CN112991368B - Target object detection method and device, storage medium and electronic device - Google Patents
Target object detection method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN112991368B CN112991368B CN202110283068.5A CN202110283068A CN112991368B CN 112991368 B CN112991368 B CN 112991368B CN 202110283068 A CN202110283068 A CN 202110283068A CN 112991368 B CN112991368 B CN 112991368B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- door frame
- line segments
- door
- cloud line
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a target object detection method and device, a storage medium and an electronic device, wherein the method comprises the following steps: performing point cloud scanning on a target object positioned in a target area by a robot to determine different point cloud line segments positioned in different areas on the target object; performing door frame detection on the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames; and under the condition that a plurality of point cloud line segments conforming to preset door characteristics are determined from the door frame candidate set, determining the target object as a door, wherein the preset door characteristics are used for indicating that the point cloud line segments conforming to door conditions correspond to the door. By adopting the technical scheme, the problems that the traditional target detection method cannot accurately detect the position of the door and the like are solved.
Description
[ field of technology ]
The present invention relates to the field of communications, and in particular, to a method and apparatus for detecting a target object, a storage medium, and an electronic apparatus.
[ background Art ]
With the development of technology, devices such as robots based on ranging technologies such as laser and structured light are becoming more and more common, and these devices generally need to partition an established map, so as to facilitate user customization of personalized task policies and task modes.
The map partitioning algorithm in the related art mainly uses an image processing manner. The method is based on the narrower characteristic of the door, and adopts morphological filtering, distance-based algorithm and other methods to divide the region. However, in an actual home scene, furniture such as beds, sofas and the like are often placed, so that a narrow channel area similar to a door appears, and a map partition is not partitioned according to the actual door position, and the partition is inconsistent with an actual house type.
Aiming at the problems that the traditional target detection method cannot accurately detect the position of a door and the like in the related art, no effective solution is proposed at present.
[ invention ]
The invention aims to provide a target object detection method and device, a storage medium and an electronic device, so as to at least solve the problem that the traditional target detection method cannot accurately detect the position of a door.
The invention aims at realizing the following technical scheme:
according to an embodiment of the present invention, there is provided a method for detecting a target object, including: performing point cloud scanning on a target object positioned in a target area by a robot to determine different point cloud line segments positioned in different areas on the target object; performing door frame detection on the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames; and under the condition that a plurality of point cloud line segments conforming to preset door characteristics are determined from the door frame candidate set, determining the target object as a door, wherein the preset door characteristics are used for indicating that the point cloud line segments conforming to door conditions correspond to the door.
In an exemplary embodiment, the method further includes, before performing door frame detection on the different point cloud line segments according to a preset door frame feature and adding the point cloud line segments conforming to the door frame feature to a door frame candidate set: acquiring the type of the door in the target area; and determining the preset door frame characteristics according to the types of the doors, wherein different door frame characteristics correspond to different types of doors.
In an exemplary embodiment, the detecting the door frame according to the preset door frame characteristic, adding the point cloud line segment conforming to the door frame characteristic to the door frame candidate set includes: combining the different point cloud line segments according to a preset rule to obtain a combining point Yun Xianduan; acquiring a line segment included angle in the combined point cloud line segment and a distance between point cloud line segments in the combined point cloud line segment; and matching the included angle of the line segment with the distance according to the preset door frame characteristics to determine a combined point cloud line segment conforming to the preset door frame characteristics, and adding the combined point cloud line segment conforming to the preset door frame characteristics into the door frame candidate set.
In an exemplary embodiment, combining the different point cloud segments according to a preset rule to obtain a combined point cloud segment includes: acquiring a plurality of target point cloud line segments meeting the door frame length indicated by the door frame characteristics from the different point cloud line segments; and combining the target point cloud line segments according to a preset rule to obtain a combined point cloud line segment.
In an exemplary embodiment, after matching the line segment included angle and the distance according to a preset door frame feature to determine a combined point cloud line segment conforming to the preset door frame feature, and adding the combined point cloud line segment conforming to the preset door frame feature to the door frame candidate set, the method further includes: traversing the door frame candidate set, and determining a pair of combined point cloud line segments conforming to the door characteristics from the door frame candidate set, wherein the pair of combined point cloud line segments are used for indicating a pair of unilateral door frames which are correspondingly arranged; a pair of combined point cloud line segments that fit the gate feature is added to a gate candidate set.
In one exemplary embodiment, traversing the set of door frame candidates, determining a pair of combined point cloud line segments from the set of door frame candidates that conform to the door feature, comprises: acquiring a door frame distance and a door frame included angle corresponding to a pair of unilateral door frames indicated by any pair of combined point cloud line segments in the door frame candidate set; and matching the door frame distance and the door frame included angle according to the door characteristics to determine a pair of combined point cloud line segments conforming to the door characteristics.
In one exemplary embodiment, after adding a pair of combined point cloud line segments conforming to the gate feature to a gate candidate set, further comprising: traversing the gate candidate set; and eliminating the pair of combined point cloud line segments or the other pair of combined point cloud line segments from the door candidate set under the condition that the distance between the pair of combined point cloud line segments and the other pair of combined point cloud line segments in the door candidate set is smaller than a preset distance.
In one exemplary embodiment, after the determining that the target object is a door, the method further includes: adding the position of the door to a map constructed by the robot; partitioning the map according to the position of the door.
According to still another embodiment of the present invention, there is provided a detection apparatus for a target object, including: the first determining module is used for carrying out point cloud scanning on a target object positioned in a target area through a robot so as to determine different point cloud line segments positioned in different areas on the target object; the detection module is used for detecting the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames; and the second determining module is used for determining that the target object is a door under the condition that a plurality of point cloud line segments which accord with preset door characteristics are determined from the door frame candidate set, wherein the preset door characteristics are used for indicating that the point cloud line segments which accord with door conditions correspond to the doors.
According to a further embodiment of the present invention, there is provided a computer-readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the method of detecting a target object as described in any of the above at run-time.
According to a further embodiment of the present invention, there is provided an electronic device comprising a memory, in which a computer program is stored, and a processor arranged to run the computer program to perform the method of detecting a target object as described in any of the above.
According to the detection method of the target object, the robot is used for carrying out point cloud scanning on the target object in the target area, so that different point cloud line segments in different areas on the target object are determined, door frame detection is carried out on the different point cloud line segments according to preset door frame characteristics, the point cloud line segments conforming to the door frame characteristics are added into a door frame candidate set, and the target object is determined to be a door under the condition that a plurality of point cloud line segments in the door frame candidate set conform to the preset door characteristics. By adopting the technical scheme, the problems that the traditional target detection method cannot accurately detect the position of the door and the like are solved. And determining that the target object is a door by judging whether a plurality of point cloud line segments of different areas on the target object accord with door characteristics.
[ description of the drawings ]
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a block diagram showing the hardware structure of a computer terminal of a target object detection method according to an embodiment of the present invention;
FIG. 2 is a flow chart (one) of a method of detecting a target object according to an embodiment of the present invention;
FIG. 3 is a schematic view of a door frame (one) of a method for detecting a target object according to an embodiment of the present invention;
FIG. 4 is a schematic view of a door frame (II) of a method for detecting a target object according to an embodiment of the present invention;
FIG. 5 is a flowchart (II) of a method for detecting a target object according to an embodiment of the present invention;
fig. 6 is a block diagram of a target object detection apparatus according to an embodiment of the present invention.
[ detailed description ] of the invention
The invention will be described in detail hereinafter with reference to the drawings in conjunction with embodiments. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided by the embodiments of the present invention may be executed in a computer terminal or similar computing device. Taking a computer terminal as an example, fig. 1 is a block diagram of a hardware structure of a computer terminal of a target object detection method according to an embodiment of the present invention. As shown in fig. 1, the computer terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor (Microprocessor Unit, abbreviated MPU) or a programmable logic device (Programmable logic device, abbreviated PLD)) or the like and a memory 104 for storing data, and optionally, the above-described computer terminal may further include a transmission device 106 for communication functions and an input-output device 108.
The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for detecting a target object in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the computer terminal 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.
The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.
In this embodiment, a method for detecting a target object is provided, and fig. 2 is a flowchart (a) of a method for detecting a target object according to an embodiment of the present invention, as shown in fig. 2, where the flowchart includes the following steps:
step S202, performing point cloud scanning on a target object located in a target area by a robot to determine different point cloud line segments located in different areas on the target object;
step S204, detecting the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames;
step S206, determining that the target object is a door when a plurality of point cloud line segments meeting a preset door characteristic are determined from the door frame candidate set, where the preset door characteristic is used to indicate that the point cloud line segments meeting a door condition correspond to a door.
According to the method, a target object detection method is introduced, point cloud scanning is conducted on target objects in a target area through a robot, so that different point cloud line segments in different areas on the target object are determined, door frame detection is conducted on the different point cloud line segments according to preset door frame characteristics, the point cloud line segments conforming to the door frame characteristics are added into a door frame candidate set, and the target object is determined to be a door under the condition that a plurality of point cloud line segments in the door frame candidate set conform to the preset door characteristics. By adopting the technical scheme, the problems that the traditional target detection method cannot accurately detect the position of the door and the like are solved. And determining that the target object is a door by judging whether a plurality of point cloud line segments of different areas on the target object accord with door characteristics.
It should be noted that, in the process of executing the step S202, in an alternative embodiment, the robot may move in the target area, and the ranging device on the robot transmits a pulse through the transmitter during the operation of the robot, and after the pulse signal is reflected by the target object, the reflected pulse signal is received by the pulse receiver to form the point cloud data. Among them, ranging apparatuses include ranging apparatuses based on the principles of laser light, structured light, TOF (Time of flight), and the like. After the point cloud data is acquired, fitting a point cloud line segment to the continuous points in each frame of point cloud by using a wear-based regression (deming regression), wherein the specific fitting method is as follows: sequential data were collected as seed points and an attempt was made to fit a regression line. If the fitting cannot be performed, removing the initial seed points, adding new data points, retrying the fitting, and if the fitting can be performed, calculating the vertical distance and the regression distance from the next sequential data point to the fitting straight line, and determining whether the regression line is added. If the next sequential data point can be added, the data point is added and the line is re-fitted. If the cloud line cannot be added, judging whether the fitted straight line is Fu Gedian as required by the cloud line segment.
In the executing process of step S204, there are various implementation manners, in an optional embodiment, before performing door frame detection on the different point cloud line segments according to a preset door frame feature and adding the point cloud line segments that conform to the door frame feature into a door frame candidate set, the method further includes: acquiring the type of the door in the target area; and determining the preset door frame characteristics according to the types of the doors, wherein different door frame characteristics correspond to different types of doors.
It should be noted that, in this embodiment, before the door frame detection is performed on different point cloud line segments, the door type in the target area to be detected needs to be obtained first, and the characteristics of the corresponding door frame are obtained according to the door type, where the door frame characteristics at least include one of the following: the length of each line segment in the door frame, the included angle between the line segments and the distance between the line segments. For example: in the method, a door frame is shown in fig. 3 and 4, wherein the door frame is provided with three line segments, the length of the line segment I is 5cm, the length of the line segment II is 5cm, the length of the line segment III is 20cm, the included angle between two adjacent line segments is 5 degrees for the line segment I, the line segment II and the line segment III, the distance between two adjacent line segments is about 2-5mm, and the problem that the error needs to be considered when the door frame in an actual house is manufactured according to the drawing, so that the door frame characteristic is built, the face plate on one door frame is abstracted into the line segments for better building the door frame characteristic, and the face plate is ideally not spaced from and parallel to the face plate, but a certain distance and angle exist due to the existence of the error, so that the included angle between two adjacent line segments is 5 degrees and the distance between two adjacent line segments is about 2-5mm when the door frame characteristic is built is required to be explained; fig. 4 is a schematic view of a door frame (two) according to an embodiment of the present invention, where the door frame in fig. 4 has two line segments, a length of a line segment four is 15cm, a length of a line segment five is 5cm, an included angle between the line segment four and the line segment five is 5 degrees, and a distance between the line segment four and the line segment five is about 2-5mm. It should be noted that the door frame in fig. 3 and fig. 4 is only an example, and in the actual detection process, the door frame features are extracted according to the actual features of the door frame in the area to be detected.
In the executing process of the step S204, optionally, the door frame detection is performed on the different point cloud line segments according to the preset door frame characteristics, and the point cloud line segments conforming to the door frame characteristics are added to the door frame candidate set, which can be implemented by the following technical scheme: combining the different point cloud line segments according to a preset rule to obtain a combining point Yun Xianduan; acquiring a line segment included angle in the combined point cloud line segment and a distance between point cloud line segments in the combined point cloud line segment; and matching the included angle of the line segment with the distance according to the preset door frame characteristics to determine a combined point cloud line segment conforming to the preset door frame characteristics, and adding the combined point cloud line segment conforming to the preset door frame characteristics into the door frame candidate set.
In this embodiment, the different point cloud line segments determined in step S202 need to be combined according to a preset rule, so as to obtain a combined point cloud line segment, determine whether the line segment included angle in the combined point cloud line segment and the distance between the point cloud line segments in the combined point cloud line segment match with a preset door frame feature, and if so, add the combined point cloud line segment that meets the preset door frame feature to the door frame candidate set. For example, if the door frame feature of the door in the area to be detected is shown in fig. 3, different point cloud line segments are combined to obtain combined point cloud line segments, and then whether the different point cloud line segments in the combined point cloud line segments meet the requirement that the included angle between adjacent line segments in the preset feature of the door frame shown in fig. 3 is 5 degrees is determined, and the distance between the adjacent line segments is about 2-5mm. If so, adding the set of eligible combined point cloud line segments to the door frame candidate set.
It should be noted that, in an optional embodiment, in step S204, the combination of the different point cloud segments according to a preset rule to obtain a combined point cloud segment may be implemented by the following technical scheme: acquiring a plurality of target point cloud line segments meeting the door frame length indicated by the door frame characteristics from the different point cloud line segments; and combining the target point cloud line segments according to a preset rule to obtain a combined point cloud line segment.
In this embodiment, a plurality of target point cloud line segments satisfying the door frame length indicated by the door frame feature need to be acquired from different point cloud line segments, for example, in fig. 3, the door frame feature is: the length of the first line segment is 5cm, the length of the second line segment is 5cm, and the length of the third line segment is 20cm. The door frame length indicated by the door frame characteristics is obtained, then a plurality of target point cloud line segments meeting the conditions are determined from different point cloud line segments, and the plurality of target point cloud line segments are combined according to a preset rule to obtain a combined point cloud line segment. It is added that the preset rule may be any combination of different line segments in an alternative embodiment.
It should be noted that, in the above step S204, there are multiple execution manners, optionally, the line segment included angle and the distance are matched according to a preset door frame feature, so as to determine a combined point cloud line segment according to the preset door frame feature, and after adding the combined point cloud line segment according to the preset door frame feature to the door frame candidate set, the method further includes: traversing the door frame candidate set, and determining a pair of combined point cloud line segments conforming to the door characteristics from the door frame candidate set, wherein the pair of combined point cloud line segments are used for indicating a pair of unilateral door frames which are correspondingly arranged; a pair of combined point cloud line segments that fit the gate feature is added to a gate candidate set.
In this embodiment, when it is determined by a preset door frame characteristic that a target object corresponding to a combination point cloud segment is a door frame, the combination point cloud segment is added to a door frame candidate set, then the door frame candidate set is traversed, a pair of combination point cloud segments conforming to the door characteristic is determined from the door frame candidate set according to the door characteristic in the region to be detected, and the pair of combination point cloud segments conforming to the door characteristic is added to the door candidate set. It should be noted that the combined point cloud line segment is used for indicating a single-side door frame which is correspondingly arranged, and the pair of combined point cloud line segments is used for indicating a pair of single-side door frames which are correspondingly arranged, wherein the pair of single-side door frames are combined into one door.
In order to solve the above problem, traversing the door frame candidate set, and determining a pair of combined point cloud line segments conforming to the door characteristics from the door frame candidate set may be implemented by the following technical scheme: acquiring a door frame distance and a door frame included angle corresponding to a pair of unilateral door frames indicated by any pair of combined point cloud line segments in the door frame candidate set; and matching the door frame distance and the door frame included angle according to the door characteristics to determine a pair of combined point cloud line segments conforming to the door characteristics.
In this embodiment, in order to determine a pair of combined point cloud line segments conforming to the door feature from the door frame candidate set, a distance and an included angle between two single-sided door frames corresponding to the door feature need to be obtained, for example, as shown in fig. 3 and 4, two single-sided door frames corresponding to one type of door are obtained, the distance between the two single-sided door frames is 80cm, the included angle is 10 degrees, traversal is performed from the door frame candidate set, whether the door frame distance corresponding to the pair of single-sided door frames indicated by the pair of combined point cloud line segments is equal to 80cm or not is determined, the door frame included angle is equal to 10 degrees, and if so, the pair of combined point cloud line segments is determined to be used for indicating the door.
To determine that a gate corresponding to a pair of combined point cloud line segments within a gate candidate set is not repeated in the gate candidate set, in an optional embodiment, after adding a pair of combined point cloud line segments that conform to the gate feature to the gate candidate set, the method further includes: traversing the gate candidate set; and eliminating the pair of combined point cloud line segments or the other pair of combined point cloud line segments from the door candidate set under the condition that the distance between the pair of combined point cloud line segments and the other pair of combined point cloud line segments in the door candidate set is smaller than a preset distance.
In this embodiment, the doors in one house are not very close to each other in real life, but the doors corresponding to one pair of combined point cloud line segments and the other pair of combined point cloud line segments constructed by the point clouds may be identical, so that the detection needs to be performed on the door candidate set, whether one door is used for two pairs of combined point cloud line segments in the door candidate set is determined by setting a preset distance, and when the door candidate set has the condition that the distance between the pair of combined point cloud line segments and the other pair of combined point cloud line segments is smaller than the preset distance, the doors corresponding to the two pairs of combined point cloud line segments can be identified to be identical, and at this time, the pair of combined point cloud line segments or the other pair of combined point cloud line segments need to be removed from the door candidate set. It should be noted that the preset distance may be 20cm, or other distances, and may be set according to practical situations, where the distance between two pairs of point cloud segments may be a distance between a midpoint of two of a pair of combined point cloud segments and a midpoint of two of another pair of combined point cloud segments.
It should be noted that, in the process of executing the step S206, optionally, after the determining that the target object is a door, the method further includes: adding the position of the door to a map constructed by the robot; partitioning the map according to the position of the door.
In this embodiment, after determining that the target object is a door, all detected door information is added to a map constructed by a robot, and a closed connected domain is found according to the position of the door, where different connected domains are different partitions, and each connected domain can be set to different gray values to be distinguished, so that the partition of the map is completed.
It will be apparent that the embodiments described above are merely some, but not all, embodiments of the invention. In order to better understand the analysis method of the dial test log, the following description will explain the above process with reference to the embodiments, but is not intended to limit the technical solution of the embodiments of the present invention, specifically:
in an alternative embodiment, fig. 5 is a flowchart (ii) of a method for detecting a target object according to an embodiment of the present invention, specifically including the following steps:
step S502: collecting point cloud data;
step S504: fitting point Yun Xianduan;
step S506: detecting a single-side door frame;
step S508: identifying a door;
step S510: and (5) checking a door.
In the executing process of step S502, the robot operates in the area to be detected, the ranging device on the robot transmits a pulse through the transmitter, and after the pulse signal is reflected by the target object, the reflected pulse signal is received by the pulse receiver to form point cloud data. The ranging device comprises a ranging device based on the principles of laser, structured light, TOF and the like.
In the executing process of the step S504, the point cloud data acquired in the step S502 is acquired first, and the continuous points in each frame of point cloud are fitted with the point cloud segments by using the wear-based regression, and the specific fitting method is as follows: and collecting the point clouds which are sequentially arranged as seed points, and trying to fit a regression line. If the fitting cannot be performed, eliminating the initial seed points, adding new data points (point clouds in the point cloud data), retrying the fitting, and if the fitting can be performed, calculating the vertical distance and the regression distance from the next sequential data point to the fitting straight line, and determining whether the regression line is added. If the next sequential data point can be added, the data point is added and the line is re-fitted. If the cloud line cannot be added, judging whether the fitted straight line is Fu Gedian as required by the cloud line segment.
In the executing process of step S506, the characteristics of the preset door frame in the area to be detected need to be obtained, for example, there is a type of door in the area to be detected, two corresponding single sides of the door are shown in fig. 3 and 4, and three line segments are arranged in the door frame in fig. 3, wherein the length of the first line segment is 5cm, the length of the second line segment is 5cm, the length of the third line segment is 20cm, the included angle between two adjacent line segments is 5 degrees, and the distance between two adjacent line segments is about 2-5mm; the door frame of FIG. 4 has two line segments, the length of the line segment four is 15cm, the length of the line segment five is 5cm, the included angle between the line segment four and the line segment five is 5 degrees, and the distance between the line segment four and the line segment five is about 2-5mm. The long line segment and the short line segment (corresponding to the point cloud line segment in the above embodiment) with the preset door frame length in the step S504 are extracted, and any combination of the long line segment and the short line segment may be performed, for example, a combination of three line segments or a combination of one long line segment and one short line segment is adopted, then door frame detection is performed, and if the combined line segment meets the door frame characteristics, the combined line segment (corresponding to the combining point Yun Xianduan in the above embodiment) is added to the single-side door frame candidate set.
In the executing process of the step S508, the single-sided door frame candidate set in the step S506 needs to be traversed, a pair of single-sided door frames meeting the door characteristics is found, and the center point or the end point of the single-sided door frame is respectively used as the start point and the end point of the door and added into the door candidate set. It should be noted that, the door features corresponding to the two single-sided door frames in fig. 3 and 4 include: the distance between two single-side door frames is 80cm, the included angle is 10 degrees, and the single-side door frames are provided with overlapping parts in the vertical direction.
In the executing process of the step S510, it is necessary to screen the gate information in the gate candidate set in the step S508, and if the distance between two gates is detected to be within 20cm, it is considered as a repeated gate, and only one gate information is reserved at this time, and the repeated gates are combined.
After the gate information is detected from the region to be detected through the steps, adding all the detected gate information to a map constructed by the robot, and then searching for a closed connected domain according to the gate information, wherein different connected domains are different partitions, and each connected domain can be set to be different gray values for distinguishing, so that the map partition is completed.
It should be noted that, in an alternative embodiment, the above-mentioned acquisition of the door frame information of the area to be detected may also be obtained by a camera.
In addition, according to the technical scheme provided by the embodiment of the application, the target object can be detected in a prepared manner, the problems that the traditional target detection method cannot accurately detect the position of the door and the like are solved, so that the door information can be accurately identified when the robot constructs a house area, the map partition is more in line with an actual house type, and the phenomenon that the map partition is not in line with the actual house type due to the fact that the narrow channel area similar to the door is formed in an actual household scene because furniture such as a bed and a sofa is placed is avoided.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk, optical disk), comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
In this embodiment, a device for detecting a target object is further provided, and the device for detecting a target object is used to implement the foregoing embodiments and preferred embodiments, which have already been described and will not be described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 6 is a block diagram of a target object detection apparatus according to an alternative embodiment of the present invention, as shown in fig. 6:
a first determining module 62, configured to perform, by using a robot, point cloud scanning on a target object located in a target area, so as to determine different point cloud line segments located in different areas on the target object;
the detection module 64 is configured to detect the different point cloud line segments according to a preset door frame feature, and add a point cloud line segment that meets the door frame feature to a door frame candidate set, where the preset door frame feature is used to indicate that the point cloud line segment that meets a door frame condition corresponds to a door frame;
the second determining module 66 is configured to determine that the target object is a door if a plurality of point cloud line segments that meet a preset door characteristic are determined from the door frame candidate set, where the preset door characteristic is used to indicate that the point cloud line segments that meet a door condition correspond to a door.
According to the invention, a target object detection device is introduced, a robot is used for carrying out point cloud scanning on a target object in a target area, so that different point cloud line segments in different areas on the target object are determined, door frame detection is carried out on the different point cloud line segments according to preset door frame characteristics, the point cloud line segments conforming to the door frame characteristics are added into a door frame candidate set, and the target object is determined to be a door under the condition that a plurality of point cloud line segments in the door frame candidate set conform to the preset door characteristics. By adopting the technical scheme, the problems that the traditional target detection method cannot accurately detect the position of the door and the like are solved. And determining that the target object is a door by judging whether a plurality of point cloud line segments of different areas on the target object accord with door characteristics.
It should be noted that, in an alternative embodiment, the first determining module 62 is configured to perform, by using the robot, a point cloud scan on a target object located in a target area, so as to determine different point cloud line segments located in different areas on the target object. In this embodiment, in the process that the robot moves in the target area, the ranging device on the robot transmits a pulse through the transmitter, and after the pulse signal is reflected by the target object, the reflected pulse signal is received by the pulse receiver, so as to form point cloud data. The ranging device comprises a ranging device based on the principles of laser, structured light, TOF and the like. After the point cloud data are acquired, fitting the continuous points in each frame of point cloud with the point cloud line segments by using the wear-based regression, wherein the specific fitting method is as follows: sequential data were collected as seed points and an attempt was made to fit a regression line. If the fitting cannot be performed, removing the initial seed points, adding new data points, retrying the fitting, and if the fitting can be performed, calculating the vertical distance and the regression distance from the next sequential data point to the fitting straight line, and determining whether the regression line is added. If the next sequential data point can be added, the data point is added and the line is re-fitted. If the cloud line cannot be added, judging whether the fitted straight line is Fu Gedian as required by the cloud line segment.
In an alternative embodiment, the detection module 64 is also used to obtain the type of door within the target area; and determining the preset door frame characteristics according to the types of the doors, wherein different door frame characteristics correspond to different types of doors.
It should be noted that, in this embodiment, before the door frame detection is performed on different point cloud line segments, the door type in the target area to be detected needs to be obtained first, and the characteristics of the corresponding door frame are obtained according to the door type, where the door frame characteristics at least include one of the following: the length of each line segment in the door frame, the included angle between the line segments and the distance between the line segments. For example: in the method, a door frame is shown in fig. 3 and 4, wherein the door frame is provided with three line segments, the length of the line segment I is 5cm, the length of the line segment II is 5cm, the length of the line segment III is 20cm, the included angle between two adjacent line segments is 5 degrees for the line segment I, the line segment II and the line segment III, the distance between two adjacent line segments is about 2-5mm, and the problem that the error needs to be considered when the door frame in an actual house is manufactured according to the drawing, so that the door frame characteristic is built, the face plate on one door frame is abstracted into the line segments for better building the door frame characteristic, and the face plate is ideally not spaced from and parallel to the face plate, but a certain distance and angle exist due to the existence of the error, so that the included angle between two adjacent line segments is 5 degrees and the distance between two adjacent line segments is about 2-5mm when the door frame characteristic is built is required to be explained; fig. 4 is a schematic view of a door frame (two) according to an embodiment of the present invention, where the door frame in fig. 4 has two line segments, a length of a line segment four is 15cm, a length of a line segment five is 5cm, an included angle between the line segment four and the line segment five is 5 degrees, and a distance between the line segment four and the line segment five is about 2-5mm. It should be noted that the door frame in fig. 3 and fig. 4 is only an example, and in the actual detection process, the door frame features are extracted according to the actual features of the door frame in the area to be detected.
Optionally, the detection module 64 is further configured to combine the different point cloud segments according to a preset rule to obtain a combining point Yun Xianduan; acquiring a line segment included angle in the combined point cloud line segment and a distance between point cloud line segments in the combined point cloud line segment; and matching the included angle of the line segment with the distance according to the preset door frame characteristics to determine a combined point cloud line segment conforming to the preset door frame characteristics, and adding the combined point cloud line segment conforming to the preset door frame characteristics into the door frame candidate set.
In this embodiment, the different point cloud line segments determined from the first determining module 62 are required to be combined according to a preset rule, so as to obtain a combined point cloud line segment, determine whether the line segment included angle in the combined point cloud line segment and the distance between the point cloud line segments in the combined point cloud line segment match with a preset door frame feature, and if so, add the combined point cloud line segment conforming to the preset door frame feature to the door frame candidate set. For example, if the door frame feature of the door in the area to be detected is shown in fig. 3, different point cloud line segments are combined to obtain combined point cloud line segments, and then whether the different point cloud line segments in the combined point cloud line segments meet the requirement that the included angle between adjacent line segments in the preset feature of the door frame shown in fig. 3 is 5 degrees is determined, and the distance between the adjacent line segments is about 2-5mm. If so, adding the set of eligible combined point cloud line segments to the door frame candidate set.
It should be noted that, in an alternative embodiment, the detection module 64 is further configured to obtain a plurality of target point cloud line segments from the different point cloud line segments, where the target point cloud line segments satisfy the door frame length indicated by the door frame feature; and combining the target point cloud line segments according to a preset rule to obtain a combined point cloud line segment.
In this embodiment, a plurality of target point cloud line segments satisfying the door frame length indicated by the door frame feature need to be acquired from different point cloud line segments, for example, in fig. 3, the door frame feature is: the length of the first line segment is 5cm, the length of the second line segment is 5cm, and the length of the third line segment is 20cm. The door frame length indicated by the door frame characteristics is obtained, then a plurality of target point cloud line segments meeting the conditions are determined from different point cloud line segments, and the plurality of target point cloud line segments are combined according to a preset rule to obtain a combined point cloud line segment. It is added that the preset rule may be any combination of different line segments in an alternative embodiment.
It should be noted that, optionally, the detection module 64 is further configured to traverse the door frame candidate set, and determine a pair of combined point cloud line segments conforming to the door feature from the door frame candidate set, where the pair of combined point cloud line segments is used to indicate a pair of single-side door frames that are correspondingly set; a pair of combined point cloud line segments that fit the gate feature is added to a gate candidate set.
In this embodiment, when it is determined by a preset door frame characteristic that a target object corresponding to a combination point cloud segment is a door frame, the combination point cloud segment is added to a door frame candidate set, then the door frame candidate set is traversed, a pair of combination point cloud segments conforming to the door characteristic is determined from the door frame candidate set according to the door characteristic in the region to be detected, and the pair of combination point cloud segments conforming to the door characteristic is added to the door candidate set. It should be noted that the combined point cloud line segment is used for indicating a single-side door frame which is correspondingly arranged, and the pair of combined point cloud line segments is used for indicating a pair of single-side door frames which are correspondingly arranged, wherein the pair of single-side door frames are combined into one door.
To solve the above problem, in an alternative embodiment, the second determining module 66 is further configured to obtain a door frame distance and a door frame included angle corresponding to a pair of single-sided door frames indicated by any pair of combined point cloud line segments in the door frame candidate set; and matching the door frame distance and the door frame included angle according to the door characteristics to determine a pair of combined point cloud line segments conforming to the door characteristics.
In this embodiment, in order to determine a pair of combined point cloud line segments conforming to the door feature from the door frame candidate set, a distance and an included angle between two single-sided door frames corresponding to the door feature need to be obtained, for example, as shown in fig. 3 and 4, two single-sided door frames corresponding to one type of door are obtained, the distance between the two single-sided door frames is 80cm, the included angle is 10 degrees, traversal is performed from the door frame candidate set, whether the door frame distance corresponding to the pair of single-sided door frames indicated by the pair of combined point cloud line segments is equal to 80cm or not is determined, the door frame included angle is equal to 10 degrees, and if so, the pair of combined point cloud line segments is determined to be used for indicating the door.
In an alternative embodiment, the second determination module 66 is further configured to traverse the set of gate candidates; and eliminating the pair of combined point cloud line segments or the other pair of combined point cloud line segments from the door candidate set under the condition that the distance between the pair of combined point cloud line segments and the other pair of combined point cloud line segments in the door candidate set is smaller than a preset distance.
In this embodiment, the doors in one house are not very close to each other in real life, but the doors corresponding to one pair of combined point cloud line segments and the other pair of combined point cloud line segments constructed by the point clouds may be identical, so that the detection needs to be performed on the door candidate set, whether one door is used for two pairs of combined point cloud line segments in the door candidate set is determined by setting a preset distance, and when the door candidate set has the condition that the distance between the pair of combined point cloud line segments and the other pair of combined point cloud line segments is smaller than the preset distance, the doors corresponding to the two pairs of combined point cloud line segments can be identified to be identical, and at this time, the pair of combined point cloud line segments or the other pair of combined point cloud line segments need to be removed from the door candidate set. It should be noted that the preset distance may be 20cm, or other distances, and may be set according to practical situations, where the distance between two pairs of point cloud segments may be a distance between a midpoint of two of the pair of combined point cloud segments and a midpoint of two of the other pair of combined point cloud segments.
It should be noted that, optionally, the second determining module 66 is further configured to add the position of the door to the map constructed by the robot; partitioning the map according to the position of the door.
In this embodiment, after determining that the target object is a door, all detected door information is added to a map constructed by a robot, and a closed connected domain is found according to the position of the door, where different connected domains are different partitions, and each connected domain can be set to different gray values to be distinguished, so that the partition of the map is completed.
It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.
Embodiments of the present invention also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
Alternatively, in the present embodiment, the above-described storage medium may be configured to store a computer program for performing the steps of:
S1, performing point cloud scanning on a target object located in a target area by a robot to determine different point cloud line segments located in different areas on the target object;
s2, detecting the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames;
and S3, under the condition that a plurality of point cloud line segments meeting the preset door characteristics are determined from the door frame candidate set, determining the target object as a door, wherein the preset door characteristics are used for indicating that the point cloud line segments meeting the door conditions correspond to the door.
Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a usb disk, a ROM, a RAM, a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.
An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
Alternatively, in the present embodiment, the above-described processor may be configured to execute the following steps by a computer program:
s1, performing point cloud scanning on a target object located in a target area by a robot to determine different point cloud line segments located in different areas on the target object;
s2, detecting the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames;
and S3, under the condition that a plurality of point cloud line segments meeting the preset door characteristics are determined from the door frame candidate set, determining the target object as a door, wherein the preset door characteristics are used for indicating that the point cloud line segments meeting the door conditions correspond to the door.
Alternatively, specific examples in this embodiment may refer to examples described in the foregoing embodiments and optional implementations, and this embodiment is not described herein.
Embodiments of the present invention also provide a robot comprising a body, a motion assembly and a controller arranged to perform the steps of any of the method embodiments described above.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may alternatively be implemented in program code executable by computing devices, so that they may be stored in a memory device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of detecting a target object, the method comprising:
performing point cloud scanning on a target object positioned in a target area by a robot to determine different point cloud line segments positioned in different areas on the target object;
performing door frame detection on the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames;
under the condition that a plurality of point cloud line segments conforming to preset door characteristics are determined from the door frame candidate set, determining the target object as a door, wherein the preset door characteristics are used for indicating that the point cloud line segments conforming to door conditions correspond to the door;
the method for detecting the door frame comprises the steps of detecting the door frame of different point cloud line segments according to preset door frame characteristics, adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, and comprises the following steps: combining the different point cloud line segments according to a preset rule to obtain a combining point Yun Xianduan; acquiring a line segment included angle in the combined point cloud line segment and a distance between point cloud line segments in the combined point cloud line segment; and matching the included angle of the line segment with the distance according to the preset door frame characteristics to determine a combined point cloud line segment conforming to the preset door frame characteristics, and adding the combined point cloud line segment conforming to the preset door frame characteristics into the door frame candidate set.
2. The method according to claim 1, characterized in that: performing door frame detection on the different point cloud line segments according to preset door frame characteristics, and before adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, the method further comprises:
acquiring the type of the door in the target area;
and determining the preset door frame characteristics according to the types of the doors, wherein different door frame characteristics correspond to different types of doors.
3. The method according to claim 1, characterized in that: combining the different point cloud line segments according to a preset rule to obtain a combined point cloud line segment, which comprises the following steps:
acquiring a plurality of target point cloud line segments meeting the door frame length indicated by the door frame characteristics from the different point cloud line segments;
and combining the target point cloud line segments according to a preset rule to obtain a combined point cloud line segment.
4. The method according to claim 1, characterized in that: matching the line segment included angle with the distance according to a preset door frame characteristic to determine a combined point cloud line segment conforming to the preset door frame characteristic, and adding the combined point cloud line segment conforming to the preset door frame characteristic to the door frame candidate set, wherein the method further comprises:
Traversing the door frame candidate set, and determining a pair of combined point cloud line segments conforming to the door characteristics from the door frame candidate set, wherein the pair of combined point cloud line segments are used for indicating a pair of unilateral door frames which are correspondingly arranged;
a pair of combined point cloud line segments that fit the gate feature is added to a gate candidate set.
5. The method according to claim 4, wherein: traversing the door frame candidate set, determining a pair of combined point cloud line segments from the door frame candidate set that conform to the door feature, comprising:
acquiring a door frame distance and a door frame included angle corresponding to a pair of unilateral door frames indicated by any pair of combined point cloud line segments in the door frame candidate set;
and matching the door frame distance and the door frame included angle according to the door characteristics to determine a pair of combined point cloud line segments conforming to the door characteristics.
6. The method according to claim 4, wherein: after adding a pair of combined point cloud line segments conforming to the gate feature to a gate candidate set, further comprising:
traversing the gate candidate set;
and eliminating the pair of combined point cloud line segments or the other pair of combined point cloud line segments from the door candidate set under the condition that the distance between the pair of combined point cloud line segments and the other pair of combined point cloud line segments in the door candidate set is smaller than a preset distance.
7. The method according to claim 1, characterized in that: after the determining that the target object is a door, the method further includes:
adding the position of the door to a map constructed by the robot;
partitioning the map according to the position of the door.
8. A target object detection apparatus, characterized by comprising:
the first determining module is used for carrying out point cloud scanning on a target object positioned in a target area through a robot so as to determine different point cloud line segments positioned in different areas on the target object;
the detection module is used for detecting the different point cloud line segments according to preset door frame characteristics, and adding the point cloud line segments conforming to the door frame characteristics into a door frame candidate set, wherein the preset door frame characteristics are used for indicating that the point cloud line segments conforming to door frame conditions correspond to door frames;
the second determining module is used for determining that the target object is a door under the condition that a plurality of point cloud line segments which accord with preset door characteristics are determined from the door frame candidate set, wherein the preset door characteristics are used for indicating that the point cloud line segments which accord with door conditions correspond to the doors;
the detection module is further configured to combine the different point cloud line segments according to a preset rule to obtain a combining point Yun Xianduan; acquiring a line segment included angle in the combined point cloud line segment and a distance between point cloud line segments in the combined point cloud line segment; and matching the included angle of the line segment with the distance according to the preset door frame characteristics to determine a combined point cloud line segment conforming to the preset door frame characteristics, and adding the combined point cloud line segment conforming to the preset door frame characteristics into the door frame candidate set.
9. A computer-readable storage medium, characterized in that the storage medium has stored therein a computer program, wherein the computer program is arranged to execute the method of any of the claims 1 to 7 when run.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the method of any of the claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110283068.5A CN112991368B (en) | 2021-03-16 | 2021-03-16 | Target object detection method and device, storage medium and electronic device |
| PCT/CN2021/116189 WO2022193566A1 (en) | 2021-03-16 | 2021-09-02 | Method and apparatus for detecting target object, and storage medium and electronic apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110283068.5A CN112991368B (en) | 2021-03-16 | 2021-03-16 | Target object detection method and device, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112991368A CN112991368A (en) | 2021-06-18 |
| CN112991368B true CN112991368B (en) | 2023-08-15 |
Family
ID=76332624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110283068.5A Active CN112991368B (en) | 2021-03-16 | 2021-03-16 | Target object detection method and device, storage medium and electronic device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112991368B (en) |
| WO (1) | WO2022193566A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991368B (en) * | 2021-03-16 | 2023-08-15 | 追觅创新科技(苏州)有限公司 | Target object detection method and device, storage medium and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411778A (en) * | 2011-07-28 | 2012-04-11 | 武汉大学 | Automatic registration method of airborne laser point cloud and aerial image |
| CN106504288A (en) * | 2016-10-24 | 2017-03-15 | 北京进化者机器人科技有限公司 | A kind of domestic environment Xiamen localization method based on binocular vision target detection |
| CN108280852A (en) * | 2018-01-16 | 2018-07-13 | 常景测量科技（武汉）有限公司 | A kind of door and window point cloud shape detecting method and system based on laser point cloud data |
| CN109998421A (en) * | 2018-01-05 | 2019-07-12 | 艾罗伯特公司 | Mobile clean robot combination and persistence drawing |
| CN109998429A (en) * | 2018-01-05 | 2019-07-12 | 艾罗伯特公司 | Mobile clean robot artificial intelligence for context aware |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10078790B2 (en) * | 2017-02-16 | 2018-09-18 | Honda Motor Co., Ltd. | Systems for generating parking maps and methods thereof |
| CN111813882B (en) * | 2020-06-18 | 2024-05-14 | 浙江华睿科技股份有限公司 | Robot map construction method, device and storage medium |
| CN111897334B (en) * | 2020-08-02 | 2022-06-14 | 珠海一微半导体股份有限公司 | Robot region division method based on boundary, chip and robot |
| CN112991368B (en) * | 2021-03-16 | 2023-08-15 | 追觅创新科技(苏州)有限公司 | Target object detection method and device, storage medium and electronic device |
-
2021
- 2021-03-16 CN CN202110283068.5A patent/CN112991368B/en active Active
- 2021-09-02 WO PCT/CN2021/116189 patent/WO2022193566A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102411778A (en) * | 2011-07-28 | 2012-04-11 | 武汉大学 | Automatic registration method of airborne laser point cloud and aerial image |
| CN106504288A (en) * | 2016-10-24 | 2017-03-15 | 北京进化者机器人科技有限公司 | A kind of domestic environment Xiamen localization method based on binocular vision target detection |
| CN109998421A (en) * | 2018-01-05 | 2019-07-12 | 艾罗伯特公司 | Mobile clean robot combination and persistence drawing |
| CN109998429A (en) * | 2018-01-05 | 2019-07-12 | 艾罗伯特公司 | Mobile clean robot artificial intelligence for context aware |
| CN108280852A (en) * | 2018-01-16 | 2018-07-13 | 常景测量科技（武汉）有限公司 | A kind of door and window point cloud shape detecting method and system based on laser point cloud data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112991368A (en) | 2021-06-18 |
| WO2022193566A1 (en) | 2022-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE602004008555T2 (en) | Method for the proximity determination of the devices in a wireless network | |
| AT511881B1 (en) | METHOD AND SYSTEM FOR LOCATING A COMMUNICATION DEVICE | |
| CA3139773A1 (en) | Determining motion zones in a space traversed by wireless signals | |
| CA3139775A1 (en) | Determining a confidence for a motion zone identified as a location of motion for motion detected by wireless signals | |
| CN114072692A (en) | Determining a location of motion detected from a wireless signal based on a wireless link count | |
| CN105282758A (en) | Self-adaptive dynamic construction method of WIFI indoor positioning system fingerprint database | |
| CA3139774A1 (en) | Determining a motion zone for a location of motion detected by wireless signals | |
| CN107994960A (en) | A kind of indoor activity detection method and system | |
| CN106156055A (en) | The identification of search engine reptile, processing method and processing device | |
| CN112991368B (en) | Target object detection method and device, storage medium and electronic device | |
| KR20180071294A (en) | Router address type identification method and apparatus | |
| CN112631282A (en) | Intelligent path planning method, device, system and medium for sweeping robot | |
| CN112102370A (en) | Target tracking method and device, storage medium and electronic device | |
| CN112842180A (en) | Sweeping robot, distance measurement and obstacle avoidance method and device thereof, and readable storage medium | |
| CN113780233B (en) | Aisle area identification method and device | |
| CN106060862A (en) | Positioning reference data acquiring and updating method and system | |
| CN114036314B (en) | Knowledge-graph-based permeation path identification method and system | |
| US11895559B2 (en) | Moving means determination device | |
| KR101940802B1 (en) | System for calculating the number of the local triangular using the terminal resources and method thereof | |
| CN111429791A (en) | Identity determination method, identity determination device, storage medium and electronic device | |
| DE112015003512T5 (en) | Two-pass acquisition technique for pulse distance measurements without echoes | |
| CN117332734B (en) | Singlechip design system integrating multiple communication modes | |
| CN114710228B (en) | Time synchronization method and device, storage medium and electronic device | |
| CN109788431B (en) | Bluetooth positioning method, device, equipment and system based on adjacent node group | |
| CN113132292B (en) | Dynamic monitoring method and system for botnet control channel |
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 | ||
| CB02 | Change of applicant information |
Address after: 215000 E3, building 16, No. 2288, Wuzhong Avenue, Yuexi, Wuzhong District, Suzhou City, Jiangsu Province Applicant after: Pursuit innovation technology (Suzhou) Co.,Ltd. Address before: 215104 E3, building 16, No. 2288, Wuzhong Avenue, Yuexi, Wuzhong District, Suzhou City, Jiangsu Province Applicant before: ZHUICHUANG TECHNOLOGY (SUZHOU) Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |