WO2025146201A1 - 对象寻找方法、自移动设备、计算机存储介质、电子设备 - Google Patents
对象寻找方法、自移动设备、计算机存储介质、电子设备Info
- Publication number
- WO2025146201A1 WO2025146201A1 PCT/CN2025/070790 CN2025070790W WO2025146201A1 WO 2025146201 A1 WO2025146201 A1 WO 2025146201A1 CN 2025070790 W CN2025070790 W CN 2025070790W WO 2025146201 A1 WO2025146201 A1 WO 2025146201A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- area
- search
- initial
- found
- target object
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/24—Floor-sweeping machines, motor-driven
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
- A47L11/4091—Storing or parking devices, arrangements therefor; Means allowing transport of the machine when it is not being used
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
- A47L2201/02—Docking stations; Docking operations
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
- A47L2201/04—Automatic control of the travelling movement; Automatic obstacle detection
Definitions
- the present disclosure relates to the field of smart home technology, and in particular to an object search method, a self-mobile device, a computer storage medium, and an electronic device.
- some self-moving devices have the function of automatically returning to the charging pile.
- the self-moving device can only find the charging pile based on the signal sent by the charging pile. Once the signal cannot be received, the above-mentioned automatic return to the charging pile function cannot be realized.
- the purpose of the present disclosure is to provide an object search method, a mobile device, a computer storage medium and an electronic device, thereby overcoming the technical problem of only being able to search for objects capable of sending signals due to the limitations of related technologies, at least to a certain extent.
- an object search method which is applied to a self-mobile device, wherein the self-mobile device is provided with an image acquisition device, and the method comprises:
- the image capture device After receiving the object search instruction, the image capture device captures the view image of the mobile device during movement; the object search instruction includes feature description information of the target object to be found;
- the target object is detected in the viewfinder image according to the feature description information, an object detection result is obtained, and an object search result for the target object is determined based on the object detection result.
- capturing the view image of the self-moving device during the movement by the image acquisition device includes:
- the image acquisition device is used to acquire an initial framing image of the self-moving device during its movement in the initial sub-area to be found.
- determining an initial sub-area to be found from the current scene includes:
- a circular area with the initial position as the center and a preset distance as the radius is determined as the initial sub-area to be found.
- determining an initial sub-area to be found from the current scene includes:
- the search priority corresponding to the key search area is higher than other areas in the current scene, and the search priority is used to represent the order in which the mobile device searches for the target object in different areas of the current scene;
- determining the initial sub-area to be searched in the key search area includes:
- a circular area with the initial position as the center and a preset distance as the radius is determined as the initial sub-area to be found.
- the step of acquiring, by the image acquisition device, an initial framing image of the mobile device during its movement within the initial sub-area to be found includes:
- the image acquisition device is used to acquire an initial framing image of the self-moving device during its rotation in the initial sub-area to be found.
- determining a key search area from the current scene includes:
- the designated search area is determined as the key search area.
- the method further includes:
- the historical search record is used to store the mapping relationship between the feature description information of the historical search object and its search result, and the search result includes the historical appearance area of the historical search object.
- the method after moving from the current position to the key search area, the method further includes:
- the acquisition frequency of the image acquisition device is controlled to increase from a first frequency to a second frequency.
- the method further includes:
- the initial sub-region to be found is marked as an initial found sub-region.
- detecting whether the target object is included in the viewfinder image according to the feature description information to obtain an object detection result includes:
- the target object is detected according to the feature description information to obtain an initial object detection result.
- determining an object search result for the target object based on the object detection result includes:
- the initial object detection result indicates that the target object is included in the initial viewfinder image, marking the initial searched sub-region as the appearance region of the target object in a pre-created scene map;
- the marked appearance area and/or the initial view image are output as an object search result for the target object.
- the method further includes:
- the marked appearance area and/or the re-shot initial view image are determined as an object search result for the target object.
- determining an object search result for the target object based on the object detection result includes:
- the initial object detection result indicates that the target object is not included in the initial view image, determining a next sub-region to be searched;
- An object search result for the target object is determined based on the next object detection result.
- determining the next sub-area to be found includes:
- the preset sub-region determination strategy determine the next sub-region to be found
- the preset sub-region determination strategy includes: the distance between the center position of the next sub-region to be found and the initial position is less than a preset distance threshold, and the overlapping area between the next sub-region to be found and the initial found sub-region is less than a preset area threshold.
- the method further includes:
- the method further includes:
- a control signal sent by a remote control device of the mobile device
- the remote control device includes a Bluetooth remote control device, an infrared remote control device and a radio frequency remote control device.
- the target object includes one or more objects
- the types of any two objects in the multiple objects are the same or different.
- a self-moving device wherein the self-moving device is provided with an image acquisition device, and the self-moving device comprises:
- the object search module is used to detect whether the viewfinder image contains the target object according to the feature description information, obtain an object detection result, and determine an object search result for the target object based on the object detection result.
- a computer storage medium on which a computer program is stored.
- the object searching method described in the first aspect is implemented.
- an electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the object searching method described in the first aspect above by executing the executable instructions.
- a framing image of the mobile device during movement is captured by an image capture device, and whether the framing image includes the target object is detected according to the feature description information to obtain an object detection result, and an object search result for the target object is determined based on the object detection result.
- the object search result can be quickly output by capturing images and performing image detection based on the feature description information, which not only avoids the time-consuming and labor costs caused by manual search for the target object and reduces the burden of manual search, but also can accurately identify the target object with the help of the feature description information, reduces the possibility of misidentification, and improves the accuracy of the object search result.
- FIG1 is a schematic diagram showing a flow chart of an object search method in an embodiment of the present disclosure
- FIG2 is a schematic diagram showing a flow chart of how to capture a framing image from a mobile device during movement by an image capture device in an embodiment of the present disclosure
- FIG3 is a schematic diagram showing how to determine an initial sub-region to be searched in an embodiment of the present disclosure
- FIG4 is a schematic diagram showing a flow chart of how to determine a key search area in an embodiment of the present disclosure
- FIG5 is a flow chart showing how to determine an object search result based on the initial object detection result when the initial object detection result indicates that the target object is included in the initial view image in an embodiment of the present disclosure
- FIG6 is a flow chart showing how to determine an object search result based on the initial object detection result when the initial object detection result indicates that the target object is not included in the initial view image in an embodiment of the present disclosure
- FIG7 is a schematic diagram showing how to determine the next sub-area to be found in an embodiment of the present disclosure
- FIG8 is a schematic diagram showing a flow chart of how a mobile device moves to a next sub-area to be found in an embodiment of the present disclosure
- FIG9 is a schematic diagram showing the structure of a self-moving device in an exemplary embodiment of the present disclosure.
- FIG. 10 is a schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure.
- the above scheme has at least the following defects: the method of searching for objects is single, and the target object must be able to send out a signal or provide an identification mark before it can be searched based on the signal. It is too dependent on the pile signal and has great limitations.
- an object searching method is provided, which at least to some extent overcomes the defect in the related art that only objects capable of emitting signals can be searched.
- FIG1 is a schematic flow chart of an object search method according to an embodiment of the present disclosure.
- the object search method may be executed by a mobile device.
- an object search method includes the following steps:
- Step S110 after receiving the object search instruction, the image capture device captures the view image of the mobile device during the movement; the object search instruction includes feature description information of the target object to be found;
- Step S120 detecting whether the viewfinder image contains a target object according to the feature description information, obtaining an object detection result, and determining an object search result for the target object based on the object detection result.
- the object search instruction includes feature description information of the target object to be found
- a framing image of the mobile device during movement is captured by an image capture device, and whether the framing image includes the target object is detected according to the feature description information to obtain an object detection result, and an object search result for the target object is determined based on the object detection result.
- the limitation of the related technology that only objects with signal transmission capabilities can be identified is overcome, the types and ranges of target objects that can be searched are expanded, and the coverage of the search is improved; on the other hand, the object search result can be quickly output by capturing images and performing image detection based on the feature description information, which not only avoids the time-consuming and labor costs caused by manual search for target objects and reduces the burden of manual search, but also can accurately identify the target object with the help of feature description information, reduces the possibility of misidentification, and improves the accuracy of the object search result.
- the self-moving device e.g., sweeping robot
- the function of the image acquisition device is to acquire images or videos.
- the image acquisition device may be an RGB camera, which is a sensor that recognizes and measures the color and brightness of the surface of an object by taking images of multiple colors at high speed. RGB refers to the three colors of red, green, and blue. The increase and decrease of these three colors constitute a variety of colors, so the RGB camera can capture very rich color images and videos.
- a user can control a mobile device to search for a specified target object by issuing an object search instruction.
- the above-mentioned target object can be one or more objects (for example: charging pile, pet, stool, coin, remote control, etc.).
- the types of any two objects in the multiple objects are the same or different, for example: charging pile and pet, pet A (kitten) and pet B (puppy). It can be set according to actual conditions, and the present disclosure does not make any special limitations on this.
- the above-mentioned object search instruction may include feature description information of the target object to be found.
- the feature description information may be the name, shape, size, color, high-frequency placement position, etc. of the target object, or may be a picture of the target object, etc., which may be set according to actual conditions, and the present disclosure does not specifically limit this. Given that the feature description information can be flexibly customized, the present disclosure can adapt to the needs of different targets and scenarios, making the solution have a wide range of application prospects.
- the object search instruction may include the following forms:
- Control instructions issued by the application of the mobile device that is, the user can install the application of the mobile device through the Internet or other smart devices. Through the operation interface of the application, the user can input text, pictures, etc. to generate the above control instructions;
- a control signal sent by a remote control device of the mobile device wherein the remote control device may be a Bluetooth remote control device, an infrared remote control device, a radio frequency remote control device, etc., which may be set according to actual conditions, and the present disclosure does not make any special limitation on this.
- the mobile device may receive the object search instruction, and then step S110 may be executed.
- step S110 after receiving the object search instruction, the image acquisition device acquires the view image of the mobile device during the movement.
- the mobile device may use the image acquisition device to acquire the view image of the mobile device during its movement.
- FIG. 2 shows a schematic flow chart of how to collect a framing image from a mobile device during movement by an image acquisition device in an embodiment of the present disclosure, including steps S201 to S202:
- step S201 an initial sub-region to be found is determined from the current scene.
- the self-mobile device can directly determine its own initial position in the current scene (which can be the real-time position of the self-mobile device at the moment of receiving the object search instruction, for example: position A), and then use the initial position as the object search starting point to start searching for the target object.
- the self-mobile device can use the initial position as the object search starting point, and can determine a circular area with the initial position as the center and a preset distance as the radius as an initial sub-area to be found, and start searching for the target object in the initial sub-area to be found.
- the above-mentioned preset distance length (exemplarily, it can be represented by r) can be determined according to the shooting range or coverable area range of the above-mentioned RGB camera.
- the preset distance length r can be any value within the numerical range of 50cm-130cm, and can be set according to actual conditions. The present disclosure does not make any special limitation on this.
- Figure 3 shows a schematic diagram of how to determine the initial sub-area to be found in an embodiment of the present disclosure.
- the shaded circle in the figure indicates the initial position of the mobile device, and the circular area containing the shaded circle is the above-mentioned initial sub-area to be found.
- a key search area may be first determined from the current scene, and then the current position may be moved into the key search area to determine an initial sub-area to be searched in the key search area.
- the above-mentioned key search area is the area or range where the target object is most likely to be found.
- the self-mobile device can be guided to quickly find the target object, saving search time and improving the efficiency of object search.
- the present disclosure can set the search priority corresponding to the key search area to be higher, while the search priority corresponding to the non-key search area is lower, so that the self-mobile device can preferentially search for the above-mentioned target object from the key search area. If the above-mentioned target object is not found from the key search area, it can go to other non-key search areas to continue searching or terminate the task, and directly generate the object search result.
- FIG. 4 shows a schematic flow chart of how to determine a key search area in an embodiment of the present disclosure, including steps S401 to S403:
- step S401 it is detected whether the object search instruction includes a designated search area for the target object.
- the mobile device may detect whether the object search instruction contains a designated search area for the target object.
- the designated search area may be an area where the target object is often placed or appears.
- step S402 if the object search instruction includes a designated search area, the designated search area is determined as a key search area.
- the mobile device can directly determine the designated search area as the key search area.
- step S403 if the object search instruction does not include a designated search area, the historical search record is retrieved according to the feature description information to obtain the historical appearance area of the target object, and the historical appearance area is determined as the key search area.
- the mobile device can retrieve the historical search record according to the feature description information included in the object search instruction to obtain the historical appearance area of the target object.
- the above-mentioned historical search records can be used to store the mapping relationship between the feature description information of the historical search object and its search results.
- the search results can include the historical appearance area of the historical search object, and the historical appearance area is the location area where the target object has appeared in the past or was often placed in the past.
- the self-mobile device can also count the number of appearances corresponding to each historical appearance area, and then determine the search priority of the above multiple historical appearance areas according to the number of appearances, so as to determine which historical appearance area to search for the above target object first according to the search priority, thereby improving the object search efficiency.
- the self-mobile device After determining the key search area, the self-mobile device can move from the current position into the key search area, and then the self-mobile device can determine its initial position in the key search area (for example: position B). Then, referring to the relevant description of the above step S201, the self-mobile device can use the initial position as the starting point for object search. Specifically, a circular area with the initial position as the center and a preset distance as the radius can be determined as the initial sub-area to be searched, and the search for the target object can be started in the initial sub-area to be searched.
- the acquisition frequency of the image acquisition device can be controlled to increase from the first frequency to the second frequency, or the image resolution of the image acquisition device can be controlled to increase from the first resolution to the second resolution, or the self-moving device can also automatically adjust the number of traversals of each sub-area to be searched to two or more times, so as to focus on searching for the above-mentioned target object in the key search area.
- the specific implementation method can be set according to actual conditions, and the present disclosure does not make any special limitations on this.
- step S202 an initial framing image of the mobile device during its movement in the initial sub-region to be found is captured by an image capture device.
- the self-mobile device can rotate a preset angle (the preset angle can be 360 degrees) in the initial sub-area to be found with the initial position (i.e., position A in the current scene or position B in the key search area) as the rotation center, and capture the initial framing image of the self-mobile device during the rotation process in the initial sub-area to be found through the image acquisition device.
- the preset angle can be 360 degrees
- the mobile device After the image acquisition device captures the initial framing image of the mobile device during its rotation in the initial sub-region to be found, the mobile device can mark the initial sub-region to be found as the initial found sub-region. Based on this, the time-consuming search problem caused by repeated search of a certain sub-region can be avoided.
- step S120 After the initial framing image is obtained, the process proceeds to step S120 to detect whether the framing image contains a target object according to the feature description information, obtain an object detection result, and determine an object search result for the target object based on the object detection result.
- the self-mobile device can detect whether the initial view image contains the target object based on the feature description information contained in the object search instruction to obtain an initial object detection result.
- a trained object recognition model can be pre-deployed in the self-mobile device, and features of the initial view image can be extracted based on the object recognition model. Then, the extracted features can be classified or matched to output an initial object detection result, which can indicate whether the initial view image contains the target object.
- an object search result for the target object may be determined based on the initial object detection result.
- the object search result for the target object can be determined by referring to the processing flow shown in Figure 5; and for the case where the above-mentioned initial object detection result represents that the initial framed image does not contain the above-mentioned target object, the object search result for the target object can be determined by referring to the processing flow shown in Figure 6.
- FIG. 5 shows a flowchart of how to determine an object search result based on the initial object detection result when the initial object detection result indicates that the target object is included in the initial view image in the embodiment of the present disclosure, including steps S501-S502:
- step S501 the initially searched sub-region is marked as the appearance region of the target object in the pre-created scene map.
- the initially searched sub-area may be marked as the appearance area of the target object in the pre-created scene map.
- the scene map may be a map created indoors by the mobile device using sensors and algorithms before cleaning, and the map may include information such as the indoor layout and the location of furniture.
- step S502 the marked appearance area and/or the initial view image is output as an object search result for the target object.
- the marked appearance area and/or the initial view image may be output as an object search result for the target object.
- the shooting resolution of the RGB camera can be increased, and then, the initial framing image can be re-shot in the initial searched sub-area, and then, the marked appearance area and/or the re-shot initial framing image can be determined as the object search result for the target object.
- FIG. 6 shows a flowchart of how to determine an object search result based on the initial object detection result when the initial object detection result indicates that the initial viewfinder image does not contain the target object in the embodiment of the present disclosure, including steps S601 to S604:
- step S601 the next sub-region to be found is determined.
- the self-mobile device can determine the next sub-area to be found from the above-mentioned current scene or the above-mentioned key search area.
- the self-mobile device can determine the next sub-area to be found according to a preset sub-area determination strategy, wherein the above-mentioned preset sub-area determination strategy may include: the distance between the center position of the next sub-area to be found and the above-mentioned initial position is less than a preset distance threshold (the preset distance value, for example, can be a value greater than 0 and less than 2r, which can be set according to actual conditions, and the present disclosure does not make special restrictions on this), and the overlapping area between the next sub-area to be found and the above-mentioned initial searched sub-area is less than a preset area threshold (the preset area value can be set according to actual conditions, and the present disclosure does not make special restrictions on this).
- the preset distance value for example, can be a value greater than 0 and less than 2r, which can
- the next sub-area to be found is determined.
- the present invention can enable the self-moving device to preferentially search the area that is close to the initial position and has a smaller overlap with the searched area, thereby avoiding repeated invalid searches and unnecessary movements, thereby, on the one hand, improving the search efficiency; further, taking into account that the time and power of the self-moving device are limited, it is possible to more reasonably utilize the power allocation of the sweeper and extend the use time of the robot; further, it ensures that the next sub-area to be found has a certain overlapping area with the searched area, which can avoid the problem of missing blind spots in the search process and improve the integrity of the search.
- FIG8 shows a schematic diagram of a flow chart of how a mobile device moves to the next sub-area to be found in an embodiment of the present disclosure, including steps S801 and S802:
- step S801 the center position of the next sub-region to be found is determined.
- the self-mobile device can determine the center position of the next sub-region to be found, and the center position can ensure that the self-mobile device can subsequently rotate 360 degrees to capture images covering every corner of the next sub-region to be found.
- step S802 the system moves from the initial position to the center position of the next sub-region to be found.
- the self-moving device may move from the initial position to the center position of the next sub-region to be found.
- next sub-region to be found is the last sub-region to be found in the scene currently located by the mobile device, and the last viewfinder image corresponding to the last sub-region to be found still does not contain the target object, it can be determined that the search result of the target object is: not found.
- the present disclosure also provides a self-mobile device, which is provided with an image acquisition device.
- FIG9 shows a schematic diagram of the structure of the self-mobile device in an exemplary embodiment of the present disclosure; as shown in FIG9 , the self-mobile device 900 may include an image acquisition module 910 and an object search module 920. Among them:
- the object search module 920 is used to detect whether the viewfinder image contains the target object according to the feature description information, obtain an object detection result, and determine an object search result for the target object based on the object detection result.
- the image acquisition module 910 acquires the viewfinder image of the mobile device during the movement through the image acquisition device, including:
- the image acquisition device is used to acquire an initial framing image of the self-moving device during its movement in the initial sub-area to be found.
- the image acquisition module 910 determines an initial sub-region to be found from the current scene, including:
- a circular area with the initial position as the center and a preset distance as the radius is determined as the initial sub-area to be found.
- the image acquisition module 910 determines an initial sub-region to be found from the current scene, including:
- the image acquisition module 910 determines the initial sub-region to be searched in the key search region, including:
- a circular area with the initial position as the center and a preset distance as the radius is determined as the initial sub-area to be found.
- the image acquisition module 910 acquires an initial framing image of the mobile device during its movement in the initial sub-area to be found through the image acquisition device, including:
- the image acquisition device is used to acquire an initial framing image of the self-moving device during its rotation in the initial sub-area to be found.
- the designated search area is determined as the key search area.
- the initial sub-region to be found is marked as an initial found sub-region.
- the target object is detected according to the feature description information to obtain an initial object detection result.
- the object search module 920 determines the object search result for the target object based on the object detection result, including:
- the initial object detection result indicates that the target object is included in the initial viewfinder image, marking the initial searched sub-region as the appearance region of the target object in a pre-created scene map;
- the marked appearance area and/or the initial view image are output as an object search result for the target object.
- the object search module 920 is configured to:
- the target object includes a charging pile
- the object search result includes an appearance area of the charging pile
- the electronic device 1000 may also communicate with one or more external devices 1100 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1000, and/or may communicate with any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input/output (I/O) interface 1050.
- the electronic device 1000 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) via a network adapter 1060.
- networks e.g., a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet
- the network adapter 1060 communicates with other modules of the electronic device 1000 via a bus 1030.
- other hardware and/or software modules may be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
Abstract
本公开涉及智能家居技术领域,提供了一种对象寻找方法、自移动设备、计算机存储介质、电子设备,其中,对象寻找方法应用于自移动设备,所述自移动设备设置有图像采集设备,上述方法包括:在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像;所述对象寻找指令中包含待寻找的目标对象的特征描述信息;根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,基于所述对象检测结果确定针对所述目标对象的对象寻找结果。本公开中的对象寻找方法能够克服相关技术中仅能寻找自身具备信号发射能力的对象的局限性。
Description
相关申请的交叉引用
本公开要求于2024年1月5日提交的申请号为202410024179.8,名称为“对象寻找方法、自移动设备、计算机存储介质、电子设备”的中国专利申请的优先权,该中国专利申请的全部内容通过引用全部并入本文。
本公开涉及智能家居技术领域,特别涉及一种对象寻找方法、自移动设备、计算机存储介质及电子设备。
随着智能家居技术的迅速发展,自移动设备正在为越来越多的家庭带来便利。
相关技术中,部分自移动设备具备自动回桩功能,但是,自移动设备只能基于充电桩发出的信号寻找充电桩,一旦接收不到该信号,则无法实现上述自动回桩功能。
鉴于此,本领域亟需开发一种新的对象寻找方法。
需要说明的是,上述背景技术部分公开的信息仅用于加强对本公开的背景的理解。
本公开的目的在于提供一种对象寻找方法、自移动设备、计算机存储介质及电子设备,进而至少在一定程度上克服由于相关技术的限制而导致的只能寻找有能力发出信号的对象的技术问题。
本公开的其他特性和优点将通过下面的详细描述变得显然,或部分地通过本公开的实践而习得。
根据本公开的第一方面,提供一种对象寻找方法,应用于自移动设备,所述自移动设备设置有图像采集设备,所述方法包括:
在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像;所述对象寻找指令中包含待寻找的目标对象的特征描述信息;
根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,基于所述对象检测结果确定针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,所述在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像,包括:
在接收到对象寻找指令之后,从当前所处场景中确定初始待寻找子区域;
通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像。
在本公开的示例性实施例中,所述从当前所处场景中确定初始待寻找子区域,包括:
确定所述自移动设备在所述当前所处场景中的初始位置;
将以所述初始位置为圆心,以预设距离长度为半径的圆形区域确定为所述初始待寻找子区域。
在本公开的示例性实施例中,所述从当前所处场景中确定初始待寻找子区域,包括:
从所述当前所处场景中确定关键寻找区域;所述关键寻找区域对应的寻找优先级高于所述当前所处场景中的其他区域,所述寻找优先级用于表征所述自移动设备在所述当前所处场景的不同区域中寻找所述目标对象的先后顺序;
从当前位置移动至所述关键寻找区域内,在所述关键寻找区域中确定所述初始待寻找子区域。
在本公开的示例性实施例中,所述在所述关键寻找区域中确定所述初始待寻找子区域,包括:
确定所述自移动设备在所述关键寻找区域中的初始位置;
将以所述初始位置为圆心,以预设距离长度为半径的圆形区域确定为所述初始待寻找子区域。
在本公开的示例性实施例中,所述通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像,包括:
以所述初始位置为旋转中心,在所述初始待寻找子区域内旋转预设角度;
通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内旋转过程中的初始取景图像。
在本公开的示例性实施例中,所述从当前所处场景中确定关键寻找区域,包括:
检测所述对象寻找指令中是否包含针对所述目标对象的指定寻找区域;
若所述对象寻找指令中包含所述指定寻找区域,则将所述指定寻找区域确定为所述关键寻找区域。
在本公开的示例性实施例中,所述方法还包括:
若所述对象寻找指令中不包含所述指定寻找区域,则根据所述特征描述信息检索历史寻找记录,获得所述目标对象的历史出现区域;
将所述历史出现区域确定为所述关键寻找区域;
其中,所述历史寻找记录用于存储历史寻找对象的特征描述信息与其寻找结果之间的映射关系,所述寻找结果包含所述历史寻找对象的历史出现区域。
在本公开的示例性实施例中,在从当前位置移动至所述关键寻找区域内之后,所述方法还包括:
控制所述图像采集设备的采集频率由第一频率提高至第二频率。
在本公开的示例性实施例中,在通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像之后,所述方法还包括:
将所述初始待寻找子区域标记为初始已寻找子区域。
在本公开的示例性实施例中,所述根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,包括:
根据所述特征描述信息检测所述初始取景图像中是否包含所述目标对象,获得初始对象检测结果。
在本公开的示例性实施例中,在获得初始对象检测结果之后,所述基于所述对象检测结果确定针对所述目标对象的对象寻找结果,包括:
若所述初始对象检测结果表征所述初始取景图像中包含所述目标对象,在预先创建的场景地图中将所述初始已寻找子区域标记为所述目标对象的出现区域;
将标记好的所述出现区域和/或所述初始取景图像输出为针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,在预先创建的场景地图中将所述初始已寻找子区域标记为所述目标对象的出现区域之后,所述方法还包括:
在所述初始已寻找子区域重新拍摄所述初始取景图像;
将标记好的所述出现区域和/或重新拍摄的所述初始取景图像确定为针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,在获得初始对象检测结果之后,所述基于所述对象检测结果确定针对所述目标对象的对象寻找结果,包括:
若所述初始对象检测结果表征所述初始取景图像中不包含所述目标对象,确定下一个待寻找子区域;
通过所述图像采集设备采集所述自移动设备在所述下一个待寻找子区域内移动过程中的下一个取景图像;
根据所述特征描述信息检测所述下一个取景图像中是否包含所述目标对象,获得下一个对象检测结果;
基于所述下一个对象检测结果确定针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,所述确定下一个待寻找子区域,包括:
按照预设的子区域确定策略,确定下一个待寻找子区域;
其中,所述预设的子区域确定策略包括:所述下一个待寻找子区域的中心位置与所述初始位置之间的距离小于预设距离阈值,且,所述下一个待寻找子区域与所述初始已寻找子区域之间的重叠面积小于预设面积阈值。
在本公开的示例性实施例中,在确定下一个待寻找子区域之后,所述方法还包括:
确定所述下一个待寻找子区域的中心位置;
从所述初始位置移动至所述下一个待寻找子区域的中心位置。
在本公开的示例性实施例中,在基于所述对象检测结果确定针对所述目标对象的对象寻找结果之后,所述方法还包括:
将所述对象寻找结果推送至所述自移动设备对应的应用程序和/或用户端。
在本公开的示例性实施例中,所述目标对象包括充电桩,所述对象寻找结果包括所述充电桩的出现区域;
在将所述对象寻找结果推送至所述自移动设备对应的应用程序和/或用户端之后,所述方法还包括:
前往所述充电桩对应的所述出现区域进行充电。
在本公开的示例性实施例中,所述对象寻找指令包含以下形式:
通过所述自移动设备的应用程序发出的控制指令;
语音控制指令;
通过所述自移动设备的遥控设备发出的控制信号;
其中,所述遥控设备包括蓝牙遥控设备、红外遥控设备和射频遥控设备。
在本公开的示例性实施例中,所述目标对象包含一个或多个对象;
当所述目标对象包含多个对象时,所述多个对象中任意两个对象的类型相同或不同。
根据本公开的第二方面,提供一种自移动设备,所述自移动设备设置有图像采集设备,所述自移动设备包括:
图像采集模块,用于在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像;所述对象寻找指令中包含待寻找的目标对象的特征描述信息;
对象寻找模块,用于根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,基于所述对象检测结果确定针对所述目标对象的对象寻找结果。
根据本公开的第三方面,提供一种计算机存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现上述第一方面所述的对象寻找方法。
根据本公开的第四方面,提供一种电子设备,包括:处理器;以及存储器,用于存储所述处理器的可执行指令;其中,所述处理器配置为经由执行所述可执行指令来执行上述第一方面所述的对象寻找方法。
由上述技术方案可知,本公开示例性实施例中的对象寻找方法、自移动设备、计算机存储介质及电子设备至少具备以下优点和积极效果:
在本公开的一些实施例所提供的技术方案中,通过在接收到对象寻找指令(对象寻找指令中包含待寻找的目标对象的特征描述信息)之后,通过图像采集设备采集自移动设备在移动过程中的取景图像,根据特征描述信息检测取景图像中是否包含目标对象,获得对象检测结果,基于对象检测结果确定针对目标对象的对象寻找结果,一方面,克服了相关技术中仅能识别自身具有信号发射能力的对象的局限性问题,扩展了可寻找的目标对象的种类和范围,提升了寻物覆盖广度;另一方面,通过采集图像并基于特征描述信息进行图像检测的方式便可快速输出对象寻找结果,不仅避免了人工寻找目标对象所导致的耗时和人力成本,减轻了人工寻找负担,而且能够借助于特征描述信息准确的识别出目标对象,降低了误识别的可能性,提升了对象寻找结果的准确度。
本公开应当理解的是,以上的一般描述和后文的细节描述仅是示例性和解释性的,并不能限制本公开。
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本公开的实施例,并与说明书一起用于解释本公开的原理。显而易见地,下面描述中的附图仅仅是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1示出本公开实施例中对象寻找方法的流程示意图;
图2示出本公开实施例中如何通过图像采集设备采集自移动设备在移动过程中的取景图像的流程示意图;
图3示出本公开实施例中如何确定初始待寻找子区域的示意图;
图4示出本公开实施例中如何确定关键寻找区域的流程示意图;
图5示出本公开实施例中当初始对象检测结果表征初始取景图像中包含目标对象时,如何基于初始对象检测结果确定对象寻找结果的流程示意图;
图6示出本公开实施例中当初始对象检测结果表征初始取景图像中不包含目标对象时,如何基于初始对象检测结果确定对象寻找结果的流程示意图;
图7示出本公开实施例中一种如何确定下一个待寻找子区域的示意图;
图8示出本公开实施例中自移动设备如何移动至下一个待寻找子区域的流程示意图;
图9示出本公开示例性实施例中自移动设备的结构示意图;
图10示出本公开示例性实施例中电子设备的结构示意图。
现在将参考附图更全面地描述示例实施方式。然而,示例实施方式能够以多种形式实施,且不应被理解为限于在此阐述的范例;相反,提供这些实施方式使得本公开将更加全面和完整,并将示例实施方式的构思全面地传达给本领域的技术人员。所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。在下面的描述中,提供许多具体细节从而给出对本公开的实施方式的充分理解。然而,本领域技术人员将意识到,可以实践本公开的技术方案而省略所述特定细节中的一个或更多,或者可以采用其它的方法、组元、装置、步骤等。在其它情况下,不详细示出或描述公知技术方案以避免喧宾夺主而使得本公开的各方面变得模糊。
本说明书中使用用语“一个”、“一”、“该”和“所述”用以表示存在一个或多个要素/组成部分/等;用语“包括”和“具有”用以表示开放式的包括在内的意思并且是指除了列出的要素/组成部分/等之外还可存在另外的要素/组成部分/等;用语“第一”和“第二”等仅作为标记使用,不是对其对象的数量限制。
此外,附图仅为本公开的示意性图解,并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分,因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体,不一定必须与物理或逻辑上独立的实体相对应。
相关技术中,当自移动设备尝试回桩,但无法在记录的桩坐标点接收到桩信号(例如红外信号、patten图样等)时,则无法实现自动回桩功能。
因而,上述方案至少存在以下缺陷:寻物方式单一,必须目标物有能力发出信号或提供识别标识,才可以基于该信号进行寻找,对桩信号的依赖性过高,局限性较大。
在本公开的实施例中,首先提供了一种对象寻找方法,至少在一定程度上克服相关技术中只能寻找有能力发出信号的对象的缺陷。
图1示出本公开实施例中对象寻找方法的流程示意图,该对象寻找方法的执行主体可以是自移动设备。
参考图1,根据本公开的一个实施例的对象寻找方法包括以下步骤:
步骤S110,在接收到对象寻找指令之后,通过图像采集设备采集自移动设备在移动过程中的取景图像;对象寻找指令中包含待寻找的目标对象的特征描述信息;
步骤S120,根据特征描述信息检测取景图像中是否包含目标对象,获得对象检测结果,基于对象检测结果确定针对目标对象的对象寻找结果。
在图1所示实施例所提供的技术方案中,通过在接收到对象寻找指令(对象寻找指令中包含待寻找的目标对象的特征描述信息)之后,通过图像采集设备采集自移动设备在移动过程中的取景图像,根据特征描述信息检测取景图像中是否包含目标对象,获得对象检测结果,基于对象检测结果确定针对目标对象的对象寻找结果,一方面,克服了相关技术中仅能识别自身具有信号发射能力的对象的局限性问题,扩展了可寻找的目标对象的种类和范围,提升了寻物覆盖广度;另一方面,通过采集图像并基于特征描述信息进行图像检测的方式便可快速输出对象寻找结果,不仅避免了人工寻找目标对象所导致的耗时和人力成本,减轻了人工寻找负担,而且能够借助于特征描述信息准确的识别出目标对象,降低了误识别的可能性,提升了对象寻找结果的准确度。
以下对图1中的各个步骤的具体实现过程进行详细阐述:
在步骤S110之前,需要说明的是,本公开中的自移动设备(例如:扫地机器人)上设置有图像采集设备,该图像采集设备的作用是采集图像或视频。示例性的,该图像采集设备可以是RGB摄像头,RGB摄像头是一种通过高速拍摄多种颜色的图像、识别和测量物体表面颜色和亮度的传感器。其中RGB指的是红、绿、蓝三种颜色,这三种颜色的增减组成了多种颜色,所以RGB摄像头可以拍摄出非常丰富的颜色图像和视频。
在本公开中,用户可以通过发出对象寻找指令的方式控制自移动设备寻找指定的目标对象。
上述目标对象可以是一个或多个对象(例如:充电桩、宠物、凳子、钱币、遥控器等),当对象包含多个对象时,多个对象中任意两个对象的类型相同或不同,例如:充电桩和宠物,宠物A(小猫)和宠物B(小狗),可以根据实际情况自行设定,本公开对此不作特殊限定。
上述对象寻找指令中可以包含待寻找的目标对象的特征描述信息,特征描述信息可以是目标对象的名称、形状、大小、颜色、高频摆放位置等,也可以是目标对象的图片等,可以根据实际情况自行设定,本公开对此不作特殊限定。鉴于特征描述信息可以灵活定制,从而,本公开可以适应不同目标和场景的需求,使得该方案具有广泛的应用前景。
其中,上述对象寻找指令可以包含以下形式:
①通过自移动设备的应用程序发出的控制指令,即用户可以通过收集或其他智能设备安装自移动设备的应用程序,通过该应用程序的操作界面,用户可以输入文字、图片等来生成上述控制指令;
②语音控制指令,即用户通过语音的方式直接发出指令;
③通过自移动设备的遥控设备发出的控制信号,其中,该遥控设备可以是蓝牙遥控设备、红外遥控设备和射频遥控设备等,可以根据实际情况自行设定,本公开对此不作特殊限定。
在用户发出上述对象寻找指令之后,自移动设备可以接收该对象寻找指令,之后,可以执行步骤S110。
在步骤S110中,在接收到对象寻找指令之后,通过图像采集设备采集自移动设备在移动过程中的取景图像。
本步骤中,自移动设备在接收到上述对象寻找指令之后,可以通过上述图像采集设备采集自移动设备在移动过程中的取景图像。
具体的,参考图2,图2示出本公开实施例中如何通过图像采集设备采集自移动设备在移动过程中的取景图像的流程示意图,包含步骤S201-步骤S202:
在步骤S201中,从当前所处场景中确定初始待寻找子区域。
本步骤中,在第一种可选的实施方式中,自移动设备可以直接确定自身在当前所处场景中的初始位置(可以是接收到对象寻找指令的时刻自移动设备所处的实时位置,例如:位置A),进而,以该初始位置作为对象寻找起点,开始寻找该目标对象,具体的,自移动设备可以以该初始位置作为对象寻找起点,可以将以该初始位置为圆心,以预设距离长度为半径的圆形区域确定为初始待寻找子区域,在该初始待寻找子区域中开始寻找目标对象。
上述预设距离长度(示例性的,可以用r表示)可以是根据上述RGB摄像头的拍摄范围或可覆盖区域范围确定的,示例性的,该预设距离长度r可以是50cm-130cm的数值范围内的任意数值,可以根据实际情况自行设定,本公开对此不作特殊限定。
参考图3,图3示出本公开实施例中如何确定初始待寻找子区域的示意图,如图3所示,图中带阴影的圆圈所示即为自移动设备的初始位置,包含该带阴影的圆圈的圆形区域即为上述初始待寻找子区域。
在第二种可选的实施方式中,可以先从当前所处场景中确定关键寻找区域,进而,从当前位置移动至关键寻找区域内,在关键寻找区域中确定初始待寻找子区域。
其中,上述关键寻找区域即最有可能找到目标对象的区域或范围,通过设置关键寻找区域,能够指导自移动设备快速找到目标对象,节省寻找耗时,提升对象寻找效率。示例性的,本公开可以设置关键寻找区域对应的寻找优先级较高,而非关键寻找区域对应的寻找优先级较低,从而,自移动设备可以优先从该关键寻找区域去寻找上述目标对象,若没有从该关键寻找区域找到上述目标对象,可以再去其他的非关键寻找区域中继续寻找或者终止任务,直接生成对象寻找结果。
参考图4,图4示出本公开实施例中如何确定关键寻找区域的流程示意图,包含步骤S401-步骤S403:
在步骤S401中,检测对象寻找指令中是否包含针对目标对象的指定寻找区域。
本步骤中,自移动设备可以检测上述对象寻找指令中是否包含针对目标对象的指定寻找区域,该指定寻找区域可以是目标对象经常摆放或经常出现的区域。
在步骤S402中,若对象寻找指令中包含指定寻找区域,则将指定寻找区域确定为关键寻找区域。
本步骤中,若检测出上述对象寻找指令中包含了上述指定寻找区域,则自移动设备可以直接将上述指定寻找区域确定为关键寻找区域。
在步骤S403中,若对象寻找指令中不包含指定寻找区域,则根据特征描述信息检索历史寻找记录,获得目标对象的历史出现区域,将历史出现区域确定为关键寻找区域。
本步骤中,若检测出上述对象寻找指令中不包含上述指定寻找区域,则自移动设备可以根据上述对象寻找指令中包含的特征描述信息检索历史寻找记录,以获得目标对象的历史出现区域。
其中,上述历史寻找记录可以用于存储历史寻找对象的特征描述信息与其寻找结果之间的映射关系,寻找结果可以包含历史寻找对象的历史出现区域,历史出现区域即该目标对象过去出现过或过去经常摆放的位置区域。
需要说明的是,假设历史寻找记录中检索到多个历史出现区域,例如:a、b和c,则自移动设备还可以统计每个历史出现区域对应的出现次数,进而,按照出现次数确定上述多个历史出现区域的寻找优先级,以根据寻找优先级确定先去哪个历史出现区域中寻找上述目标对象,从而,提升对象寻找效率。
在确定出关键寻找区域之后,自移动设备可以从当前位置移动至关键寻找区域内,之后,自移动设备可以确定自身在关键寻找区域中的初始位置(例如:位置B),进而,参考上述步骤S201的相关表述,自移动设备可以以该初始位置作为对象寻找起点,具体的,可以将以该初始位置为圆心,以预设距离长度为半径的圆形区域确定为初始待寻找子区域,在该初始待寻找子区域中开始寻找目标对象。
需要说明的是,在从当前位置移动至关键寻找区域内之后,可以控制图像采集设备的采集频率由第一频率提高至第二频率,或者,控制图像采集设备的图像分辨率由第一分辨率提高至第二分辨率,或者,自移动设备还可以将每个待寻找子区域的遍历次数自动调整为两遍或两遍以上,以着重在关键寻找区域内寻找上述目标对象,具体的实施方式可以根据实际情况自行设定,本公开对此不作特殊限定。
在确定出初始待寻找子区域之后,接着参考图2,在步骤S202中,通过图像采集设备采集自移动设备在初始待寻找子区域内移动过程中的初始取景图像。
本步骤中,在确定出初始待寻找子区域之后,自移动设备可以以初始位置(即上述当前所处场景中的位置A或者关键寻找区域中的位置B)为旋转中心,在初始待寻找子区域内旋转预设角度(该预设角度可以是360度),通过图像采集设备采集自移动设备在初始待寻找子区域内旋转过程中的初始取景图像。
在通过图像采集设备采集自移动设备在初始待寻找子区域内旋转过程中的初始取景图像之后,自移动设备可以将该初始待寻找子区域标记为初始已查找子区域,基于此,可以避免某个子区域的重复查找所导致的查找耗时问题。
在获得初始取景图像之后,可以进入步骤S120中,根据特征描述信息检测取景图像中是否包含目标对象,获得对象检测结果,基于对象检测结果确定针对目标对象的对象寻找结果。
本步骤中,自移动设备可以基于上述对象寻找指令中包含的特征描述信息检测该初始取景图像中是否包含上述目标对象,获得初始对象检测结果。示例性的,自移动设备中可以预先部署一训练好的对象识别模型,基于该对象识别模型可以对上述初始取景图像进行特征提取,进而,可以对提取出来的特征进行分类或者匹配,以输出初始对象检测结果,该初始对象检测结果可以表征上述初始取景图像中是否包含目标对象。
在获得初始对象检测结果之后,可以基于该初始对象检测结果确定针对目标对象的对象寻找结果。
具体的,针对上述初始对象检测结果表征初始取景图像中包含上述目标对象的情况,可以参考图5所示的处理流程来确定针对目标对象的对象寻找结果;而针对上述初始对象检测结果表征初始取景图像中不包含上述目标对象的情况,可以参考图6所示的处理流程来处理流程来确定针对目标对象的对象寻找结果。
首先,参考图5,图5示出本公开实施例中当初始对象检测结果表征初始取景图像中包含目标对象时,如何基于初始对象检测结果确定对象寻找结果的流程示意图,包含步骤S501-步骤S502:
在步骤S501中,在预先创建的场景地图中将初始已寻找子区域标记为目标对象的出现区域。
本步骤中,可以在预先创建的场景地图中将初始已寻找子区域标记为目标对象的出现区域。其中,上述场景地图可以是自移动设备在清扫前使用传感器和算法在室内创建的地图,该地图中可以包含室内的布局、家具的位置等信息。
在步骤S502中,将标记好的出现区域和/或初始取景图像输出为针对目标对象的对象寻找结果。
本步骤中,在一种可选的实施方式中,可以标记好的上述出现区域和/或初始取景图像输出为针对目标对象的对象寻找结果。
在另一种可选的实施方式中,示例性的,在标记完上述目标对象的出现区域之后,可以提高RGB摄像头的拍摄分辨率,进而,可以在上述初始已寻找子区域中重新拍摄上述初始取景图像,进而,将标记好的出现区域和/或重新拍摄的初始取景图像确定为针对目标对象的对象寻找结果。
接下来,参考图6,图6示出本公开实施例中当初始对象检测结果表征初始取景图像中不包含目标对象时,如何基于初始对象检测结果确定对象寻找结果的流程示意图,包含步骤S601-步骤S604:
在步骤S601中,确定下一个待寻找子区域。
本步骤中,自移动设备可以从上述当前所处场景或者上述关键寻找区域中确定下一个待寻找子区域。示例性的,自移动设备可以按照预设的子区域确定策略,确定下一个待寻找子区域,其中,上述预设的子区域确定策略可以包括:下一个待寻找子区域的中心位置与上述初始位置之间的距离小于预设距离阈值(预先设定的距离值,示例性的,可以是大于0小于2r的数值,可以根据实际情况自行设定,本公开对此不作特殊限定),且,下一个待寻找子区域与上述初始已寻找子区域之间的重叠面积小于预设面积阈值(预先设定的面积值,可以根据实际情况自行设定,本公开对此不作特殊限定)。
参考图7,图7示出本公开实施例中一种如何确定下一个待寻找子区域的示意图,如图7所示,下一个待寻找子区域的中心位置可以位于上述初始已寻找子区域的边界线上,从而,下一个待寻找子区域的中心位置与初始位置之间的距离为r,并且,下一个待寻找子区域与初始已寻找子区域之间存在部分重叠面积,从而,自移动设备可以通过在下一个待寻找子区域的中心位置上旋转360度来采集下一个待寻找子区域对应的取景图像,类似的,后续的再下一个待寻找子区域的具体确定方式与该下一个待寻找子区域的确定方式相同。
基于上述策略确定下一个待寻找子区域,本公开能够使得自移动设备优先搜索距离初始位置较近且与已搜索区域重叠较小的区域,避免了重复无效搜索和不必要的移动,从而,一方面,提高了搜索效率;进一步的,考虑到了自移动设备的时间和电量是有限的,从而能够更合理的利用扫地机人的电量分配,延长了机器人的使用时长;进一步的,确保了下一个待寻找子区域与已搜索区域有一定的重叠面积,可以避免搜索过程中的搜索死角遗漏问题,提高搜索的完整性。
在确定出下一个待寻找子区域之后,参考图8,图8示出本公开实施例中自移动设备如何移动至下一个待寻找子区域的流程示意图,包含步骤S801-步骤S802:
在步骤S801中,确定下一个待寻找子区域的中心位置。
本步骤中,在确定出下一个待寻找子区域之后,自移动设备可以确定下一个待寻找子区域的中心位置,该中心位置可以确保自移动设备后续旋转360可以采集到覆盖下一个待寻找子区域内每个角落的图像。
在步骤S802中,从初始位置移动至下一个待寻找子区域的中心位置。
本步骤中,在确定出下一个待寻找子区域的中心位置之后,自移动设备可以从上述初始位置移动至该下一个待寻找子区域的中心位置。
在移动至下一个待寻找子区域的中心位置之后,可以接着参考图6,在步骤S602中,通过图像采集设备采集自移动设备在下一个待寻找子区域内移动过程中的下一个取景图像。
本步骤中,自移动设备可以在该中心位置上旋转360度,以通过图像采集设备采集自移动设备在下一个待寻找子区域内旋转过程中的下一个取景图像,在获得下一个取景图像之后,可以将该下一个待寻找子区域标记为已寻找子区域。
在步骤S603中,根据特征描述信息检测下一个取景图像中是否包含目标对象,获得下一个对象检测结果。
本步骤中,在获得下一个取景图像之后,自移动设备可以再次调用上述物体识别模型,以使得该物体识别模型基于上述对象寻找指令中包含的特征描述信息检测下一个取景图像中是否包含目标对象,获得下一个对象检测结果。
在步骤S604中,基于下一个对象检测结果确定针对目标对象的对象寻找结果。
本步骤中,自移动设备可以基于该下一个对象检测结果确定针对目标对象的对象寻找结果。示例性的,具体而言,当下一个对象检测结果表征下一个取景图像中包含目标对象时,可以直接在预先创建的场景地图中将下一个已寻找子区域标记为目标对象的出现区域,之后,将标记好的出现区域和/或上述下一张初始取景图像输出为针对目标对象的对象寻找结果。而当下一个对象检测结果表征下一个取景图像中不包含目标对象的时候,则可以重新确定下一个待寻找子区域,直至下一个待寻找子区域为自移动设备当前所处场景中的最后一个待寻找子区域,或者,检测出下一个待寻找子区域对应的下一个取景图像中包含目标对象的时候,终止从当前所处场景中寻找目标对象。
若下一个待寻找子区域为自移动设备当前所处场景中的最后一个待寻找子区域,并且,该最后一个待寻找子区域对应的最后一个取景图像中仍未包含上述目标对象,则可以确定出目标对象的寻找结果为:未找到。
在基于对象检测结果确定针对目标对象的对象寻找结果之后,本公开可以将对象寻找结果推送至自移动设备对应的应用程序和/或用户端,示例性的,可以显示在应用程序的提醒界面上,也可以以语音回复的方式告知用户,可以根据实际情况自行设定,本公开对此不作特殊限定。
需要说明的是,当上述目标对象为充电桩的时候,若对象寻找结果中包含充电桩的出现区域,则将对象寻找结果推送至自移动设备对应的应用程序和/或用户端之后,自移动设备可以自行前往充电桩对应的出现区域进行充电。
还需要说明的是,当上述对象寻找指令中的目标对象包含两个或两个以上对象的情况下,示例性的,以对象寻找指令中包含对象A、对象B和对象C的特征描述信息为例进行说明,则在一种可选的实施方式中,自移动设备可以在获得每个取景图像之后,检测该取景图像中是否包含对象A、对象B和对象C,若包含任一指定对象(例如:对象A),则可以标记该指定对象的位置,并将该指定对象(对象A)从待寻找对象中剔除,接着采集下一张取景图像,并检测该取景图像中是否包含对象B和对象C,直至找到上述三个对象或者遍历完当前所处场景,结束任务,输出对象寻找结果(可以是三个对象都找到的成功结果,也可以是三个对象都未找到的失败结果,还可以是部分对象找到,部分对象未找到的结果)。在另一种可选的实施方式中,自移动设备可以在获得每个取景图像之后,先检测该取景图像中是否包含对象A,在找到对象A或者遍历完当前所处场景,结束寻找对象A的任务,之后,再在当前所处场景中采集取景图像,检测该取景图像中是否包含对象B,在找到对象B或者遍历完当前所处场景,结束寻找对象B的任务,最后,再在当前所处场景中采集取景图像,检测该取景图像中是否包含对象C,在找到对象C或者遍历完当前所处场景,结束寻找对象C的任务。以上方式,均可以根据实际情况自行设定,本公开对此不作特殊限定。
基于以上技术方案,本公开至少具有以下技术效果:
第一,通过响应对象寻找指令的方式来寻找目标对象,克服了相关技术中仅能识别自身具有信号发射能力的对象的局限性问题,扩展了可寻找的目标对象的种类和范围,提升了寻物覆盖广度;
第二,通过设置在每个位置旋转360度采集每个待寻找子区域内的取景图像,之后,选取与当前位置距离最近且与当前的待寻找子区域重叠面积最小的下一个待寻找子区域的方式来继续寻找目标对象,能够避免产生寻物死角,保证搜索区域覆盖环境中的各个角落;
第三,通过从当前所处场景中确定关键寻找区域(即目标对象的指定寻找区域或者目标对象的历史出现区域),优先去关键寻找区域中寻找目标对象,能够辅助自移动设备快速寻找到目标对象,节省对象寻找耗时,提升对象寻找效率。
本公开还提供了一种自移动设备,所述自移动设备设置有图像采集设备,图9示出本公开示例性实施例中自移动设备的结构示意图;如图9所示,自移动设备900可以包括图像采集模块910和对象寻找模块920。其中:
图像采集模块910,用于在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像;所述对象寻找指令中包含待寻找的目标对象的特征描述信息;
对象寻找模块920,用于根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,基于所述对象检测结果确定针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,所述在接收到对象寻找指令之后,图像采集模块910通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像,包括:
在接收到对象寻找指令之后,从当前所处场景中确定初始待寻找子区域;
通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像。
在本公开的示例性实施例中,所述图像采集模块910从当前所处场景中确定初始待寻找子区域,包括:
确定所述自移动设备在所述当前所处场景中的初始位置;
将以所述初始位置为圆心,以预设距离长度为半径的圆形区域确定为所述初始待寻找子区域。
在本公开的示例性实施例中,所述图像采集模块910从当前所处场景中确定初始待寻找子区域,包括:
从所述当前所处场景中确定关键寻找区域;所述关键寻找区域对应的寻找优先级高于所述当前所处场景中的其他区域,所述寻找优先级用于表征所述自移动设备在所述当前所处场景的不同区域中寻找所述目标对象的先后顺序;
从当前位置移动至所述关键寻找区域内,在所述关键寻找区域中确定所述初始待寻找子区域。
在本公开的示例性实施例中,所述图像采集模块910在所述关键寻找区域中确定所述初始待寻找子区域,包括:
确定所述自移动设备在所述关键寻找区域中的初始位置;
将以所述初始位置为圆心,以预设距离长度为半径的圆形区域确定为所述初始待寻找子区域。
在本公开的示例性实施例中,所述图像采集模块910通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像,包括:
以所述初始位置为旋转中心,在所述初始待寻找子区域内旋转预设角度;
通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内旋转过程中的初始取景图像。
在本公开的示例性实施例中,所述图像采集模块910从当前所处场景中确定关键寻找区域,包括:
检测所述对象寻找指令中是否包含针对所述目标对象的指定寻找区域;
若所述对象寻找指令中包含所述指定寻找区域,则将所述指定寻找区域确定为所述关键寻找区域。
在本公开的示例性实施例中,所述图像采集模块910,被配置为:
若所述对象寻找指令中不包含所述指定寻找区域,则根据所述特征描述信息检索历史寻找记录,获得所述目标对象的历史出现区域;
将所述历史出现区域确定为所述关键寻找区域;
其中,所述历史寻找记录用于存储历史寻找对象的特征描述信息与其寻找结果之间的映射关系,所述寻找结果包含所述历史寻找对象的历史出现区域。
在本公开的示例性实施例中,在从当前位置移动至所述关键寻找区域内之后,所述图像采集模块910,被配置为:
控制所述图像采集设备的采集频率由第一频率提高至第二频率。
在本公开的示例性实施例中,在通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像之后,所述方法还包括:
将所述初始待寻找子区域标记为初始已寻找子区域。
在本公开的示例性实施例中,所述对象寻找模块920根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,包括:
根据所述特征描述信息检测所述初始取景图像中是否包含所述目标对象,获得初始对象检测结果。
在本公开的示例性实施例中,在获得初始对象检测结果之后,所述对象寻找模块920基于所述对象检测结果确定针对所述目标对象的对象寻找结果,包括:
若所述初始对象检测结果表征所述初始取景图像中包含所述目标对象,在预先创建的场景地图中将所述初始已寻找子区域标记为所述目标对象的出现区域;
将标记好的所述出现区域和/或所述初始取景图像输出为针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,在预先创建的场景地图中将所述初始已寻找子区域标记为所述目标对象的出现区域之后,所述对象寻找模块920,被配置为:
在所述初始已寻找子区域重新拍摄所述初始取景图像;
将标记好的所述出现区域和/或重新拍摄的所述初始取景图像确定为针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,在获得初始对象检测结果之后,所述对象寻找模块920基于所述对象检测结果确定针对所述目标对象的对象寻找结果,包括:
若所述初始对象检测结果表征所述初始取景图像中不包含所述目标对象,确定下一个待寻找子区域;
通过所述图像采集设备采集所述自移动设备在所述下一个待寻找子区域内移动过程中的下一个取景图像;
根据所述特征描述信息检测所述下一个取景图像中是否包含所述目标对象,获得下一个对象检测结果;
基于所述下一个对象检测结果确定针对所述目标对象的对象寻找结果。
在本公开的示例性实施例中,所述对象寻找模块920确定下一个待寻找子区域,包括:
按照预设的子区域确定策略,确定下一个待寻找子区域;
其中,所述预设的子区域确定策略包括:所述下一个待寻找子区域的中心位置与所述初始位置之间的距离小于预设距离阈值,且,所述下一个待寻找子区域与所述初始已寻找子区域之间的重叠面积小于预设面积阈值。
在本公开的示例性实施例中,在确定下一个待寻找子区域之后,所述对象寻找模块920,被配置为:
确定所述下一个待寻找子区域的中心位置;
从所述初始位置移动至所述下一个待寻找子区域的中心位置。
在本公开的示例性实施例中,在基于所述对象检测结果确定针对所述目标对象的对象寻找结果之后,所述对象寻找模块920,被配置为:
将所述对象寻找结果推送至所述自移动设备对应的应用程序和/或用户端。
在本公开的示例性实施例中,所述目标对象包括充电桩,所述对象寻找结果包括所述充电桩的出现区域;
在将所述对象寻找结果推送至所述自移动设备对应的应用程序和/或用户端之后,所述对象寻找模块920,被配置为:
前往所述充电桩对应的所述出现区域进行充电。
在本公开的示例性实施例中,所述对象寻找指令包含以下形式:
通过所述自移动设备的应用程序发出的控制指令;
语音控制指令;
通过所述自移动设备的遥控设备发出的控制信号;
其中,所述遥控设备包括蓝牙遥控设备、红外遥控设备和射频遥控设备。
在本公开的示例性实施例中,所述目标对象包含一个或多个对象;
当所述目标对象包含多个对象时,所述多个对象中任意两个对象的类型相同或不同。
上述自移动设备中各模块的具体细节已经在对应的对象寻找方法中进行了详细的描述,因此此处不再赘述。
应当注意,尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元,但是这种划分并非强制性的。实际上,根据本公开的实施方式,上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之,上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体化。
此外,尽管在附图中以特定顺序描述了本公开中方法的各个步骤,但是,这并非要求或者暗示必须按照该特定顺序来执行这些步骤,或是必须执行全部所示的步骤才能实现期望的结果。附加的或备选的,可以省略某些步骤,将多个步骤合并为一个步骤执行,以及/或者将一个步骤分解为多个步骤执行等。
通过以上的实施方式的描述,本领域的技术人员易于理解,这里描述的示例实施方式可以通过软件实现,也可以通过软件结合必要的硬件的方式来实现。因此,根据本公开实施方式的技术方案可以以软件产品的形式体现出来,该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM,U盘,移动硬盘等)中或网络上,包括若干指令以使得一台计算设备(可以是个人计算机、服务器、移动终端、或者网络设备等)执行根据本公开实施方式的方法。
本申请还提供了一种计算机可读存储介质,该计算机可读存储介质可以是上述实施例中描述的电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读存储介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读存储介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:无线、电线、光缆、RF等等,或者上述的任意合适的组合。
计算机可读存储介质承载有一个或者多个程序,当上述一个或者多个程序被一个该电子设备执行时,使得该电子设备实现如上述实施例中所述的方法。
此外,在本公开实施例中还提供了一种能够实现上述方法的电子设备。
所属技术领域的技术人员能够理解,本公开的各个方面可以实现为系统、方法或程序产品。因此,本公开的各个方面可以具体实现为以下形式,即:完全的硬件实施方式、完全的软件实施方式(包括固件、微代码等),或硬件和软件方面结合的实施方式,这里可以统称为“电路”、“模块”或“系统”。
下面参照图10来描述根据本公开的这种实施方式的电子设备1000。图10显示的电子设备1000仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。
如图10所示,电子设备1000以通用计算设备的形式表现。电子设备1000的组件可以包括但不限于:上述至少一个处理单元1010、上述至少一个存储单元1020、连接不同系统组件(包括存储单元1020和处理单元1010)的总线1030以及显示单元1040。
其中,所述存储单元存储有程序代码,所述程序代码可以被所述处理单元1010执行,使得所述处理单元1010执行本说明书上述“示例性方法”部分中描述的根据本公开各种示例性实施方式的步骤。例如,所述处理单元1010可以执行如图1中所示的:步骤S110,在接收到对象寻找指令之后,通过图像采集设备采集自移动设备在移动过程中的取景图像;对象寻找指令中包含待寻找的目标对象的特征描述信息;步骤S120,根据特征描述信息检测取景图像中是否包含目标对象,获得对象检测结果,基于对象检测结果确定针对目标对象的对象寻找结果。
存储单元1020可以包括易失性存储单元形式的可读介质,例如随机存取存储单元(RAM)10201和/或高速缓存存储单元10202,还可以进一步包括只读存储单元(ROM)10203。
存储单元1020还可以包括具有一组(至少一个)程序模块10205的程序/实用工具10204,这样的程序模块10205包括但不限于:操作系统、一个或者多个应用程序、其它程序模块以及程序数据,这些示例中的每一个或某种组合中可能包括网络环境的实现。
总线1030可以为表示几类总线结构中的一种或多种,包括存储单元总线或者存储单元控制器、外围总线、图形加速端口、处理单元或者使用多种总线结构中的任意总线结构的局域总线。
电子设备1000也可以与一个或多个外部设备1100(例如键盘、指向设备、蓝牙设备等)通信,还可与一个或者多个使得用户能与该电子设备1000交互的设备通信,和/或与使得该电子设备1000能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口1050进行。并且,电子设备1000还可以通过网络适配器1060与一个或者多个网络(例如局域网(LAN),广域网(WAN)和/或公共网络,例如因特网)通信。如图所示,网络适配器1060通过总线1030与电子设备1000的其它模块通信。应当明白,尽管图中未示出,可以结合电子设备1000使用其它硬件和/或软件模块,包括但不限于:微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本公开的其他实施例。本申请旨在涵盖本公开的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的,本公开的真正范围和精神由权利要求指出。
Claims (10)
- 一种对象寻找方法,应用于自移动设备,所述自移动设备设置有图像采集设备,所述方法包括:在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像;所述对象寻找指令中包含待寻找的目标对象的特征描述信息;根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,基于所述对象检测结果确定针对所述目标对象的对象寻找结果。
- 根据权利要求1所述的方法,其中,所述在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像,包括:在接收到对象寻找指令之后,从当前所处场景中确定初始待寻找子区域;通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像。
- 根据权利要求2所述的方法,其中,所述从当前所处场景中确定初始待寻找子区域,包括:确定所述自移动设备在所述当前所处场景中的初始位置;将以所述初始位置为圆心,以预设距离长度为半径的圆形区域确定为所述初始待寻找子区域。
- 根据权利要求2所述的方法,其中,所述从当前所处场景中确定初始待寻找子区域,包括:从所述当前所处场景中确定关键寻找区域;所述关键寻找区域对应的寻找优先级高于所述当前所处场景中的其他区域,所述寻找优先级用于表征所述自移动设备在所述当前所处场景的不同区域中寻找所述目标对象的先后顺序;从当前位置移动至所述关键寻找区域内,在所述关键寻找区域中确定所述初始待寻找子区域。
- 根据权利要求4所述的方法,其中,所述在所述关键寻找区域中确定所述初始待寻找子区域,包括:确定所述自移动设备在所述关键寻找区域中的初始位置;将以所述初始位置为圆心,以预设距离长度为半径的圆形区域确定为所述初始待寻找子区域。
- 根据权利要求2至5中任一项所述的方法,其中,所述通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内移动过程中的初始取景图像,包括:以所述初始位置为旋转中心,在所述初始待寻找子区域内旋转预设角度;通过所述图像采集设备采集所述自移动设备在所述初始待寻找子区域内旋转过程中的初始取景图像。
- 根据权利要求4或5所述的方法,其中,所述从当前所处场景中确定关键寻找区域,包括:检测所述对象寻找指令中是否包含针对所述目标对象的指定寻找区域;若所述对象寻找指令中包含所述指定寻找区域,则将所述指定寻找区域确定为所述关键寻找区域。
- 一种自移动设备,所述自移动设备设置有图像采集设备,所述自移动设备包括:图像采集模块,用于在接收到对象寻找指令之后,通过所述图像采集设备采集所述自移动设备在移动过程中的取景图像;所述对象寻找指令中包含待寻找的目标对象的特征描述信息;对象寻找模块,用于根据所述特征描述信息检测所述取景图像中是否包含所述目标对象,获得对象检测结果,基于所述对象检测结果确定针对所述目标对象的对象寻找结果。
- 一种计算机存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现权利要求1至7中任意一项所述的对象寻找方法。
- 一种电子设备,包括:处理器;以及存储器,用于存储所述处理器的可执行指令;其中,所述处理器配置为经由执行所述可执行指令来执行权利要求1至7中任意一项所述的对象寻找方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410024179.8A CN118072265A (zh) | 2024-01-05 | 2024-01-05 | 对象寻找方法、自移动设备、计算机存储介质、电子设备 |
| CN202410024179.8 | 2024-01-05 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025146201A1 true WO2025146201A1 (zh) | 2025-07-10 |
Family
ID=91096250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2025/070790 Pending WO2025146201A1 (zh) | 2024-01-05 | 2025-01-06 | 对象寻找方法、自移动设备、计算机存储介质、电子设备 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN118072265A (zh) |
| WO (1) | WO2025146201A1 (zh) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118072265A (zh) * | 2024-01-05 | 2024-05-24 | 北京石头世纪科技股份有限公司 | 对象寻找方法、自移动设备、计算机存储介质、电子设备 |
| CN118711151A (zh) * | 2024-06-07 | 2024-09-27 | 北京石头创新科技有限公司 | 对象寻找方法、自移动设备、计算机存储介质 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992814A (zh) * | 2017-11-28 | 2018-05-04 | 北京小米移动软件有限公司 | 对象寻找方法及装置 |
| US20200082207A1 (en) * | 2018-09-07 | 2020-03-12 | Baidu Online Network Technology (Beijing) Co., Ltd. | Object detection method and apparatus for object detection |
| CN114241405A (zh) * | 2021-11-25 | 2022-03-25 | 北京小米移动软件有限公司 | 物品寻找方法、物品寻找装置及存储介质 |
| CN114764877A (zh) * | 2020-12-31 | 2022-07-19 | 氪见(南京)科技有限公司 | 信息处理方法、装置、设备、移动机器人及存储介质 |
| CN118072265A (zh) * | 2024-01-05 | 2024-05-24 | 北京石头世纪科技股份有限公司 | 对象寻找方法、自移动设备、计算机存储介质、电子设备 |
-
2024
- 2024-01-05 CN CN202410024179.8A patent/CN118072265A/zh active Pending
-
2025
- 2025-01-06 WO PCT/CN2025/070790 patent/WO2025146201A1/zh active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992814A (zh) * | 2017-11-28 | 2018-05-04 | 北京小米移动软件有限公司 | 对象寻找方法及装置 |
| US20200082207A1 (en) * | 2018-09-07 | 2020-03-12 | Baidu Online Network Technology (Beijing) Co., Ltd. | Object detection method and apparatus for object detection |
| CN114764877A (zh) * | 2020-12-31 | 2022-07-19 | 氪见(南京)科技有限公司 | 信息处理方法、装置、设备、移动机器人及存储介质 |
| CN114241405A (zh) * | 2021-11-25 | 2022-03-25 | 北京小米移动软件有限公司 | 物品寻找方法、物品寻找装置及存储介质 |
| CN118072265A (zh) * | 2024-01-05 | 2024-05-24 | 北京石头世纪科技股份有限公司 | 对象寻找方法、自移动设备、计算机存储介质、电子设备 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118072265A (zh) | 2024-05-24 |
| TW202527867A (zh) | 2025-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2025146201A1 (zh) | 对象寻找方法、自移动设备、计算机存储介质、电子设备 | |
| EP2988210B1 (en) | Gesture control method, apparatus and system | |
| CN111127648B (zh) | 室内平面地图的生成方法及装置、清扫地图的生成方法 | |
| WO2013041048A1 (zh) | 遥控方法及用于实现该遥控方法的电子设备 | |
| WO2021169720A1 (zh) | 内容操作方法、装置、终端及存储介质 | |
| CN108416866A (zh) | 一种巡检任务处理方法及设备 | |
| WO2014061257A1 (ja) | 認識装置、認識方法、遠隔制御装置、認識プログラム、及びサーバ | |
| CN107871000B (zh) | 音频播放方法、装置、存储介质及电子设备 | |
| CN112971616B (zh) | 一种充电座规避方法、装置、扫地机器人及存储介质 | |
| TW202547411A (zh) | 對象尋找方法、自移動設備、計算機存儲介質 | |
| WO2024007807A1 (zh) | 一种误差校正方法、装置及移动设备 | |
| CN112824182A (zh) | 自动泊车方法、装置、计算机设备和存储介质 | |
| CN103947153B (zh) | 搜索网络中的对象的方法和系统 | |
| CN106407977A (zh) | 目标内容的定位搜索的方法和装置 | |
| CN103049187B (zh) | 一种拼接式多屏交互电子白板系统的信号处理方法 | |
| CN110361978B (zh) | 基于物联网操作系统的智能设备控制方法和装置及系统 | |
| WO2025092478A1 (zh) | 基于充电桩的智能行走设备控制方法及相关设备 | |
| TWI919718B (zh) | 對象尋找方法、自移動設備、電腦儲存媒體及電子設備 | |
| CN110962132B (zh) | 一种机器人系统 | |
| CN104216506B (zh) | 基于手势操作的数据交互方法及装置 | |
| CN104111756B (zh) | 提高图像帧率的方法和系统、光学成像触摸屏系统 | |
| CN105763930A (zh) | 一种推送电视节目二维码的方法、智能电视机及机顶盒 | |
| CN116110391B (zh) | 一种扫地机器人的智能语音控制方法、系统、设备及介质 | |
| CN117456432A (zh) | 障碍物的识别方法、电子设备及计算机程序产品 | |
| WO2023207610A1 (zh) | 建图方法、装置、存储介质及电子装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 25736440 Country of ref document: EP Kind code of ref document: A1 |