point in the image and the prior distance between the joint points of the target object;
and controlling the movable platform to move relative to the target object according to the target distance.
27. The movable platform of claim 26, wherein the target object is a target person, and the articulation points comprise at least one of human skeletal articulation points corresponding to a right shoulder, a right elbow, a right wrist, a left shoulder, a left elbow, a left wrist, a right hip, a right knee, a right ankle, a left hip, a left knee, a left ankle, a crown of a head, and a neck;
the prior distances between the joint points of the target object comprise at least one of the prior distances between shoulders and elbows, between elbows and wrists, between left shoulders, right shoulders, between shoulders and hips, between hips and knees and between knee ankles.
28. The movable platform of claim 26, wherein the processor is further configured to implement:
and determining the target distance between the movable platform and the target object according to the pixel coordinate values of target pixel points in the image and the prior distance between the joint points of the target object by using a small hole imaging principle or a triangulation principle.
29. The movable platform of any one of claims 26-28, wherein the processor is further configured to implement:
determining attributes of the target object;
determining a priori distances between different joint points of the target object according to the attributes.
30. The movable platform of claim 29, wherein the properties of the target object include at least one of: gender of the target object, whether it is an adult.
31. The movable platform of any one of claims 26-30, wherein the target distance is a first target distance, the processor further configured to implement:
determining a target frame of the target object in the image;
determining a second target distance between the movable platform and the target object according to the target frame;
the controlling the movable platform to move relative to the target object according to the target distance comprises:
controlling the movable platform to move relative to the target object according to the first target distance and the second target distance.
32. The movable platform of claim 31, wherein the number of the first target distances is plural, a plurality of the first target distances being determined according to different a priori distances, the controlling the movable platform to move relative to the target object according to the first target distances and the second target distances comprising:
determining a difference between a plurality of the first target distances and the second target distances;
when the difference value meets a preset condition, controlling the movable platform to move relative to the target object according to the second target distance;
and when the difference value does not meet the preset condition, controlling the movable platform to move relative to the target object according to the plurality of first target distances.
33. The movable platform of claim 32, wherein the processor is further configured to implement:
when the difference value between the first target distances and the second target distances is smaller than a first difference threshold value, determining that the difference value meets the preset condition.
34. The movable platform of claim 32, wherein the controlling the movable platform to move relative to the target object according to the plurality of first target distances comprises:
determining an average value of the first target distances according to the first target distances;
and controlling the movable platform to move relative to the target object according to the average value.
35. The movable platform of claim 34, wherein the determining an average of a plurality of the first target distances from a plurality of the first target distances comprises:
rejecting abnormal values in a plurality of first target distances, wherein the difference value between the abnormal value and the first target distances except the abnormal value is larger than a preset threshold value;
and determining the average value of the first target distances according to the first target distances after the abnormal values are eliminated.
36. The movable platform of claim 32, wherein the determining a plurality of differences between the first target distance and the second target distance comprises:
rejecting outliers in the plurality of first target distances, wherein a difference between the outliers and the first target distances other than the outliers is greater than a second difference threshold;
and determining the difference value between the first target distance and the second target distance after the abnormal value is eliminated.
37. The movable platform of claim 31, wherein the determining a second target distance between the movable platform and the target object from the target box comprises:
and determining a second target distance between the movable platform and the target object according to the length of the target frame in a preset direction and the prior length of the target object in the preset direction.
38. The movable platform of claim 37, wherein determining a second target distance between the movable platform and the target object based on the length of the target frame in a predetermined direction and the a priori length of the target object in the predetermined direction comprises:
determining a second target distance between the movable platform and the target object according to the height of the target frame in the vertical direction and the prior height of the target object.
39. The movable platform of claim 37, wherein the processor is further configured to implement:
and determining the prior length of the target object in the preset direction according to the attribute of the target object.
40. The movable platform of any one of claims 26-30, wherein the number of target distances is plural, plural target distances being determined according to different a priori distances, the controlling the movable platform to move relative to the target object according to the target distances comprising:
determining an average value of the target distances according to the target distances;
and controlling the movable platform to move relative to the target object according to the average value.
41. The movable platform of claim 40, wherein the determining an average of a plurality of the target distances from the plurality of target distances comprises:
rejecting outliers in a plurality of the target distances, a difference between the outliers and the target distances other than the outliers being greater than a third difference threshold;
and determining the average value of the target distances according to the target distances after the abnormal values are eliminated.
42. The movable platform of any one of claims 26-41, wherein the processor is further configured to implement:
filtering the target distance;
the controlling the movable platform to move relative to the target object according to the target distance comprises:
and determining the position of the target object according to the target distance after the filtering processing.
43. The movable platform of claim 42, wherein the filtering the target distance comprises:
detecting an outlier in the target distance through a first low pass filter;
filtering the target distance through a second low-pass filter to smooth the target distance;
wherein a cut-off frequency of the first low-pass filter is lower than a cut-off frequency of the second low-pass filter.
44. The movable platform of claim 43, wherein outliers in the target distance are detected by a plurality of first low pass filters whose cutoff frequencies increase sequentially.
45. The movable platform of claim 43 or 44, wherein the filtering the target distance by a second low-pass filter comprises:
updating the outlier by the second low pass filter.
46. The movable platform of claim 45, wherein the updating the outlier by the second low pass filter comprises:
and filtering other target distances except the abnormal value through the second low-pass filter to obtain the updated target distance at the abnormal value.
47. The movable platform of any one of claims 26-46, wherein at least one articulation point is not at an end of the target object.
48. The movable platform of any one of claims 26-46, wherein the controlling the movable platform to move relative to the target object as a function of the target distance comprises:
determining the position of a target object according to the shooting angle of the shooting device for shooting the target object and the target distance;
and controlling the movable platform to move relative to the target object according to the position of the target object.
49. The movable platform of any one of claims 26-48, wherein the controlling the movable platform to move relative to the target object comprises:
planning a movement route of the movable platform and/or a photographing direction of the photographing device.
50. The movable platform of any one of claims 26-48, wherein the controlling the movable platform to move relative to the target object comprises:
and controlling the movable platform to bypass or follow the target object.
51. The movable platform of any one of claims 26-50, wherein the movable platform comprises at least one of: cloud platform, unmanned vehicles or unmanned ships and light boats.
52. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the method according to any one of claims 1-25.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2020/087083 WO2021217311A1 (en) | 2020-04-26 | 2020-04-26 | Movable platform and control method therefor, and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112753210A true CN112753210A (en) | 2021-05-04 |
Family
ID=75651303
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202080005304.0A Pending CN112753210A (en) | 2020-04-26 | 2020-04-26 | Movable platform, control method thereof and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112753210A (en) |
WO (1) | WO2021217311A1 (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105847684A (en) * | 2016-03-31 | 2016-08-10 | 深圳奥比中光科技有限公司 | Unmanned aerial vehicle |
CN108022255A (en) * | 2017-12-07 | 2018-05-11 | 深圳慧源创新科技有限公司 | Unmanned plane automatic tracking method, unmanned plane autotracker and unmanned plane |
CN108628306A (en) * | 2018-04-10 | 2018-10-09 | 平安科技(深圳)有限公司 | Robot ambulation disorder detection method, device, computer equipment and storage medium |
CN108960211A (en) * | 2018-08-10 | 2018-12-07 | 罗普特(厦门)科技集团有限公司 | A kind of multiple target human body attitude detection method and system |
CN109271845A (en) * | 2018-07-31 | 2019-01-25 | 浙江理工大学 | Human action analysis and evaluation methods based on computer vision |
CN109782812A (en) * | 2019-03-06 | 2019-05-21 | 深圳慧源创新科技有限公司 | Unmanned plane during flying method, apparatus, PID controller and storage medium |
CN109960962A (en) * | 2017-12-14 | 2019-07-02 | 腾讯科技(深圳)有限公司 | Image-recognizing method, device, electronic equipment and readable storage medium storing program for executing |
WO2019144296A1 (en) * | 2018-01-23 | 2019-08-01 | 深圳市大疆创新科技有限公司 | Control method and apparatus for movable platform and movable platform |
CN110225400A (en) * | 2019-07-08 | 2019-09-10 | 北京字节跳动网络技术有限公司 | A kind of motion capture method, device, mobile terminal and storage medium |
CN110807391A (en) * | 2019-10-25 | 2020-02-18 | 中国人民解放军国防科技大学 | Human body posture instruction identification method for human-unmanned aerial vehicle interaction based on vision |
CN110991268A (en) * | 2019-11-13 | 2020-04-10 | 华中科技大学 | Depth image-based Parkinson hand motion quantization analysis method and system |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104506773A (en) * | 2014-12-22 | 2015-04-08 | 天津市亚安科技股份有限公司 | Camera automatic zoom control method based on human eye distance |
CN107458308B (en) * | 2016-06-02 | 2020-06-30 | 爱保科技有限公司 | Driving assisting method and system |
CN106354156A (en) * | 2016-09-29 | 2017-01-25 | 腾讯科技(深圳)有限公司 | Method and device for tracking target object, and air vehicle |
CN107908195B (en) * | 2017-11-06 | 2021-09-21 | 深圳市道通智能航空技术股份有限公司 | Target tracking method, target tracking device, tracker and computer-readable storage medium |
WO2020037524A1 (en) * | 2018-08-22 | 2020-02-27 | 深圳市大疆创新科技有限公司 | Control method for movable platform, movable platform and readable storage medium |
CN109887040B (en) * | 2019-02-18 | 2020-04-14 | 北京航空航天大学 | Moving target active sensing method and system for video monitoring |
-
2020
- 2020-04-26 CN CN202080005304.0A patent/CN112753210A/en active Pending
- 2020-04-26 WO PCT/CN2020/087083 patent/WO2021217311A1/en active Application Filing
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105847684A (en) * | 2016-03-31 | 2016-08-10 | 深圳奥比中光科技有限公司 | Unmanned aerial vehicle |
CN108022255A (en) * | 2017-12-07 | 2018-05-11 | 深圳慧源创新科技有限公司 | Unmanned plane automatic tracking method, unmanned plane autotracker and unmanned plane |
CN109960962A (en) * | 2017-12-14 | 2019-07-02 | 腾讯科技(深圳)有限公司 | Image-recognizing method, device, electronic equipment and readable storage medium storing program for executing |
WO2019144296A1 (en) * | 2018-01-23 | 2019-08-01 | 深圳市大疆创新科技有限公司 | Control method and apparatus for movable platform and movable platform |
CN110651274A (en) * | 2018-01-23 | 2020-01-03 | 深圳市大疆创新科技有限公司 | Movable platform control method and device and movable platform |
CN108628306A (en) * | 2018-04-10 | 2018-10-09 | 平安科技(深圳)有限公司 | Robot ambulation disorder detection method, device, computer equipment and storage medium |
CN109271845A (en) * | 2018-07-31 | 2019-01-25 | 浙江理工大学 | Human action analysis and evaluation methods based on computer vision |
CN108960211A (en) * | 2018-08-10 | 2018-12-07 | 罗普特(厦门)科技集团有限公司 | A kind of multiple target human body attitude detection method and system |
CN109782812A (en) * | 2019-03-06 | 2019-05-21 | 深圳慧源创新科技有限公司 | Unmanned plane during flying method, apparatus, PID controller and storage medium |
CN110225400A (en) * | 2019-07-08 | 2019-09-10 | 北京字节跳动网络技术有限公司 | A kind of motion capture method, device, mobile terminal and storage medium |
CN110807391A (en) * | 2019-10-25 | 2020-02-18 | 中国人民解放军国防科技大学 | Human body posture instruction identification method for human-unmanned aerial vehicle interaction based on vision |
CN110991268A (en) * | 2019-11-13 | 2020-04-10 | 华中科技大学 | Depth image-based Parkinson hand motion quantization analysis method and system |
Also Published As
Publication number | Publication date |
---|---|
WO2021217311A1 (en) | 2021-11-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110874864B (en) | Method, device, electronic equipment and system for obtaining three-dimensional model of object | |
US9047507B2 (en) | Upper-body skeleton extraction from depth maps | |
CN106960454B (en) | Depth of field obstacle avoidance method and equipment and unmanned aerial vehicle | |
CN108363946B (en) | Face tracking system and method based on unmanned aerial vehicle | |
JP6985532B2 (en) | Data processing methods and devices, electronic devices and storage media | |
US20180160045A1 (en) | Method and device of image processing and camera | |
CN113074733A (en) | Flight trajectory generation method, control device and unmanned aerial vehicle | |
EP3644826A1 (en) | A wearable eye tracking system with slippage detection and correction | |
CN107798702B (en) | Real-time image superposition method and device for augmented reality | |
CN113366491B (en) | Eyeball tracking method, device and storage medium | |
CN106625673A (en) | Narrow space assembly system and assembly method | |
US9630322B2 (en) | Information processing apparatus, method therefor, measurement apparatus, and working apparatus for estimating a position/orientation of a three-dimensional object based on relative motion | |
CN109448105B (en) | Three-dimensional human body skeleton generation method and system based on multi-depth image sensor | |
JP2016173313A (en) | Visual line direction estimation system, visual line direction estimation method and visual line direction estimation program | |
WO2022021027A1 (en) | Target tracking method and apparatus, unmanned aerial vehicle, system, and readable storage medium | |
JP2018004420A (en) | Device, mobile body device, positional deviation detecting method, and distance measuring method | |
CN110619660A (en) | Object positioning method and device, computer readable storage medium and robot | |
JP6947066B2 (en) | Posture estimator | |
CN110720113A (en) | Parameter processing method and device, camera equipment and aircraft | |
CN114722913A (en) | Attitude detection method and apparatus, electronic device, and computer-readable storage medium | |
CN110673607B (en) | Feature point extraction method and device under dynamic scene and terminal equipment | |
Moore et al. | A stereo vision system for uav guidance | |
CN110651274A (en) | Movable platform control method and device and movable platform | |
JP2018009918A (en) | Self-position detection device, moving body device, and self-position detection method | |
CN111105467A (en) | Image calibration method and device and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20230113 |