CN115713843A - Object monitoring method, system and device based on sweeping robot and storage medium - Google Patents
Object monitoring method, system and device based on sweeping robot and storage medium Download PDFInfo
- Publication number
- CN115713843A CN115713843A CN202211258942.0A CN202211258942A CN115713843A CN 115713843 A CN115713843 A CN 115713843A CN 202211258942 A CN202211258942 A CN 202211258942A CN 115713843 A CN115713843 A CN 115713843A
- Authority
- CN
- China
- Prior art keywords
- target object
- target
- sweeping robot
- image frame
- robot
- 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
Landscapes
- Manipulator (AREA)
Abstract
The invention discloses an object monitoring method, system and device based on a sweeping robot and a storage medium, and relates to the technical field of intelligent sweeping robots. Through carrying out the algorithm improvement on the basis of robot of sweeping the floor for the robot of sweeping the floor can also carry out the tracking control to personnel at home except possessing the function of cleaning. The sweeping robot acquires a target tracking image of a target object in real time in the process of tracking the target object, analyzes the target tracking image, determines the trunk aspect ratio of the target object, and performs state abnormity alarm aiming at the target object when the trunk aspect ratio is larger than the preset aspect ratio to indicate that the target object is likely to fall down, so that the robot can find the accident condition of the household old people.
Description
Technical Field
The invention relates to the technical field of intelligent sweeping robots, in particular to a method, a system, a device and a storage medium for monitoring an object based on a sweeping robot.
Background
With the coming of aging, the need of monitoring the elderly is more and more prominent, especially, the elderly living alone are prone to falling down due to sudden diseases or other reasons, and family members cannot find the condition that the elderly have accidents in time, so that the best rescue opportunity is missed.
At present, the monitoring mode to solitary old man is mainly at solitary old man's house in installation camera, comes the long-range condition of watching the old man at home through the camera, but this kind of mode exists the control blind area, can not effectively monitor the old man, if every position at home all installs the camera, can increase the installation and the network transmission cost of camera. In addition, the guardian is difficult to check the monitoring picture all the time, so that the guardian cannot find whether the old people have an accident in time.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a method, a system, a device and a storage medium for monitoring an object based on a sweeping robot, which can find whether the old people at home fall down or not in time and reduce the monitoring cost.
On one hand, the embodiment of the invention provides an object monitoring method based on a sweeping robot, which is applied to the sweeping robot, and the object monitoring method based on the sweeping robot comprises the following steps:
acquiring target object characteristics;
tracking a target object based on the target object characteristics and collecting a target tracking image;
determining the trunk aspect ratio of the target object according to the target tracking image;
and when the trunk aspect ratio is larger than a preset aspect ratio, performing state abnormity alarm on the target object.
According to some embodiments of the invention, the alarming for the target object for the abnormal state comprises:
controlling an alarm module arranged on the sweeping robot to give an alarm in advance;
monitoring whether the false alarm information is received or not in a preset time period, controlling the alarm module to stop alarming when the false alarm information is received in the preset time period, and sending alarm information to a related user terminal when the false alarm information is not received in the preset time period.
According to some embodiments of the invention, tracking the target object based on the target object feature comprises:
controlling the sweeping robot to move according to a preset path, and acquiring a video stream through a camera arranged on the sweeping robot;
performing target identification on the current image frame of the video stream according to the target object characteristics, and judging whether a target object exists in the current image frame;
when the current image frame has the target object, adjusting the position or the posture of the sweeping robot in real time according to the offset of the target object relative to the center of the image;
and when the target object does not exist in the current image frame, controlling the sweeping robot to continuously move according to the preset path and carrying out target analysis on the next image frame until the target object exists in the image frame.
According to some embodiments of the present invention, the target object feature comprises a target torso geometric shape feature, and the performing target recognition on the current image frame of the video stream according to the target object feature to determine whether a target object exists in the current image frame comprises the following steps:
inputting the current image frame into a torso recognition model to recognize whether the current image frame contains a human torso;
when the image frame comprises a human body trunk, determining a first similarity between the geometric morphological characteristics of the human body trunk and the geometric morphological characteristics of the target trunk;
and judging whether a target object exists in the current image frame according to the first similarity.
According to some embodiments of the present invention, the target object feature further comprises a target face feature, and the determining whether the target object exists in the current image frame according to the first similarity comprises:
when the first similarity is smaller than or equal to a first preset similarity, the current image frame has no target object;
when the first similarity is larger than a first preset similarity, adjusting the position or the posture of the sweeping robot to capture a front image of the trunk of the human body, inputting the front image into a face recognition model to obtain a face feature, determining a second similarity between the face feature and the target face feature, when the second similarity is larger than the second preset similarity, a target object exists in the current image frame, otherwise, the target object does not exist in the current image frame.
According to some embodiments of the invention, the determining the torso aspect ratio of the target object from the target tracking image comprises:
performing pixel segmentation operation on the target tracking image to obtain an outer contour data set of the target object, wherein the outer contour data set comprises a plurality of coordinate data;
determining first coordinate data with the smallest abscissa, second coordinate data with the largest abscissa, third coordinate data with the smallest ordinate and fourth coordinate data with the largest ordinate in the outer contour data set;
determining a torso width from the first coordinate data and the second coordinate data;
determining a torso height according to the third coordinate data and the fourth coordinate data;
a torso aspect ratio is determined from the torso width and the torso height.
According to some embodiments of the invention, the object monitoring method based on the sweeping robot further comprises the following steps:
judging whether the target object leaves outdoors or not according to the target tracking image;
and when the target object is determined to leave the outdoor, controlling the sweeping robot to move to the charging seat for charging according to the position of the charging seat.
On the other hand, an embodiment of the present invention further provides an object monitoring system based on a sweeping robot, which is applied to the sweeping robot, and the object monitoring system based on the sweeping robot includes:
the preset module is used for acquiring the characteristics of the target object;
the tracking module is used for tracking a target object based on the target object characteristics and acquiring a target tracking image;
the analysis module is used for determining the trunk aspect ratio of the target object according to the target tracking image;
and the alarm module is used for carrying out state abnormity alarm aiming at the target object when the trunk height-width ratio is greater than a preset height-width ratio.
On the other hand, an embodiment of the present invention further provides an object monitoring device based on a sweeping robot, including:
at least one processor;
at least one memory for storing at least one program;
when the at least one program is executed by the at least one processor, the at least one processor is enabled to implement the object monitoring method based on the sweeping robot as described above.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, where the computer-executable instructions are configured to cause a computer to execute the method for monitoring an object based on a sweeping robot as described above.
The technical scheme of the invention at least has one of the following advantages or beneficial effects: through carrying out the algorithm improvement on the basis of robot of sweeping the floor for the robot of sweeping the floor can also carry out the tracking control to personnel at home except possessing the function of cleaning. The sweeping robot acquires a target tracking image of a target object in real time in the process of tracking the target object, analyzes the target tracking image, determines the trunk aspect ratio of the target object, and performs state abnormity alarm aiming at the target object when the trunk aspect ratio is larger than the preset aspect ratio to indicate that the target object is likely to fall down, so that the robot can find the accident condition of the household old people.
Drawings
Fig. 1 is a flowchart of an object monitoring method based on a sweeping robot according to an embodiment of the present invention;
FIG. 2 is a flowchart of one embodiment of step S120 of FIG. 1;
FIG. 3 is a flowchart of one embodiment of step S320 of FIG. 2;
fig. 4 is a schematic view of an object monitoring device based on a sweeping robot according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or components having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplicity of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, if there are first, second, etc. described, they are only used for distinguishing technical features, but they are not interpreted as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the precedence of the indicated technical features.
The embodiment of the invention provides an object monitoring method based on a sweeping robot, which is applied to the sweeping robot, wherein the sweeping robot is provided with at least one camera and a processor, the processor scans room environments through the camera to construct a room layout three-dimensional space diagram, plans a sweeping path according to the three-dimensional space diagram, and controls the sweeping robot to move according to the sweeping path to finish sweeping rooms.
The sweeping robot is provided with a sweeping mode and a monitoring mode, and in the sweeping mode, the sweeping robot sweeps a room according to a preset sweeping path; in the monitoring mode, the sweeping robot identifies a target object, tracks and shoots the target object within a certain preset range, analyzes whether the target object falls down or not in real time according to the shot image, and gives an alarm when the target object is determined to fall down. The monitoring mode of the sweeping robot is set to be the main line task, the sweeping mode is set to be the branch line task, namely the sweeping robot executes the monitoring mode to monitor the target object by default, when a sweeping instruction is received in the process of executing the monitoring mode, the sweeping mode is executed, and when the sweeping task is completed or a sweeping exit instruction is received in the process of executing the sweeping mode, the monitoring mode is continuously executed.
The sweeping robot is provided with a distance sensor, and in the monitoring mode, the distance sensor detects the distance between the sweeping robot and the target object, so that the sweeping robot and the target object keep a certain distance, for example, the sweeping robot and the target object keep a distance of 1.5 meters for tracking.
The robot of sweeping the floor can adopt infrared camera and visible light camera, and infrared camera is used for assisting the visible light camera at night and shoots, guarantees the definition that the image was shot at night, realizes the all-weather control of the robot of sweeping the floor.
The following describes in detail an object monitoring method based on a sweeping robot according to an embodiment of the present invention, mainly in a monitoring mode of the sweeping robot.
Referring to fig. 1, the object monitoring method based on the sweeping robot according to the embodiment of the present invention includes, but is not limited to, step S110, step S120, step S130, and step S140.
Step S110, target object characteristics are obtained.
In this embodiment, the target object features may include target torso geometric features and target facial features, the target object features are pre-stored by performing initialization setting on the sweeping robot, specifically, after the sweeping robot enters an initialization mode, pictures of multiple target objects in different postures are taken around the target object, a three-dimensional body diagram of the target object is constructed according to the pictures of the multiple target objects, the target torso geometric features are obtained according to the three-dimensional body diagram, further, a facial picture of the target object is taken, and feature extraction is performed on the facial picture to obtain the target facial features. It is to be understood that the three-dimensional body figure may be a three-dimensional body figure when the target object stands, a three-dimensional body figure when the target object sits down, or the like.
And step S120, tracking the target object and acquiring a target tracking image.
In this embodiment, a target object is searched in a room according to pre-stored target object characteristics, and after the target object is searched, the target object is tracked at a certain distance and photographed to acquire a target tracking image including the target object.
Step S130, determining the height-width ratio of the trunk of the target object according to the target tracking image.
Step S140, when the trunk aspect ratio is larger than the preset aspect ratio, a state abnormity alarm is performed for the target object.
In this embodiment, the trunk aspect ratio is used for the ratio of the vertical direction length and the horizontal direction length of sign target object trunk, when the target object stands, the trunk aspect ratio approximately equals the ratio of target object height and width, when the target object lies down, the trunk aspect ratio approximately equals the ratio of target object width and height, therefore, there is obvious difference between the trunk aspect ratio when the target object stands or sits and the trunk aspect ratio when the target object lies down, through setting up preset aspect ratio, and compare the trunk aspect ratio of the target object who arrives with the preset aspect ratio, when the trunk aspect ratio is greater than preset aspect ratio, indicate that the target object probably falls down to the ground, then report to the police.
In this embodiment, since different people have different trunk forms, the preset aspect ratio may be set according to the target object feature of the target object, for example, the height and the shoulder width of the target object are determined according to the target object feature, and the height is divided by the shoulder width and multiplied by a proportionality coefficient smaller than 1 to obtain the preset aspect ratio.
According to some specific embodiments of the present invention, in step S140, the step of performing a state anomaly alarm on the target object includes:
step S210, controlling an alarm module arranged on the sweeping robot to give an alarm in advance;
step S220, whether false alarm information is received or not is monitored in a preset time period, when the false alarm information is received in the preset time period, the alarm module is controlled to stop giving an alarm, and when the false alarm information is not received in the preset time period, alarm information is sent to a related user terminal.
In this embodiment, the floor sweeping robot is provided with an alarm module, and the alarm module can be a voice alarm module or a visual alarm module. And when the processor judges that the state of the target object is abnormal, the alarm module is controlled to alarm. If no accident happens to the target object, false alarm information can be input through a control panel or a remote controller on the sweeping robot. And if the floor sweeping robot receives the false alarm information in a preset time period, the alarm module is controlled to stop giving an alarm. And if the target object is not unexpected and the sweeping robot cannot receive the false alarm information within the preset time period, sending alarm information to the associated user terminal. It can be understood that the floor sweeping robot is preset with a family mobile phone number, and alarm information can be sent to the associated user terminal through the mobile phone number in a dialing or short message mode.
According to some embodiments of the present invention, referring to fig. 2, in step S120, the step of tracking the target object based on the target object feature includes:
step S310, controlling the sweeping robot to move according to a preset path, and collecting video streams through a camera arranged on the sweeping robot;
step S320, carrying out target identification on the current image frame of the video stream according to the target object characteristics, and judging whether the current image frame has a target object;
step S330, when the target object exists in the current image frame, the position or the posture of the sweeping robot is adjusted in real time according to the offset of the target object relative to the center of the image.
Step S340, when the target object does not exist in the current image frame, controlling the sweeping robot to continue to move according to the preset path and perform target analysis on the next image frame until it is determined that the target object exists in the image frame.
In this embodiment, the sweeping robot searches for a target object in a room according to a video stream acquired in real time during a moving process according to a preset path. The video stream collected in the searching process is composed of a plurality of image frames which are continuous in time, the sweeping robot analyzes the image frames in real time, and feature extraction is carried out on the current image frames to determine whether the current image frames have features matched with preset target object features, so that whether the current image frames have the target objects or not is judged. If the target object exists in the current image frame, the target object is locked, and the position or the posture of the sweeping robot is adjusted in real time according to the offset of the target object relative to the center of the image so as to track the target object. If the target object does not exist in the current image frame, the steps S310 to S320 are continuously performed until it is determined that the target object exists in the image frame.
According to some embodiments of the present invention, referring to fig. 3, in step S320, the step of performing target recognition on a current image frame of the video stream according to a feature of a target object, and determining whether the target object exists in the current image frame includes:
step S410, inputting the current image frame into a trunk recognition model to recognize whether the current image frame contains a human trunk or not;
step S420, when the image frame comprises a human body, determining a first similarity between the geometric shape feature of the human body and the geometric shape feature of the target body;
and step S430, judging whether the current image frame has the target object according to the first similarity.
Further, in step S430, the step of determining whether the target object exists in the current image frame according to the first similarity includes:
step S510, when the first similarity is smaller than or equal to a first preset similarity, the current image frame has no target object;
step S520, when the first similarity is larger than a first preset similarity, the position or the posture of the sweeping robot is adjusted to capture a front image of the trunk of the human body, the front image is input into the face recognition model to obtain face features, a second similarity between the face features and the target face features is determined, when the second similarity is larger than the second preset similarity, a target object exists in the current image frame, otherwise, the target object does not exist in the current image frame.
In this embodiment, the robot for cleaning the floor first determines whether the current image frame includes a human trunk through a trunk recognition model, analyzes whether the geometric shape features of the human trunk of the image frame are similar to the geometric shape features of the target trunk of the target object under the condition that the image frame includes the human trunk, and performs face recognition on the object in the current image frame under the condition that whether the geometric shape features of the human trunk of the image frame are similar to the geometric shape features of the target trunk of the target object is determined, so as to determine whether the image frame is the target object. In the embodiment, whether the target object exists in the current image frame is gradually judged in the above mode, so that the fine face recognition operation of each image frame is avoided, and the operation pressure of the processor is reduced under the condition of ensuring the accuracy of target object recognition.
According to some embodiments of the present invention, the step of determining the torso aspect ratio of the target object according to the target tracking image in step S130 includes:
step S610, performing pixel segmentation operation on the target tracking image to obtain an outer contour data set of the target object, wherein the outer contour data set comprises a plurality of coordinate data;
step S620, determining first coordinate data with the minimum abscissa, second coordinate data with the maximum abscissa, third coordinate data with the minimum ordinate and fourth coordinate data with the maximum ordinate in the outer contour data set;
step S630, determining the width of the trunk according to the first coordinate data and the second coordinate data;
step S640, determining the height of the trunk according to the third coordinate data and the fourth coordinate data;
step S650, determining the torso height-to-width ratio according to the torso width and the torso height.
According to some specific embodiments of the present invention, the object monitoring method based on the sweeping robot further includes the following steps:
step S710, judging whether the target object leaves outdoors according to the target tracking image;
step S720, when the target object is determined to be out of the room, the sweeping robot is controlled to move to the charging seat for charging according to the position of the charging seat.
In this embodiment, the sweeping robot is further provided with a charging mode, and in the charging mode, the sweeping robot plans a return charging path according to the current position of the sweeping robot and the position of the charging seat, and moves to the charging seat for charging according to the return charging path. When the sweeping robot triggers a charging signal in the process of executing the monitoring mode, the charging mode is executed.
In this embodiment, the charging signal may be triggered when it is determined that the target object is out of the room or the power supply of the floor sweeping robot is insufficient. In the process of tracking the target object, the sweeping robot determines whether the target object is in a preset range of a calibrated door according to the target tracking image, and if the target object is in the preset range of the calibrated door, determines the walking track of the target object according to a plurality of continuous target tracking images, so as to determine whether the target object goes outdoors.
The embodiment of the invention also provides an object monitoring system based on the sweeping robot, which is applied to the sweeping robot, and the object monitoring system based on the sweeping robot comprises:
the preset module is used for acquiring the characteristics of the target object;
the tracking module is used for tracking the target object based on the target object characteristics and acquiring a target tracking image;
the analysis module is used for determining the trunk aspect ratio of the target object according to the target tracking image;
and the alarm module is used for performing state abnormity alarm aiming at the target object when the trunk height-width ratio is greater than the preset height-width ratio.
It can be understood that, the contents in the embodiment of the object monitoring method based on the sweeping robot are all applicable to the embodiment of the system, the functions specifically implemented by the embodiment of the system are the same as those in the embodiment of the object monitoring method based on the sweeping robot, and the beneficial effects achieved by the embodiment of the object monitoring method based on the sweeping robot are also the same as those achieved by the embodiment of the object monitoring method based on the sweeping robot.
Referring to fig. 4, fig. 4 is a schematic view of an object monitoring apparatus based on a sweeping robot according to an embodiment of the present invention. The object monitoring device based on the sweeping robot in the embodiment of the present invention includes one or more control processors and a memory, and fig. 4 illustrates one control processor and one memory as an example.
The control processor and the memory may be connected by a bus or other means, as exemplified by the bus connection in fig. 4.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs as well as non-transitory computer executable programs. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located from the control processor, and the remote memory may be connected to the robot cleaner-based object monitoring device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
It will be appreciated by those skilled in the art that the arrangement shown in figure 4 does not constitute a limitation of the object monitoring apparatus based on a sweeping robot, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The non-transitory software program and instructions required to implement the sweeping robot-based object monitoring method applied to the sweeping robot-based object monitoring apparatus in the above embodiments are stored in the memory, and when executed by the control processor, the sweeping robot-based object monitoring method applied to the sweeping robot-based object monitoring apparatus in the above embodiments is executed.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and executed by one or more control processors, so as to enable the one or more control processors to execute the object monitoring method based on the sweeping robot in the above method embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as is well known to those skilled in the art.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. The object monitoring method based on the sweeping robot is characterized by being applied to the sweeping robot and comprising the following steps of:
acquiring target object characteristics;
tracking a target object based on the target object characteristics and collecting a target tracking image;
determining the trunk aspect ratio of the target object according to the target tracking image;
and when the trunk aspect ratio is larger than a preset aspect ratio, performing state abnormity alarm on the target object.
2. The object monitoring method based on the sweeping robot as claimed in claim 1, wherein the alarming for the abnormal state of the target object comprises the following steps:
controlling an alarm module arranged on the sweeping robot to give an alarm in advance;
monitoring whether the false alarm information is received or not in a preset time period, controlling the alarm module to stop alarming when the false alarm information is received in the preset time period, and sending alarm information to a related user terminal when the false alarm information is not received in the preset time period.
3. The object monitoring method based on the sweeping robot of claim 1, wherein the tracking of the target object based on the target object characteristics comprises the following steps:
controlling the sweeping robot to move according to a preset path, and acquiring a video stream through a camera arranged on the sweeping robot;
performing target identification on a current image frame of the video stream according to the target object characteristics, and judging whether a target object exists in the current image frame;
when a target object exists in the current image frame, adjusting the position or the posture of the sweeping robot in real time according to the offset of the target object relative to the center of the image;
and when the target object does not exist in the current image frame, controlling the sweeping robot to continuously move according to a preset path and carrying out target analysis on the next image frame until the target object exists in the image frame.
4. The object monitoring method based on the sweeping robot of claim 3, wherein the target object features comprise target torso geometric shape features, and the performing target recognition on the current image frame of the video stream according to the target object features and determining whether a target object exists in the current image frame comprises the following steps:
inputting the current image frame into a torso recognition model to recognize whether the current image frame contains a human torso;
when the image frame comprises a human body trunk, determining a first similarity of the geometric shape feature of the human body trunk and the geometric shape feature of the target trunk;
and judging whether a target object exists in the current image frame or not according to the first similarity.
5. The object monitoring method based on the sweeping robot of claim 4, wherein the target object features further comprise target facial features, and the determining whether the target object exists in the current image frame according to the first similarity comprises the following steps:
when the first similarity is smaller than or equal to a first preset similarity, the current image frame has no target object;
when the first similarity is larger than a first preset similarity, adjusting the position or the posture of the sweeping robot to capture a front image of the trunk of the human body, inputting the front image into a face recognition model to obtain a face feature, determining a second similarity between the face feature and the target face feature, when the second similarity is larger than the second preset similarity, a target object exists in the current image frame, otherwise, the target object does not exist in the current image frame.
6. The object monitoring method based on the sweeping robot of claim 1, wherein the determining the torso aspect ratio of the target object according to the target tracking image comprises the following steps:
performing pixel segmentation operation on the target tracking image to obtain an outer contour data set of the target object, wherein the outer contour data set comprises a plurality of coordinate data;
determining first coordinate data with the minimum abscissa, second coordinate data with the maximum abscissa, third coordinate data with the minimum ordinate and fourth coordinate data with the maximum ordinate in the outer contour data set;
determining a torso width according to the first coordinate data and the second coordinate data;
determining a torso height according to the third coordinate data and the fourth coordinate data;
a torso aspect ratio is determined from the torso width and the torso height.
7. The object monitoring method based on the sweeping robot as claimed in claim 1, further comprising the following steps:
judging whether the target object leaves outdoors or not according to the target tracking image;
and when the target object is determined to leave the outdoor, controlling the sweeping robot to move to the charging seat for charging according to the position of the charging seat.
8. The utility model provides an object monitoring system based on robot of sweeping floor which characterized in that, is applied to the robot of sweeping floor, object monitoring system based on robot of sweeping floor includes:
the preset module is used for acquiring the characteristics of the target object;
the tracking module is used for tracking a target object based on the target object characteristics and acquiring a target tracking image;
the analysis module is used for determining the height-width ratio of the trunk of the target object according to the target tracking image;
and the alarm module is used for performing state abnormity alarm aiming at the target object when the trunk height-width ratio is greater than a preset height-width ratio.
9. The utility model provides an object monitoring device based on robot of sweeping floor which characterized in that includes:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method for object monitoring based on a sweeping robot as claimed in any one of claims 1 to 7.
10. A computer readable storage medium having stored therein a processor executable program for implementing the robot cleaner-based object monitoring of any one of claims 1 to 7 when executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211258942.0A CN115713843A (en) | 2022-10-14 | 2022-10-14 | Object monitoring method, system and device based on sweeping robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211258942.0A CN115713843A (en) | 2022-10-14 | 2022-10-14 | Object monitoring method, system and device based on sweeping robot and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115713843A true CN115713843A (en) | 2023-02-24 |
Family
ID=85231148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211258942.0A Pending CN115713843A (en) | 2022-10-14 | 2022-10-14 | Object monitoring method, system and device based on sweeping robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115713843A (en) |
-
2022
- 2022-10-14 CN CN202211258942.0A patent/CN115713843A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10140832B2 (en) | Systems and methods for behavioral based alarms | |
| US9041800B2 (en) | Confined motion detection for pan-tilt cameras employing motion detection and autonomous motion tracking | |
| CN109607031B (en) | Intelligent warehousing system and method based on unmanned aerial vehicle panorama | |
| Wheeler et al. | Face recognition at a distance system for surveillance applications | |
| US8681223B2 (en) | Video motion detection, analysis and threat detection device and method | |
| US6237647B1 (en) | Automatic refueling station | |
| JP5674307B2 (en) | Subject detection system and subject detection method | |
| JP6155032B2 (en) | Shooting system | |
| EP1499129A1 (en) | Object detection device, object detection server, and object detection method | |
| US20190304272A1 (en) | Video detection and alarm method and apparatus | |
| US20090033745A1 (en) | Method and apparatus for video frame sequence-based object tracking | |
| EP3159859B1 (en) | Human presence detection in a home surveillance system | |
| CN111739248B (en) | Artificial intelligent Internet of things security system and control method | |
| WO2016013719A1 (en) | Device and method for monitoring abnormal behavior using three-dimensional image information | |
| WO2003067884A1 (en) | Method and apparatus for video frame sequence-based object tracking | |
| WO2013137074A1 (en) | System and method for controlling a climate control unit | |
| JP6339445B2 (en) | Person identification device | |
| CN112911156B (en) | Patrol robot and security system based on computer vision | |
| GB2574670A (en) | Method of and system for recognising a human face | |
| KR102128319B1 (en) | Method and Apparatus for Playing Video by Using Pan-Tilt-Zoom Camera | |
| CN209312052U (en) | A kind of carry-on police system of recognition of face | |
| CN104199425B (en) | A kind of reading intelligent agriculture monitoring early-warning system and method | |
| KR20110042554A (en) | Watching system | |
| CN115713843A (en) | Object monitoring method, system and device based on sweeping robot and storage medium | |
| CN112766183A (en) | Alarm system and method for people entering forbidden zone based on AI analysis |
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 |