Object searching method, autonomous mobile device, and computer storage medium

Abstract

The present disclosure relates to the technical field of smart homes, and provides an object searching method, an autonomous mobile device, and a computer storage medium. The object searching method is applied to an autonomous mobile device, and the autonomous mobile device is provided with an image acquisition device. The method comprises: after an object searching instruction is received, acquiring, by means of the image acquisition device, a viewfinder image of the autonomous mobile device during movement, the object searching instruction comprising feature description information of a target object to be searched for; and on the basis of the feature description information, detecting whether the target object is included in the viewfinder image, and obtaining an object detection result; and determining, on the basis of the object detection result, an object searching result for the target object. The object searching method in the present disclosure can overcome the limitation in the related art that only objects having the ability to transmit signals can be searched for.

Description

Object searching method, self-moving device, and computer storage medium

[0001] Cross-reference to Related Applications

[0002] The present disclosure claims priority to Chinese Patent Application No. 202410742909.8, filed on June 7, 2024, entitled “Object searching method, self-moving device, and computer storage medium,” the entire contents of which are incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of smart home, and in particular, to an object searching method, a self-moving device, and a computer storage medium. BACKGROUND

[0004] With the rapid development of smart home technology, self-moving devices are bringing convenience to more and more families.

[0005] In related technologies, some self-moving devices have an automatic return pile function, but the self-moving devices can only search for a charging pile based on a signal emitted by the charging pile, and once the signal cannot be received, the automatic return pile function cannot be implemented.

[0006] In view of this, there is an urgent need in the art to develop a new object searching method.

[0007] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure. SUMMARY

[0008] The purpose of the present disclosure is to provide an object searching method, a self-moving device, a computer storage medium, and an electronic device, thereby at least partially overcoming the technical problem of being able to only search for objects capable of emitting signals due to the limitations of related technologies.

[0009] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0010] According to a first aspect of the present disclosure, an object searching method is provided, applied to a self-moving device provided with an image acquisition device, the method comprising:

[0011] After receiving an object searching instruction, an image acquisition device is used to acquire a viewfinder image of the self-moving device during movement; the object searching instruction contains feature description information of a target object to be searched for;

[0012] According to the feature description information, whether the target object is contained in the view image is detected, an object detection result is obtained, and an object searching result for the target object is determined based on the object detection result.

[0013] In the example embodiments of the present disclosure, after receiving the object searching instruction, the view images of the self-moving device during movement are collected by the image collection device, including:

[0014] After receiving the object searching instruction, a plurality of image collection points are planned in the current scene; each of the image collection points is associated with a collection range, and each of the collection ranges is a circular region with the image collection point as the center and a first preset distance as the radius; the plurality of collection ranges associated with the plurality of image collection points cover the current scene.

[0015] The view images of the self-moving device during movement at each of the image collection points for each of the collection ranges are collected by the image collection device.

[0016] In the example embodiments of the present disclosure, the plurality of image collection points are planned in the current scene, including:

[0017] An initial position of the self-moving device in the current scene is determined.

[0018] The initial position is determined as an initial image collection point, and a next image collection point is planned based on the initial image collection point and a preset point setting condition.

[0019] The next image collection point is taken as a new initial image collection point, and a new next image collection point is planned based on the new initial image collection point and the preset point setting condition, until the plurality of image collection points are planned.

[0020] The preset point setting condition is used to constrain that a distance between the next image collection point and the initial image collection point is less than or equal to a second preset distance and there is no obstacle in a collection range associated with the next image collection point; the second preset distance is greater than the first preset distance, and there is a numerical correlation between the second preset distance and the first preset distance.

[0021] In the example embodiments of the present disclosure, after receiving the object searching instruction, the view images of the self-moving device during movement are collected by the image collection device, including:

[0022] determining a key searching area from a current scene, the key searching area corresponding to a higher searching priority than other areas in the current scene, the searching priority representing a sequence of searching the target object in different areas of the current scene by the self-moving device;

[0023] moving from an initial position in the current scene to the key searching area, and planning a plurality of image collection points in the key searching area, each of the image collection points being associated with a collection range, each of the collection ranges being a circular area with the image collection point as a center and a first preset distance as a radius, and the plurality of collection ranges associated with the plurality of image collection points covering the key searching area;

[0024] collecting, by the image collection device, a viewfinder image for each collection range in a process of moving of the self-moving device at each of the image collection points.

[0025] In an example embodiment of the present disclosure, the determining the key searching area from the current scene comprises:

[0026] detecting whether a specified searching area for the target object is included in the object searching instruction;

[0027] if the specified searching area is included in the object searching instruction, determining the specified searching area as the key searching area.

[0028] In an example embodiment of the present disclosure, the method further comprises:

[0029] if the specified searching area is not included in the object searching instruction, retrieving a historical searching record according to the feature description information to obtain a historical appearance area of the target object;

[0030] determining the historical appearance area as the key searching area;

[0031] wherein the historical searching record is used to store a mapping relationship between feature description information of a historical searching object and a searching result of the historical searching object, the searching result including a historical appearance area of the historical searching object.

[0032] In an example embodiment of the present disclosure, after moving from the initial position in the current scene to the key searching area, the method further comprises:

[0033] controlling a collection frequency of the image collection device to increase from a first frequency to a second frequency.

[0034] In an example embodiment of the present disclosure, the planning a plurality of image collection points in the key searching area comprises:

[0035] determining an initial position of the self-moving device in the key search area;

[0036] determining the initial position as an initial image collection point, planning a next image collection point based on the initial image collection point and a preset point setting condition;

[0037] taking the next image collection point as a new initial image collection point, and planning a new next image collection point based on the new initial image collection point and the preset point setting condition, until the plurality of image collection points are planned;

[0038] The preset point setting condition is used to constrain that a distance between the next image collection point and the initial image collection point is less than or equal to a second preset distance, and there is no obstacle in a collection range associated with the next image collection point. The second preset distance is greater than the first preset distance, and there is a numerical correlation between the second preset distance and the first preset distance.

[0039] In an example embodiment of the present disclosure, the collecting, by the image collection device, a view image for each collection range during movement of the self-moving device at each image collection point includes:

[0040] rotating a preset angle with the initial image collection point as a rotation center;

[0041] collecting, by the image collection device, an initial view image for the collection range associated with the initial image collection point during rotation of the self-moving device at the initial image collection point.

[0042] In an example embodiment of the present disclosure, after collecting, by the image collection device, an initial view image for the collection range associated with the initial image collection point during rotation of the self-moving device at the initial image collection point, the method further includes:

[0043] marking the collection range associated with the initial image collection point as an initial searched area.

[0044] In an example embodiment of the present disclosure, the detecting whether the target object is contained in the view image according to the feature description information to obtain an object detection result includes:

[0045] detecting whether the target object is contained in the initial view image according to the feature description information to obtain an initial object detection result.

[0046] In the example embodiment of the present disclosure, after obtaining the initial object detection result, the object searching result for the target object is determined based on the object detection result, including:

[0047] If the initial object detection result indicates that the target object is contained in the initial view image, the initial searched region is marked as an appearance region of the target object in the pre-created scene map;

[0048] The marked appearance region and / or the initial view image are output as the object searching result for the target object.

[0049] In the example embodiment of the present disclosure, after the initial searched region is marked as the appearance region of the target object in the pre-created scene map, the method further includes:

[0050] The initial view image is re-shot at the initial image collection point;

[0051] The marked appearance region and / or the re-shot initial view image are determined as the object searching result for the target object.

[0052] In the example embodiment of the present disclosure, after obtaining the initial object detection result, the object searching result for the target object is determined based on the object detection result, including:

[0053] If the initial object detection result indicates that the target object is not contained in the initial view image, a target image collection point is selected from the planned multiple image collection points; the distance between the target image collection point and the initial image collection point is less than or equal to the second preset distance;

[0054] The self-moving device moves from the initial image collection point to the target image collection point, and the image collection device collects a next view image of a collection range associated with the target image collection point during the movement of the self-moving device at the target image collection point;

[0055] According to the feature description information, it is detected whether the target object is contained in the next view image, and a next object detection result is obtained;

[0056] The object searching result for the target object is determined based on the next object detection result.

[0057] In the example embodiment of the present disclosure, after the object searching result for the target object is determined based on the object detection result, the method further includes:

[0058] push the object searching result to an application and / or a user terminal corresponding to the self-moving device.

[0059] In an example embodiment of the present disclosure, the target object comprises a charging pile, and the object searching result comprises an appearance area of the charging pile.

[0060] After the object searching result is pushed to the application and / or the user terminal corresponding to the self-moving device, the method further comprises:

[0061] driving to the appearance area corresponding to the charging pile for charging.

[0062] In an example embodiment of the present disclosure, the object searching instruction comprises the following forms:

[0063] a control instruction issued by an application of the self-moving device;

[0064] a voice control instruction;

[0065] a control signal issued by a remote control device of the self-moving device;

[0066] The remote control device comprises a Bluetooth remote control device, an infrared remote control device and a radio frequency remote control device.

[0067] In an example embodiment of the present disclosure, the target object comprises one or more objects.

[0068] When the target object comprises multiple objects, any two objects of the multiple objects are of the same type or different types.

[0069] According to a second aspect of the present disclosure, a self-moving device is provided, the self-moving device is provided with an image acquisition device, and the self-moving device comprises:

[0070] an image acquisition module configured to acquire a viewfinder image of the self-moving device in a moving process by the image acquisition device after receiving an object searching instruction; the object searching instruction comprises feature description information of a target object to be searched;

[0071] an object searching module configured to detect whether the target object is contained in the viewfinder image according to the feature description information, obtain an object detection result, and determine an object searching result for the target object based on the object detection result.

[0072] According to a third aspect of the present disclosure, a computer storage medium is provided, and the computer storage medium stores a computer program, the computer program is executed by a processor to implement the object searching method of the first aspect.

[0073] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the object finding method of the first aspect described above via execution of the executable instructions.

[0074] From the above technical solutions, the object finding method, the self-moving device, the computer storage medium and the electronic device in the example embodiments of the present disclosure at least have the following advantages and positive effects:

[0075] In the technical solutions provided in some embodiments of the present disclosure, after receiving the object finding instruction (the object finding instruction contains the feature description information of the target object to be found), the image capturing device captures the framing image of the self-moving device during movement, detects whether the target object is contained in the framing image according to the feature description information, obtains the object detection result, and determines the object finding result for the target object based on the object detection result. On the one hand, the limitation that only objects with signal emission capability can be identified in the related art is overcome, the types and range of the target objects that can be found are expanded, and the coverage of the object finding is improved. On the other hand, the object finding result can be quickly output by capturing the image and detecting the image based on the feature description information. Not only the time and labor cost caused by manual finding of the target object are avoided, and the burden of manual finding is reduced, but also the target object can be accurately identified with the help of the feature description information, the possibility of misidentification is reduced, and the accuracy of the object finding result is improved.

[0076] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0077] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0078] FIG. 1 shows a flowchart of an object finding method in an embodiment of the present disclosure;

[0079] FIG. 2 shows a flowchart of how an image capturing device captures a framing image of a self-moving device during movement in a current scene in an embodiment of the present disclosure;

[0080] FIG. 3 shows a flowchart of how to plan multiple image capturing points in a current scene in an embodiment of the present disclosure;

[0081] FIG. 4 shows a schematic diagram of a plurality of image collection points planned in an embodiment of the present disclosure;

[0082] FIG. 5 shows a schematic diagram of a process of how an image collection device collects a framing image in an embodiment of the present disclosure;

[0083] FIG. 6 shows a schematic diagram of a process of how to determine a key search area from a current scene in an embodiment of the present disclosure;

[0084] FIG. 7 shows a schematic diagram of a process of how to determine an object search result based on an initial object detection result when the initial object detection result indicates that the target object is contained in an initial framing image in an embodiment of the present disclosure;

[0085] FIG. 8 shows a schematic diagram of a process of how to determine an object search result based on an initial object detection result when the initial object detection result indicates that the target object is not contained in an initial framing image in an embodiment of the present disclosure;

[0086] FIG. 9 shows a schematic diagram of a structure of a mobile device in an exemplary embodiment of the present disclosure;

[0087] FIG. 10 shows a schematic diagram of a structure of an electronic device in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0088] Example implementations are now described with reference to the drawings; however, these implementations are merely examples of implementations and are not intended to be limiting on the scope of what can be claimed. Rather, these implementations are intended to demonstrate example implementations considered by the inventors to be most useful, the scope of what can be claimed is intended to include one or more aspects of the example implementations as described herein, and one or more such aspects are described herein. It should be noted that the use of particular terminology when describing certain features or aspects of the example implementations should not be taken to indicate that such terminology is being redefined herein to be restricted to include any specific characteristics of the examples with that terminology, nor is a description of such with such terminology intended to exclude any embodiments falling within the scope of the present disclosure. Embodiments are described herein with reference to particular examples that at times can be discussed in a context of particular applications. Those of ordinary skill in the art will realize that the description of the example implementations is illustrative and is not intended to limit the scope of what can be claimed. Certain features and aspects described herein can be used separately or in any combination. Various modifications as well as combinations of features, aspects and / or functions of the described implementations can be made by those skilled in the art without departing from the scope of the present disclosure. Accordingly, the description is intended for purposes of illustration, not limitation, and this disclosure, including the description, is to be regarded as illustrative rather than restrictive.

[0089] The use of the terms "one," "a," "an" and "the" in this specification are intended to denote at least one of the items being described, rather than one or only a single item. The terms "including," "comprising," "having" and "containing" are intended to be permissive, and not to exclude or to limit the described implementations to the items listed. The terms "first," "second," and "third" and the like in the description and in the claims, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of use in either order.

[0090] In addition, the accompanying drawings are only schematic and are non-limiting illustrative embodiments of the disclosure, and are not necessarily drawn to scale. The same reference numerals in different drawings denote the same or similar functionalities for the sake of clarity and continuousness of the specification, thus repetitive description thereof will be omitted. Some of the block diagrams in the drawings are functional entities, which do not necessarily have to correspond to physically or logically independent entities.

[0091] In the related art, when the self-moving device attempts to return to the stake, but fails to receive the stake signal (e.g., infrared signal, pattern, etc.) at the recorded stake coordinate point, the automatic return-to-stake function cannot be implemented.

[0092] Therefore, the above scheme at least has the following defects: the object searching method is single, and the target object must have the ability to emit a signal or provide an identification mark, so that the signal can be used for searching. The dependence on the stake signal is too high, and the limitation is large.

[0093] In the embodiments of the disclosure, first, an object searching method is provided, which at least partially overcomes the defect that only objects capable of emitting a signal can be searched in the related art.

[0094] FIG. 1 shows a flowchart of an object searching method in the embodiments of the disclosure, and the execution subject of the object searching method can be a self-moving device.

[0095] Referring to FIG. 1, the object searching method according to one embodiment of the disclosure includes the following steps:

[0096] Step S110, after receiving an object searching instruction, an image acquisition device is used to acquire a view image of the self-moving device during movement; the object searching instruction contains feature description information of a target object to be searched.

[0097] Step S120, whether the target object is contained in the view image is detected according to the feature description information, an object detection result is obtained, and an object searching result for the target object is determined based on the object detection result.

[0098] In the technical solution provided in the embodiment shown in FIG. 1, after receiving an object searching instruction (the object searching instruction contains feature description information of a target object to be searched), a viewfinder image of the mobile device during movement is collected by an image collection device, whether the target object is contained in the viewfinder image is detected according to the feature description information, an object detection result is obtained, and an object searching result for the target object is determined based on the object detection result. On the one hand, the limitation that only objects with signal emission capability can be identified in the related art is overcome, the types and range of the target objects that can be searched are expanded, and the coverage of the object searching is improved. On the other hand, the object searching result can be quickly output by collecting the image and detecting the image based on the feature description information, which not only avoids the time consumption and labor cost caused by manual searching of the target object, reduces the burden of manual searching, but also accurately identifies the target object with the help of the feature description information, reduces the possibility of misidentification, and improves the accuracy of the object searching result.

[0099] The specific implementation process of each step in FIG. 1 is described in detail as follows:

[0100] Before step S110, it should be noted that the self-moving device (for example, a sweeping robot) in the present disclosure is provided with an image collection device, and the image collection device is used to collect images or videos. For example, the image collection device can be an RGB camera, which is a sensor that can capture images of multiple colors at high speed, and identify and measure the color and brightness of the surface of an object. RGB refers to red, green, and blue, and the increase or decrease of these three colors forms a variety of colors, so the RGB camera can capture very rich color images and videos.

[0101] In addition, the self-moving device in the present disclosure is also provided with a laser radar (Laser Direct Structuring, LDS), and the self-moving device can measure the distance between itself and obstacles in the surrounding environment through the laser radar, and then scan a complete map model according to the measured distance, and finally perform positioning and navigation according to the map model. In the present disclosure, the user can control the self-moving device to search for a specified target object by issuing an object searching instruction.

[0102] The above target object can be one or more objects (for example, a charging pile, a pet, a stool, money, a remote controller, etc.). When the object contains multiple objects, any two objects in the multiple objects are of the same type or different types, for example, a charging pile and a pet, a pet A (a cat) and a pet B (a dog), which can be set according to actual conditions, and the present disclosure does not make special limitations on this.

[0103] The object searching instruction can include feature description information of the target object to be searched. The feature description information can be the name, shape, size, color, high-frequency placement position, or picture of the target object, and can be set according to actual conditions, and the present disclosure does not make special limitations thereon. Since the feature description information can be flexibly customized, the present disclosure can adapt to the needs of different targets and scenes, so that the scheme has a wide application prospect.

[0104] The object searching instruction can include the following forms:

[0105] ①The control instruction is issued through an application program of the self-moving device. That is, the user can install an application program of the self-moving device on a collection device or other smart device, and input text, pictures, or the like through an operation interface of the application program to generate the control instruction.

[0106] ②The voice control instruction. That is, the user directly issues the instruction in the form of voice.

[0107] ③The control signal is issued through a remote control device of the self-moving device. The remote control device can be a Bluetooth remote control device, an infrared remote control device, a radio frequency remote control device, or the like, and can be set according to actual conditions, and the present disclosure does not make special limitations thereon.

[0108] After the user issues the object searching instruction, the self-moving device can receive the object searching instruction, and then execute step S110.

[0109] In step S110, after receiving the object searching instruction, the image acquisition device acquires the view image of the self-moving device during movement.

[0110] In this step, after receiving the object searching instruction, the self-moving device can acquire the view image of the self-moving device during movement through the image acquisition device.

[0111] In an optional embodiment, after receiving the object searching instruction, the self-moving device can directly execute the object searching instruction in the current scene, so that the image acquisition device can acquire the view image of the self-moving device during movement in the current scene. Specifically, referring to FIG. 2, FIG. 2 shows a flowchart of how the image acquisition device acquires the view image of the self-moving device during movement in the current scene in the embodiment of the present disclosure, including steps S201-S202.

[0112] In step S201, after receiving the object searching instruction, a plurality of image acquisition points are planned in the current scene.

[0113] In this step, after receiving the object finding instruction, the self-moving device can plan multiple image collection points in the current scene.

[0114] The image collection point is a fixed position for the self-moving device to collect the view image. It should be noted that each image collection point in the present disclosure is associated with a collection range, and each collection range can be a circular area with the above-mentioned each image collection point as the center and the first preset distance as the radius. When planning the above-mentioned multiple image collection points, it is necessary to ensure that the multiple collection ranges associated with the above-mentioned multiple image collection points can completely cover the above-mentioned current scene, so as to avoid the problem of blind area or dead angle.

[0115] It should be noted that the above-mentioned first preset distance (for example, which can be represented by r) can be determined according to the shooting range or coverable area range of the above-mentioned RGB camera. Preferably, in order to ensure that the collected view image is clear and visible, the above-mentioned first preset distance in the present disclosure can be a length value slightly smaller than the shooting range or coverable area range of the above-mentioned RGB camera, for example: assuming that the shooting range of the above-mentioned RGB camera is a circular area with a radius of 150 cm, the above-mentioned first preset distance in the present disclosure can be set to a length value slightly smaller than the above-mentioned 150 cm, for example: 130 cm. Specifically, it can be set according to the actual situation, and the present disclosure does not make special limitation thereto.

[0116] Referring to FIG. 3, FIG. 3 shows a flowchart of how to plan multiple image collection points in the current scene in the embodiment of the present disclosure, including steps S301-S303:

[0117] In step S301, the initial position of the self-moving device in the current scene is determined.

[0118] In this step, the self-moving device can determine the initial position of itself in the current scene (which can be the real-time position of the self-moving device at the moment when the object finding instruction is received, for example: position A).

[0119] In step S302, the initial position is determined as the initial image collection point, and the next image collection point is planned based on the initial image collection point and the preset point setting condition.

[0120] In this step, the above-mentioned initial position can be determined as the initial image collection point (for example: point 1), and then the next image collection point (for example: point 2) is planned based on the above-mentioned initial image collection point and the preset point setting condition.

[0121] The preset point position setting condition is used to constrain that a distance between the next image acquisition point position and the initial image acquisition point position is less than or equal to a second preset distance, and there is no obstacle in a collection range associated with the next image acquisition point position (whether there is an obstacle in the collection range associated with the next image acquisition point position can be determined according to an environmental scanning result of the laser radar LDS).

[0122] The second preset distance is greater than the first preset distance, and there is a numerical correlation relationship between the second preset distance and the first preset distance. For example, the numerical correlation relationship can be that the second preset distance is equal to twice the first preset distance. Taking the distance between the next image acquisition point position and the initial image acquisition point position as an example, the distance between the next image acquisition point position and the previous image acquisition point position is equal to 2r. When r is 130 cm, 2r is 2*130 cm.

[0123] In step S303, the next image acquisition point position is taken as a new initial image acquisition point position, and a new next image acquisition point position is planned based on the new initial image acquisition point position and the preset point position setting condition, until a plurality of image acquisition point positions are planned.

[0124] In this step, the next image acquisition point position can be taken as a new initial image acquisition point position (i.e., point position 2), and a new next image acquisition point position can be planned based on the new initial image acquisition point position and the preset point position setting condition (i.e., a new next image acquisition point position such as point position 3 can be planned according to the previous image acquisition point position and the preset point position setting condition). For example, a position with a distance equal to 2r from the point position 2 and no obstacle in the associated collection range can be determined as the point position 3. Similarly, the point position 4 can be determined based on the position of the point position 3 and the preset point position setting condition, until a plurality of image acquisition point positions are planned, so that the collection range covered by the plurality of image acquisition point positions can cover the current scene.

[0125] For example, referring to FIG. 4, FIG. 4 shows a schematic diagram of a plurality of image collection points (a total of 8 image collection points, numbered 1-8, the order of the numbers is only used to distinguish the image collection points, and does not represent the generation order when planning) planned in an embodiment of the present disclosure. As shown in FIG. 4, assuming that point 1 is the first image collection point planned, and points 2 and 5 are determined based on the position of point 1 and the preset point setting conditions, then the distance between point 2 and point 1 is 2r, and the distance between point 5 and point 1 is also 2r. Similarly, if point 3 and point 6 are determined based on the position of point 2 and the preset point setting conditions, then the distance between point 3 and point 2 is 2r, and the distance between point 6 and point 2 is also 2r.

[0126] After the above-mentioned plurality of image collection points are planned, the image collection device can then collect the view images of each collection range during the movement of the self-moving device at each image collection point in step S202 of FIG. 2.

[0127] In this step, the self-moving device can rotate a preset angle (for example: 360 degrees or an integer multiple of 360 degrees, which can be set according to actual conditions) around each image collection point as a rotation center, and collect the view images of the collection range associated with each image collection point during the rotation of the self-moving device at each image collection point by the image collection device. For details, please refer to the related explanation of step S503 below.

[0128] In another optional embodiment, after receiving the object finding instruction, the self-moving device can first determine a key finding area from the current scene, and then move from the initial position in the current scene to the key finding area, and execute the above-mentioned object finding instruction in the key finding area, so that the image collection device can collect the view images during the movement of the self-moving device in the key finding area.

[0129] The key finding area is the area or range where the target object is most likely to be found. By setting the key finding area, the self-moving device can quickly find the target object, save time, and improve the object finding efficiency. For example, the present disclosure can set a higher finding priority for the key finding area (the finding priority is used to represent the order of the self-moving device finding the target object in different areas of the current scene), and a lower finding priority for the non-key finding area, so that the self-moving device can preferentially find the target object from the key finding area. If the target object is not found in the key finding area, the self-moving device can continue to find in other non-key finding areas or terminate the task and directly generate the object finding result.

[0130] Specifically, referring to FIG. 5, FIG. 5 shows a flowchart illustrating how the image acquisition device acquires the view image during the movement of the mobile device in the key search area according to an embodiment of the present disclosure, including steps S501-S503:

[0131] In step S501, the key search area is determined from the current scene.

[0132] In this step, referring to FIG. 6, FIG. 6 shows a flowchart illustrating how the key search area is determined from the current scene according to an embodiment of the present disclosure, including steps S601-S603:

[0133] In step S601, it is detected whether the specified search area for the target object is included in the object search instruction.

[0134] In this step, the mobile device can detect whether the specified search area for the target object is included in the object search instruction. The specified search area can be an area where the target object is often placed or often appears.

[0135] In step S602, if the specified search area is included in the object search instruction, the specified search area is determined as the key search area.

[0136] In this step, if it is detected that the specified search area is included in the object search instruction, the mobile device can directly determine the specified search area as the key search area.

[0137] In step S603, if the specified search area is not included in the object search instruction, the historical search record is searched 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.

[0138] In this step, if it is detected that the specified search area is not included in the object search instruction, the mobile device can search 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.

[0139] The historical search record can be used to store the mapping relationship between the feature description information of the historical search object and the search result thereof. The search result can include the historical appearance area of the historical search object, and the historical appearance area is the position area where the target object has appeared in the past or has been placed frequently in the past.

[0140] It should be noted that, assuming that multiple historical appearance regions are retrieved in the historical search record, for example: a, b and c, the mobile device can also count the number of appearances corresponding to each historical appearance region, and then determine the search priority of the multiple historical appearance regions according to the number of appearances, so as to determine which historical appearance region to search first according to the search priority, thereby improving the object search efficiency.

[0141] After the key search region is determined, the mobile device can be moved from the initial position in the current scene to the key search region, and a plurality of image collection points can be planned in the key search region, as shown in FIG. 5.

[0142] In this step, the mobile device can move from the initial position in the current scene to the key search region. After moving into the key search region, the collection frequency of the image collection device can be controlled to increase from the first frequency to the second frequency, or the image resolution of the image collection device can be controlled to increase from the first resolution to the second resolution, or the mobile device can also automatically adjust the number of traversals at each image collection point to two or more times, so as to focus on searching for the target object in the key search region. The specific implementation can be set by the actual situation, and the present disclosure does not make special limitations on this.

[0143] After moving into the key search region, the mobile device can plan a plurality of image collection points in the key region.

[0144] Specifically, the mobile device can first determine the initial position (for example: position B) of itself in the key search region, and then refer to the related explanations of step S201 to determine the initial position as the initial image collection point. The next image collection point is planned based on the initial image collection point and the preset point setting condition (the preset point setting condition is used to constrain the distance between the next image collection point and the initial image collection point to be less than or equal to the second preset distance and there is no obstacle in the collection range associated with the next image collection point). After that, the next image collection point can be determined as a new initial image collection point, and a new next image collection point is planned based on the new initial image collection point and the preset point setting condition, until a plurality of image collection points are planned.

[0145] It should be noted that each image collection point is associated with a collection range, and each collection range is a circular region with the image collection point as the center and the first preset distance (r) as the radius. The multiple collection ranges associated with the multiple image collection points can completely cover the key search region.

[0146] In step S503, the image capturing device is used to capture a view image of each capturing range during the movement of the mobile device at each image capturing point.

[0147] In this step, the mobile device can rotate each image capturing point as a rotation center by a preset angle (for example, 360 degrees or an integer multiple of 360 degrees, which can be set according to actual conditions), and the image capturing device is used to capture a view image of the capturing range associated with each image capturing point during the rotation of the mobile device at each image capturing point.

[0148] Specifically, the mobile device can first select an initial image capturing point from the planned multiple image capturing points, and then rotate the initial image capturing point as a rotation center by a preset angle (for example, 360 degrees or an integer multiple of 360 degrees, which can be set according to actual conditions), and the image capturing device is used to capture an initial view image of the capturing range associated with the initial image capturing point during the rotation of the mobile device at the initial image capturing point.

[0149] After the initial view image of the mobile device during the rotation at the initial image capturing point is captured by the image capturing device, the mobile device can mark the capturing range associated with the initial image capturing point as an initial found area, based on which the problem of time-consuming finding caused by repeated finding of a certain area can be avoided.

[0150] After obtaining the initial view image, step S120 can be entered to detect whether the target object is included in the view image according to the feature description information, obtain an object detection result, and determine an object finding result for the target object based on the object detection result.

[0151] In this step, the mobile device can detect whether the target object is included in the initial view image based on the feature description information included in the object finding instruction, and obtain an initial object detection result. For example, a trained object recognition model can be pre-deployed in the mobile device, and based on the object recognition model, the initial view image can be feature-extracted, and then the extracted features can be classified or matched to output the initial object detection result, which can represent whether the target object is included in the initial view image.

[0152] After obtaining the initial object detection result, the object finding result for the target object can be determined based on the initial object detection result.

[0153] Specifically, for the case that the initial object detection result represents that the initial framing image contains the target object, the object finding result for the target object can be determined by referring to the processing flow shown in FIG. 7; and for the case that the initial object detection result represents that the initial framing image does not contain the target object, the object finding result for the target object can be determined by referring to the processing flow shown in FIG. 8.

[0154] First, referring to FIG. 7, FIG. 7 shows a flowchart of how to determine the object finding result based on the initial object detection result when the initial object detection result represents that the initial framing image contains the target object, which includes steps S701-S702:

[0155] In step S701, the initial found sub-region is marked as the appearance region of the target object in the pre-created scene map.

[0156] In this step, the initial found sub-region can be marked as the appearance region of the target object in the pre-created scene map. The scene map can be a map created by the mobile device using sensors and algorithms before cleaning in the room, which can contain the layout of the room, the position of furniture, and other information.

[0157] In step S702, the marked appearance region and / or the initial framing image are output as the object finding result for the target object.

[0158] In this step, in an optional embodiment, the marked appearance region and / or the initial framing image can be output as the object finding result for the target object.

[0159] In another optional embodiment, for example, after marking the appearance region of the target object, the shooting resolution of the RGB camera can be improved, and then the initial framing image can be re-shot at the initial image collection point, and then the marked appearance region and / or the re-shot initial framing image are determined as the object finding result for the target object.

[0160] Next, referring to FIG. 8, FIG. 8 shows a flowchart of how to determine the object finding result based on the initial object detection result when the initial object detection result represents that the initial framing image does not contain the target object, which includes steps S801-S804:

[0161] In step S801, the target image collection point is selected from the planned multiple image collection points.

[0162] In this step, when the target image acquisition point is selected from the planned multiple image acquisition points, the point with a distance from the initial image acquisition point less than or equal to the second preset distance (2r) can be determined as the target image acquisition point.

[0163] Based on the above strategy to determine the target image acquisition point, the self-moving device can preferentially search the area close to the current position, ensuring that the self-moving device can quickly and efficiently move to a new position for image acquisition. On the one hand, this avoids repeated ineffective searches and unnecessary movement, improving search efficiency. Further, considering that the time and power of the self-moving device are limited, the power distribution of the self-moving device can be more reasonably utilized, prolonging the use time of the self-moving device. On the other hand, the multi-point and multi-angle image acquisition strategy helps to achieve comprehensive coverage and accurate detection, avoiding the problem of missing search dead angles during the search process and improving the completeness of the search.

[0164] In step S802, the self-moving device moves from the initial image acquisition point to the target image acquisition point, and the image acquisition device acquires the next view image of the target image acquisition point associated with the acquisition range during the movement of the self-moving device at the target image acquisition point.

[0165] In this step, the self-moving device can move from the initial image acquisition point to the target image acquisition point, and then rotate 360 degrees around the target image acquisition point as the center to acquire the next view image of the target image acquisition point associated with the acquisition range during the rotation of the self-moving device at the target image acquisition point.

[0166] In step S803, it is detected whether the target object is included in the next view image according to the feature description information, and a next object detection result is obtained.

[0167] In this step, after obtaining the next view image, the self-moving device can again call the object recognition model to detect whether the target object is included in the next view image based on the feature description information included in the object finding instruction, and obtain a next object detection result.

[0168] In step S804, an object finding result for the target object is determined based on the next object detection result.

[0169] In this step, the self-moving device can determine the object finding result for the target object based on the next object detection result. Specifically, when the next object detection result indicates that the target object is included in the next view image, the collection range associated with the target image collection point can be directly marked as the appearance area of the target object in the pre-created scene map. Then, the marked appearance area and / or the next initial view image are output as the object finding result for the target object. When the next object detection result indicates that the target object is not included in the next view image, the next target image collection point can be determined again until the next target image collection point is the last image collection point in the pre-planned multiple image collection points, or the next view image corresponding to the collection range associated with the target image collection point includes the target object, and the finding of the target object is terminated.

[0170] If the last view image corresponding to the collection range associated with the last image collection point still does not include the target object, it can be determined that the finding result of the target object is not found.

[0171] After determining the object finding result for the target object based on the object detection result, the present disclosure can push the object finding result to the application program corresponding to the self-moving device and / or the user terminal. For example, the object finding result can be displayed on the reminder interface of the application program, or the user can be informed in the form of voice reply. The present disclosure does not make special limitations on this.

[0172] It should be noted that when the target object is a charging pile, if the object finding result includes the appearance area of the charging pile, after the object finding result is pushed to the application program corresponding to the self-moving device and / or the user terminal, the self-moving device can automatically go to the appearance area corresponding to the charging pile for charging.

[0173] It should be further explained that, when the target object in the object searching instruction contains two or more objects, exemplary, taking the characteristic description information containing object A, object B and object C in the object searching instruction as an example, in an optional embodiment, the self-moving device can detect whether object A, object B and object C are contained in each view image after obtaining the view image, if any specified object (for example, object A) is contained, the position of the specified object can be marked, and the specified object (object A) is excluded from the objects to be searched, then the next view image is collected, and whether object B and object C are contained in the view image is detected, until the above three objects are found or the current scene is traversed, the task is ended, and the object searching result (which can be a success result that all three objects are found, or a failure result that all three objects are not found, or a result that part of the objects are found and part of the objects are not found) is output. In another optional embodiment, the self-moving device can first detect whether object A is contained in the view image after obtaining each view image, end the task of searching for object A when object A is found or the current scene is traversed, then collect the view image in the current scene, detect whether object B is contained in the view image, end the task of searching for object B when object B is found or the current scene is traversed, and finally collect the view image in the current scene, detect whether object C is contained in the view image, and end the task of searching for object C when object C is found or the current scene is traversed. The above methods can be set according to actual conditions, and the present disclosure does not specially limit this.

[0174] Based on the above technical solutions, the present disclosure has at least the following technical effects:

[0175] First, the target object is searched by responding to the object searching instruction, which overcomes the limitation that only objects with signal emission capability can be identified in the related art, expands the types and range of target objects that can be searched, and improves the search coverage;

[0176] Second, by pre-planning a plurality of image collection points capable of covering the search area, then rotating 360 degrees at each image collection point to obtain a view image at each image collection point, and then moving to a target image collection point with a distance less than or equal to a second preset distance from the current image collection point to continue searching for the target object, it can avoid dead angles in searching, and ensure that the search area covers every corner of the environment;

[0177] Thirdly, by determining a key search area (i.e. a specified search area of the target object or a historical appearance area of the target object) from a current scene, the target object is preferentially searched in the key search area, which can assist the self-moving device to quickly find the target object, save time for object searching, and improve object searching efficiency.

[0178] The present disclosure also provides a self-moving device, which is provided with an image acquisition device, and a structure schematic diagram of the self-moving device in an exemplary embodiment of the present disclosure is shown in FIG. 9. As shown in FIG. 9, the self-moving device 900 can include an image acquisition module 910 and an object searching module 920. Wherein:

[0179] The image acquisition module 910 is configured to acquire a view image of the self-moving device in a moving process by the image acquisition device after receiving an object searching instruction; the object searching instruction contains feature description information of a target object to be searched.

[0180] The object searching module 920 is configured to detect whether the target object is contained in the view image according to the feature description information, obtain an object detection result, and determine an object searching result for the target object based on the object detection result.

[0181] In an exemplary embodiment of the present disclosure, the image acquisition module 910 acquires a view image of the self-moving device in a moving process by the image acquisition device after receiving an object searching instruction, which includes:

[0182] After receiving an object searching instruction, a plurality of image acquisition points are planned in a current scene; each image acquisition point is associated with an acquisition range, and each acquisition range is a circular area with the image acquisition point as the center and a first preset distance as the radius; the plurality of acquisition ranges associated with the plurality of image acquisition points cover the current scene;

[0183] The view image for each acquisition range in the moving process of the self-moving device at each image acquisition point is acquired by the image acquisition device.

[0184] In an exemplary embodiment of the present disclosure, the image acquisition module 910 plans a plurality of image acquisition points in a current scene, which includes:

[0185] An initial position of the self-moving device in the current scene is determined;

[0186] The initial position is determined as an initial image acquisition point, and a next image acquisition point is planned based on the initial image acquisition point and a preset point setting condition;

[0187] set the next image acquisition point as a new initial image acquisition point, and plan a new next image acquisition point based on the new initial image acquisition point and the preset point setting condition, until the plurality of image acquisition points are planned;

[0188] The preset point setting condition is used to constrain that a distance between the next image acquisition point and the initial image acquisition point is less than or equal to a second preset distance, and there is no obstacle in a collection range associated with the next image acquisition point. The second preset distance is greater than the first preset distance, and there is a numerical correlation between the second preset distance and the first preset distance.

[0189] In an example embodiment of the present disclosure, the image acquisition module 910 acquires a view image of the self-moving device in the moving process through the image acquisition device after receiving the object finding instruction, including:

[0190] determining a key finding area from the current scene; the key finding area corresponds to a finding priority higher than other areas in the current scene, and the finding priority is used to represent the order of finding the target object in different areas of the current scene;

[0191] moving from an initial position in the current scene to the key finding area, and planning a plurality of image acquisition points in the key finding area; each image acquisition point is associated with a collection range, and each collection range is a circular area with the image acquisition point as the center and a first preset distance as the radius; the plurality of collection ranges associated with the plurality of image acquisition points cover the key finding area;

[0192] acquiring a view image of the self-moving device in the moving process at each image acquisition point through the image acquisition device, for each collection range.

[0193] In an example embodiment of the present disclosure, the image acquisition module 910 determines a key finding area from the current scene, including:

[0194] detecting whether the object finding instruction contains a specified finding area for the target object;

[0195] If the object finding instruction contains the specified finding area, the specified finding area is determined as the key finding area.

[0196] In an example embodiment of the present disclosure, the image acquisition module 910 is configured to:

[0197] If the object searching instruction does not contain the specified searching area, historical searching records are retrieved according to the feature description information to obtain a historical appearance area of the target object;

[0198] The historical appearance area is determined as the key searching area;

[0199] The historical searching records are used to store a mapping relationship between feature description information of a historical searching object and a searching result of the historical searching object, and the searching result contains a historical appearance area of the historical searching object.

[0200] In the exemplary embodiments of the present disclosure, after moving from an initial position in the current scene to the key searching area, the image acquisition module 910 is configured to:

[0201] Control the acquisition frequency of the image acquisition device to increase from a first frequency to a second frequency.

[0202] In the exemplary embodiments of the present disclosure, the image acquisition module 910 plans a plurality of image acquisition points in the key searching area, including:

[0203] Determine an initial position of the self-moving device in the key searching area;

[0204] Determine the initial position as an initial image acquisition point, and plan a next image acquisition point based on the initial image acquisition point and a preset point setting condition;

[0205] Take the next image acquisition point as a new initial image acquisition point, and plan a new next image acquisition point based on the new initial image acquisition point and the preset point setting condition, until the plurality of image acquisition points are planned;

[0206] The preset point setting condition is used to constrain the distance between the next image acquisition point and the initial image acquisition point to be less than or equal to a second preset distance, and there is no obstacle in the acquisition range associated with the next image acquisition point. The second preset distance is greater than the first preset distance, and there is a numerical relationship between the second preset distance and the first preset distance.

[0207] In the exemplary embodiments of the present disclosure, the image acquisition module 910 acquires a viewfinder image for each acquisition range in the movement of the self-moving device at each image acquisition point through the image acquisition device, including:

[0208] Rotate a preset angle with the initial image acquisition point as the rotation center;

[0209] acquire, by the image acquisition device, an initial view image of a collection range associated with the initial image acquisition point, in a process in which the self-moving device rotates at the initial image acquisition point.

[0210] In an example embodiment of the present disclosure, after acquiring, by the image acquisition device, an initial view image of a collection range associated with the initial image acquisition point, in a process in which the self-moving device rotates at the initial image acquisition point, the image acquisition module 910 is configured to:

[0211] mark the collection range associated with the initial image acquisition point as an initial found area.

[0212] In an example embodiment of the present disclosure, the detecting whether the target object is contained in the view image according to the feature description information to obtain an object detection result comprises:

[0213] detecting whether the target object is contained in the initial view image according to the feature description information to obtain an initial object detection result.

[0214] In an example embodiment of the present disclosure, after obtaining the initial object detection result, the object finding module 920 determines an object finding result for the target object based on the object detection result, comprising:

[0215] if the initial object detection result indicates that the target object is contained in the initial view image, marking the initial found area as an appearance area of the target object in a pre-created scene map;

[0216] outputting the marked appearance area and / or the initial view image as the object finding result for the target object.

[0217] In an example embodiment of the present disclosure, after marking the initial found area as the appearance area of the target object in the pre-created scene map, the image acquisition module 910 is configured to:

[0218] re-shoot the initial view image at the initial image acquisition point;

[0219] determining the marked appearance area and / or the re-shot initial view image as the object finding result for the target object.

[0220] In an example embodiment of the present disclosure, after obtaining the initial object detection result, the object finding module 920 determines an object finding result for the target object based on the object detection result, comprising:

[0221] If the initial object detection result represents that the target object is not contained in the initial view image, a target image capture point is selected from the planned multiple image capture points, and a distance between the target image capture point and the initial image capture point is less than or equal to the second preset distance.

[0222] The self-moving device moves from the initial image capture point to the target image capture point, and the image capture device captures a next view image of a capture range associated with the target image capture point during movement of the self-moving device at the target image capture point.

[0223] According to the feature description information, it is detected whether the target object is contained in the next view image, and a next object detection result is obtained.

[0224] Based on the next object detection result, an object finding result for the target object is determined.

[0225] In an example embodiment of the present disclosure, after determining the object finding result for the target object based on the object detection result, the object finding module 920 is configured to:

[0226] The object finding result is pushed to an application program and / or a user terminal corresponding to the self-moving device.

[0227] In an example embodiment of the present disclosure, the target object includes a charging pile, and the object finding result includes an appearance area of the charging pile.

[0228] After pushing the object finding result to the application program and / or the user terminal corresponding to the self-moving device, the object finding module 920 is configured to:

[0229] Go to the appearance area corresponding to the charging pile to charge.

[0230] In an example embodiment of the present disclosure, the object finding instruction has the following forms:

[0231] A control instruction issued through an application program of the self-moving device;

[0232] A voice control instruction;

[0233] A control signal issued through a remote control device of the self-moving device;

[0234] The remote control device includes a Bluetooth remote control device, an infrared remote control device, and a radio frequency remote control device.

[0235] In an example embodiment of the present disclosure, the target object includes one or more objects.

[0236] When the target object comprises a plurality of objects, any two objects of the plurality of objects are of the same type or different types.

[0237] The specific details of the modules in the self-moving device have been described in detail in the corresponding object searching method, and thus will not be described here again.

[0238] It should be noted that, although several modules or units of the device for action execution are mentioned in the foregoing detailed description, such a division is not mandatory. Indeed, according to embodiments of the disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into several modules or units embodied.

[0239] In addition, although the steps of the method in the disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired result. In addition or alternatively, some steps can be omitted, a plurality of steps can be combined into one step, and / or one step can be divided into a plurality of steps, etc.

[0240] Through the above description of the embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a plurality of instructions to make a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) execute the method according to the embodiments of the disclosure.

[0241] The present application also provides a computer readable storage medium, which can be included in the electronic device described in the embodiments; or can exist separately without being assembled into the electronic device.

[0242] A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus, or device.

[0243] A computer readable storage medium can be transmitted, propagated, or transferred for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0244] A computer readable storage medium can be transmitted, propagated, or transferred for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0245] Furthermore, an electronic device capable of implementing the above method is also provided in the embodiments of the present disclosure.

[0246] Those skilled in the art can understand that each aspect of the present disclosure can be implemented as a system, a method or a program product. Therefore, each aspect of the present disclosure can be embodied as a whole hardware embodiment, a whole software embodiment (including firmware, microcode, etc.), or an embodiment of combination of hardware and software, which can be collectively referred to as "circuitry", "module" or "system".

[0247] The electronic device 1000 according to this embodiment of the present disclosure is described below with reference to FIG. 10. FIG. 10 shows the electronic device 1000 only as an example, and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.

[0248] As shown in FIG. 10, the electronic device 1000 is in the form of a general computing device. The components of the electronic device 1000 can include, but are not limited to, the at least one processing unit 1010, the at least one storage unit 1020, a bus 1030 connecting different system components (including the storage unit 1020 and the processing unit 1010), and a display unit 1040.

[0249] The storage unit stores program codes which can be executed by the processing unit 1010, so that the processing unit 1010 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of the present specification. For example, the processing unit 1010 can perform the steps as shown in FIG. 1: step S110, after receiving an object searching instruction, capturing a viewfinder image of the mobile device during movement by an image capturing device; the object searching instruction contains feature description information of a target object to be searched; step S120, detecting whether the target object is contained in the viewfinder image according to the feature description information, obtaining an object detection result, and determining an object searching result for the target object based on the object detection result.

[0250] The storage unit 1020 can include a readable medium in the form of volatile storage unit, such as a random access memory (RAM) 10201 and / or a cache memory 10202, and can further include a read-only memory (ROM) 10203.

[0251] The storage unit 1020 can further include a program / utility 10204 having a set (at least one) of program modules 10205, such as an operating system, one or more application programs, other program modules, and program data, and each of these examples, or some combination thereof, can include implementation of a network environment.

[0252] The bus 1030 can represent one or more of several types of bus structures, including a storage unit bus or bus controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus architectures.

[0253] The electronic device 1000 can also communicate with one or more external devices 1100 such as a keyboard, a pointing device, a Bluetooth device, etc.; and / or one or more devices that enable a user to interact with the electronic device 1000; and / or one or more devices (e.g. routers, modems, etc.) that enable the electronic device 1000 to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface 1050. Still yet, the electronic device 1000 can communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or the Internet) through network adapter 1060. As depicted, network adapter 1060 communicates with the other components of the electronic device 1000 via bus 1030. It should be appreciated that although not shown, other hardware and / or software modules could be used in connection with the electronic device 1000. Such modules include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0254] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A target searching method, executed by a self-moving device provided with an image acquisition device, comprising: acquiring, by the image acquisition device, a view image of the self-moving device in a moving process after receiving a target searching instruction; the target searching instruction containing feature description information of a target object to be searched for; detecting whether the target object is contained in the view image according to the feature description information, obtaining a target detection result, and determining a target searching result for the target object based on the target detection result.

2. The method of claim 1, wherein, the acquiring, by the image acquisition device, a view image of the self-moving device in a moving process after receiving a target searching instruction, comprising: planning a plurality of image acquisition points in a current scene after receiving a target searching instruction; each of the image acquisition points is associated with an acquisition range, and each of the acquisition ranges is a circular region with the image acquisition point as the center and a first preset distance as the radius; the plurality of acquisition ranges associated with the plurality of image acquisition points cover the current scene; acquiring, by the image acquisition device, a view image for each acquisition range in the moving process of the self-moving device at each image acquisition point.

3. The method of claim 2, wherein, the planning a plurality of image acquisition points in a current scene, comprising: determining an initial position of the self-moving device in the current scene; determining the initial position as an initial image acquisition point, planning a next image acquisition point based on the initial image acquisition point and a preset point setting condition; taking the next image acquisition point as a new initial image acquisition point, and planning a new next image acquisition point based on the new initial image acquisition point and the preset point setting condition, until the plurality of image acquisition points are planned; wherein the preset point setting condition is used to constrain that a distance between the next image acquisition point and the initial image acquisition point is less than or equal to a second preset distance and there is no obstacle in the acquisition range associated with the next image acquisition point; the second preset distance is greater than the first preset distance and there is a numerical correlation between the second preset distance and the first preset distance.

4. The method of claim 1, wherein, the acquiring, by the image acquisition device, a view image of the self-moving device in a moving process after receiving a target searching instruction, comprising: determining a key searching area from a current scene; the key searching area corresponds to a searching priority higher than that of other areas in the current scene, and the searching priority is used to represent a sequence of searching the target object in different areas of the current scene by the self-moving device. moving from an initial position in the current scene to the key search area, and planning a plurality of image collection points in the key search area; each of the image collection points is associated with a collection range, and each of the collection ranges is a circular area with the image collection point as the center and a first preset distance as the radius; the plurality of collection ranges associated with the plurality of image collection points cover the key search area; collecting, by the image collection device, a view image for each of the collection ranges in the movement of the self-moving device at each of the image collection points.

5. The method of claim 4, wherein, The determining of the key search area from the current scene includes: detecting whether the specified search area for the target object is contained in the object search instruction; if the specified search area is contained in the object search instruction, determining the specified search area as the key search area.

6. The method of claim 5, further comprising: if the specified search area is not contained in the object search instruction, retrieving a historical search record according to the feature description information to obtain a historical appearance area of the target object; determining the historical appearance area as the key search area; wherein the historical search record is used to store a mapping relationship between the feature description information of a historical search object and a search result of the historical search object, and the search result contains the historical appearance area of the historical search object.

7. The method of claim 4, wherein, After moving from the initial position in the current scene to the key search area, the method further includes: controlling the collection frequency of the image collection device to increase from a first frequency to a second frequency.

8. The method of claim 4, wherein, The planning of the plurality of image collection points in the key search area includes: determining an initial position of the self-moving device in the key search area; determining the initial position as an initial image collection point, planning a next image collection point based on the initial image collection point and a preset point setting condition; taking the next image collection point as a new initial image collection point, and planning a new next image collection point based on the new initial image collection point and the preset point setting condition, until the plurality of image collection points are planned; wherein the preset point setting condition is used to constrain the distance between the next image collection point and the initial image collection point to be less than or equal to a second preset distance, and there is no obstacle in the collection range associated with the next image collection point; the second preset distance is greater than the first preset distance, and there is a numerical correlation between the second preset distance and the first preset distance.

9. The method of claim 3 or 8, wherein, The collecting of the view image for each of the collection ranges in the movement of the self-moving device at each of the image collection points by the image collection device includes: rotating the initial image collection point as a rotation center by a preset angle; collecting, by the image collection device, an initial view image for the collection range associated with the initial image collection point in the rotation of the self-moving device at the initial image collection point.

10. The method of claim 9, wherein, After the initial framing image of the collection range associated with the initial image collection point is collected by the image collection device, the method further comprises: Marking the collection range associated with the initial image collection point as an initial found area.

11. The method of claim 10, wherein, The method further comprises: Detecting whether the initial framing image contains the target object according to the feature description information to obtain an initial object detection result.

12. The method of claim 11, wherein, After the initial object detection result is obtained, the method further comprises: If the initial object detection result indicates that the initial framing image contains the target object, marking the initial found area as an appearance area of the target object in a pre-created scene map. Outputting the marked appearance area and / or the initial framing image as the object finding result for the target object.

13. The method of claim 12, wherein, After the initial found area is marked as the appearance area of the target object in the pre-created scene map, the method further comprises: Re-shooting the initial framing image at the initial image collection point; Determining the marked appearance area and / or the re-shot initial framing image as the object finding result for the target object.

14. The method of claim 11, wherein, After the initial object detection result is obtained, the method further comprises: If the initial object detection result indicates that the initial framing image does not contain the target object, screening a target image collection point from the planned multiple image collection points; the distance between the target image collection point and the initial image collection point is less than or equal to the second preset distance. Moving from the initial image collection point to the target image collection point, and collecting a next framing image of a collection range associated with the target image collection point by the image collection device during movement of the self-moving device at the target image collection point; Detecting whether the next framing image contains the target object according to the feature description information to obtain a next object detection result; Determining the object finding result for the target object based on the next object detection result.

15. The method of claim 1, wherein, After the object finding result for the target object is determined based on the object detection result, the method further comprises: Pushing the object finding result to an application program corresponding to the self-moving device and / or a user terminal.

16. The method of claim 15, wherein, The target object includes a charging pile, and the object finding result includes an appearance area of the charging pile. After the object finding result is pushed to the application program corresponding to the self-moving device and / or the user terminal, the method further comprises: Going to the appearance area corresponding to the charging pile for charging.

17. The method of claim 1, wherein, The object finding instruction includes the following forms: A control instruction issued through an application program of the self-moving device; A voice control instruction; a control signal sent by a remote control device of the self-moving device; wherein the remote control device comprises a Bluetooth remote control device, an infrared remote control device and a radio frequency remote control device.

18. The method of claim 1, wherein, The target object comprises one or more objects. When the target object comprises multiple objects, any two objects in the multiple objects are of the same type or different types. 19.A self-moving device, comprising: an image acquisition device; an image acquisition module configured to acquire a view image of the self-moving device in a moving process by the image acquisition device after receiving an object searching instruction; the object searching instruction comprising feature description information of a target object to be searched; an object searching module configured to detect whether the target object is included in the view image according to the feature description information, obtain an object detection result, and determine an object searching result for the target object based on the object detection result.

20. A computer storage medium having stored thereon a computer program, wherein, The computer program, when executed by a processor, implements the object searching method of any one of claims 1-18.

Images