Counting method and device for refrigeration equipment, refrigeration equipment and computer readable storage medium

Abstract

The invention relates to the technical field of intelligent household appliances, and discloses a counting method for refrigeration equipment, and the method comprises the steps: obtaining an image of a recognition region in response to a counting request; wherein the identification area comprises an article identification area and a mirror image area of the article identification area; determining an article identification area in the identification area; and under the condition that m is greater than or equal to m0, calculating the number of the target articles based on the article identification area. Wherein m is the frame number of the image of the identification area, m0 is an image frame number threshold value, and m0 is larger than or equal to 2. According to the counting method for the refrigeration equipment, the object identification area is limited, and the target objects of other parts except the object identification area are not counted in the counting range, so that the object mirror images formed by reflection of the cabinet door are filtered out, and the accuracy of counting the number of the target objects in the refrigeration equipment is further improved. The invention further discloses a counting device for the refrigeration equipment, the refrigeration equipment and a computer readable storage medium.

Description

Technical Field

[0001] The present application relates to the technical field of smart home appliances, for example, to a counting method and device for refrigeration equipment, refrigeration equipment, and a computer-readable storage medium. Background Art

[0002] At present, when smart vending machines based on visual images on the market realize the process of taking, putting back, identifying and detecting the quantity of items in the refrigerator, the reflection of the glass door of the refrigerator often forms an image of the items, which affects the calculation of the actual number of items taken out of the refrigerator, causing users to pay more or less, affecting the experience.

[0003] In the related art, a counting method is commonly provided for forming an image of an object by using the reflection of a glass door to improve the accuracy of counting the number of target objects in a refrigerator, comprising: obtaining an image of a food storage area in response to a counting request; 0 In the case of, determining the motion trajectory of the target food; calculating the number of target food in the food storage area according to the motion trajectory of the target food; wherein, m is the number of frames of the image of the food storage area, m 0 is the image frame number threshold and m 0 ≥3.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] Determining the movement trajectory of the target food by using images of the multi-frame storage area can extend the movement trajectory and thus improve the accuracy of counting the number of target items in the refrigerator. However, there is still a situation where the object mirror image is used as the target object, and the impact of the object mirror image on the statistical accuracy cannot be avoided.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a counting method and device for a refrigeration device, a refrigeration device, and a computer-readable storage medium to further improve the accuracy of counting the number of target items in the refrigeration device.

[0009] In some embodiments, the method includes: in response to a counting request, acquiring an image of a recognition area; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area; determining an object recognition area in the recognition area; and when m≥m 0 In the case of , the number of target objects is calculated based on the object recognition area. Where m is the number of frames of the image in the recognition area, m 0 is the image frame number threshold and m 0 ≥2.

[0010] Optionally, the image of the identified area includes: a plurality of frames of overhead images of the identified area.

[0011] Optionally, the step of determining the object identification area in the identification area includes: determining the intersection point of the door body boundary and the box body boundary based on multiple frames of overhead view images; controlling the intersection point to extend into a line in a direction perpendicular to the box body boundary to divide the overhead view image into two parts; and using the portion of the overhead view image containing the box body boundary as the object identification area.

[0012] Optionally, the step of calculating the number of target objects based on the object identification area includes: determining movement trajectories of the target objects in the object identification area; and calculating the number of the target objects according to the movement trajectories of the target objects.

[0013] Optionally, the step of determining the motion trajectory of the target object in the object identification area includes: detecting an object whose position has changed based on multiple frames of overhead images; if the object whose position has changed is located in the object identification area, treating the object as a target object; and generating the motion trajectory of the target object based on the position information of the target object.

[0014] Optionally, when the object whose position has changed is located within the object identification area, the step of treating the object as the target object includes: marking the object whose position has changed in multiple frames of overhead images with an identification frame; and when the identification frame is located within the object identification area, treating the object as the target object.

[0015] Optionally, determine whether the target frame is located in the object identification area in the following manner: establish a coordinate system of the object identification area with the intersection point as the origin based on multiple frames of overhead view images; obtain the coordinates of the object identification area and the identification frame; and determine that the identification frame is located in the object identification area when the coordinate value of the identification frame is less than the coordinate value of the object identification area.

[0016] Optionally, the step of obtaining the coordinates of the object recognition area and the recognition frame includes: obtaining the coordinates of a pair of diagonal points of the object recognition area, denoted as (x A ,y A )、(x B ,y B ); Get the coordinates of one pair of diagonal points of the recognition box as (x0 ,y 0 )、(x 1 ,y 1 ); wherein the obtained object recognition area corresponds to the diagonal point of the recognition frame.

[0017] Optionally, when the coordinate value of the recognition frame is smaller than the coordinate value of the object recognition area, the step of determining that the recognition frame is located in the object recognition area includes: A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In this case, it is determined that the recognition frame is within the object recognition area.

[0018] Optionally, the step of generating the motion trajectory of the target object according to the position information of the target object includes: marking the position of the target object in each frame of the overhead image, and generating the motion trajectory of the target object according to the position of the target object in each frame of the overhead image.

[0019] Optionally, the step of generating a motion trajectory of the target object according to the position of the target object in each frame of the target image includes: connecting the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image as the motion trajectory of the target object.

[0020] Optionally, the target object position in the current frame of the overhead image and the target object position in the previous frame of the overhead image are both located in the tracking chain.

[0021] Optionally, a tracking chain is generated as follows: the target object position in the next frame of the overhead image is predicted based on the target object position in the current frame of the overhead image and the target object position in the previous frame of the overhead image; the target object position in each frame of the overhead image and the predicted target object position in the next frame of the target image are connected in sequence to generate a tracking chain.

[0022] Optionally, the step of calculating the number of target objects according to the movement trajectory of the target objects includes: calculating the number of target objects when the target objects intersect with the warning line.

[0023] Optionally, the step of calculating the number of target objects includes: when the direction of the movement trajectory of the target object is away from the object identification area, the number of target objects is reduced by 1; or when the direction of the movement trajectory of the target object is close to the object identification area, the number of target objects is increased by 1.

[0024] In some embodiments, the apparatus comprises: a processor and a memory storing program instructions, wherein the processor is configured to execute a counting method for refrigeration equipment when running the program instructions.

[0025] In some embodiments, the refrigeration device includes a body, and also includes: a camera, disposed on the top wall of the body and configured to collect a top view image; and a counting device, disposed on the body.

[0026] In some embodiments, the computer-readable storage medium stores program instructions, and when the program instructions are executed, the computer is used to execute a counting method for refrigeration equipment.

[0027] The counting method and device for refrigeration equipment, refrigeration equipment, and computer-readable storage medium provided in the embodiments of the present disclosure can achieve the following technical effects:

[0028] In the embodiment of the present disclosure, since the object recognition area is limited, the target objects in other parts outside the object recognition area are not counted in the statistical range, so as to filter out the object image formed by the reflection of the cabinet door. Therefore, compared with the related art, the counting method for refrigeration equipment provided by the present disclosure can further improve the accuracy of the target object quantity statistics in the refrigeration equipment.

[0029] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0031] Figure 1 is a schematic diagram of a counting method for refrigeration equipment provided by an embodiment of the present disclosure;

[0032] Figure 2 is a schematic diagram of a counting method for refrigeration equipment provided by another embodiment of the present disclosure;

[0033] Figure 3 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0034] Figure 4 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0035] Figure 5is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0036] Figure 6 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0037] Figure 7 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0038] Figure 8 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0039] Fig. 9 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0040] Fig.10 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0041] Fig.11 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0042] Fig.12 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0043] Fig.13 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0044] Fig.14 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0045] Fig.15 is a schematic diagram of a counting method for refrigeration equipment provided by yet another embodiment of the present disclosure;

[0046] Fig.16 is a schematic diagram of a counting device for refrigeration equipment provided by an embodiment of the present disclosure;

[0047] Fig.17 It is a structural schematic diagram of a refrigeration device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0048] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0049] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0050] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0051] The disclosed embodiment can collect multiple frames of top-view images of the identification area by setting a camera on the top wall of the refrigeration equipment, and use the multiple frames of top-view images of the identification area for image recognition to limit the object identification area. Therefore, target objects in other parts outside the object identification area are not counted in the statistical range. In this way, the mirror image of the object formed by the reflection of the cabinet door can be filtered out. Therefore, the accuracy of the target object quantity statistics in the refrigeration equipment is further improved.

[0052] Combination Figure 1 As shown, the embodiment of the present disclosure provides a counting method for refrigeration equipment, comprising:

[0053] S110, the refrigeration device obtains an image of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0054] S120, the refrigeration device determines an object identification area in the identification area.

[0055] S130, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S140; if the result is no, continue to execute S130.

[0056] S140, the refrigeration device calculates the number of target items based on the item identification area.

[0057] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2.

[0058] The counting method for refrigeration equipment provided by the embodiment of the present disclosure obtains an image of a recognition area according to a counting request, and determines an object recognition area in the recognition area. The number of frames of the image in the recognition area m≥m0 In the case of m≥m, it means that the number of frames of the image of the recognition area currently acquired meets the condition for determining the motion trajectory of the target object. 0 In the case of a single-frame image, the number of target objects in the object recognition area is calculated by comparing each frame of the recognition area. Since the object recognition area is limited, only the number of target objects in the object recognition area needs to be counted, and the target objects in other parts outside the object recognition area are not included in the statistical range, so as to filter out the mirror image of the object formed by the reflection of the cabinet door, and further improve the accuracy of the target object number statistics in the refrigeration equipment.

[0059] Optionally, the image of the recognition area includes: a plurality of frames of overhead images of the recognition area. In this embodiment, by acquiring a plurality of frames of overhead images of the recognition area, the object recognition area in the recognition area is more accurately determined and the number of target objects is calculated, thereby reducing the possibility that the number of target objects is accurately calculated due to the determined object recognition area range not being consistent with the actual range.

[0060] Combination Figure 2 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0061] S210, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0062] S220, the refrigeration device determines an object identification area in the identification area.

[0063] S230, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S240; if the result is no, continue to execute S230.

[0064] S240, the refrigeration device calculates the number of target items based on the item identification area.

[0065] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2.

[0066] Optionally, the step of determining the object identification area in the identification area includes: determining the intersection point of the door body boundary and the box body boundary based on multiple frames of overhead view images; controlling the intersection point to extend into a line in a direction perpendicular to the box body boundary to divide the overhead view image into two parts; and using the portion of the overhead view image containing the box body boundary as the object identification area.

[0067] In this embodiment, the glass door of the refrigeration equipment reflects to form an image of the object. Therefore, based on multiple frames of overhead images, the intersection point of the door boundary and the box boundary is determined, and the intersection point is controlled to extend into a line in a direction perpendicular to the box boundary. The overhead image is divided into two parts, and the part of the overhead image containing the box boundary is used as the object recognition area, so that the target objects in the mirror area of ​​the object recognition area are not included in the statistical range, and the reflection of the glass door to form the object mirror image is filtered out, thereby improving the accuracy of the target object quantity statistics in the refrigeration equipment.

[0068] Combination Figure 3 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0069] S310, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0070] S320: The refrigeration device determines the intersection point between the door boundary and the cabinet boundary based on the multiple frames of overhead images.

[0071] S330, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0072] S340: The refrigeration device uses the partial top view image including the cabinet boundary as an object recognition area.

[0073] S350, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S360; if the result is no, continue to execute S350.

[0074] S360, the refrigeration device calculates the number of target items based on the item identification area.

[0075] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2.

[0076] Optionally, the step of calculating the number of target objects based on the object identification area includes: determining movement trajectories of the target objects in the object identification area; and calculating the number of the target objects according to the movement trajectories of the target objects.

[0077] In this embodiment, when the refrigeration device is actually used, the target items will be taken out or put back by the user, and the movement trajectory of the target items has two directions. By determining the movement trajectory of the target items in the item identification area, the number of target items can be correctly calculated, thereby improving the accuracy of the target item quantity statistics in the refrigeration device.

[0078] Combination Figure 4As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0079] S410, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0080] S420: The refrigeration device determines the intersection point between the door boundary and the cabinet boundary based on the multiple frames of overhead images.

[0081] S430, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0082] S440: The refrigeration device uses the partial top view image including the cabinet boundary as an object recognition area.

[0083] S450, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S460; if the result is no, continue to execute S450.

[0084] S460, the refrigeration device determines a movement trajectory of the target object in the object identification area.

[0085] S460, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0086] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2.

[0087] Optionally, the step of determining the motion trajectory of the target object in the object identification area includes: detecting an object whose position has changed based on multiple frames of overhead images; if the object whose position has changed is located in the object identification area, treating the object as a target object; and generating the motion trajectory of the target object based on the position information of the target object.

[0088] In this embodiment, the items in the mirror area of ​​the item recognition area are mirror images formed by the reflection of the glass door of the refrigeration equipment, and are not real items. Therefore, based on multiple frames of overhead images, the items with changed positions are detected. If the items with changed positions are located in the item recognition area, it is indicated that the items are real items, and the items are taken as target items and the movement trajectory of the target items is generated. If the items with changed positions are outside the item recognition area, it is indicated that the items are mirror images of items and are not counted as target items. This improves the accuracy of the number of target items counted in the refrigeration equipment.

[0089] Combination Figure 5 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0090] S510, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0091] S520: The refrigeration device determines the intersection point between the door boundary and the cabinet boundary based on the multiple frames of overhead images.

[0092] S530, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0093] S540: The refrigeration device uses the portion of the top view image including the cabinet boundary as an object recognition area.

[0094] S550, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S560; if the result is no, continue to execute S550.

[0095] S560, the refrigeration device detects the objects whose positions have changed according to the multiple frames of overhead images.

[0096] S570: When the object whose position has changed is located in the object identification area, the refrigeration device regards the object as a target object.

[0097] S580, the refrigeration device generates a movement trajectory of the target object according to the location information of the target object.

[0098] S590, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0099] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2.

[0100] Optionally, when the object whose position has changed is located within the object identification area, the step of treating the object as the target object includes: marking the object whose position has changed in multiple frames of overhead images with an identification frame; and when the identification frame is located within the object identification area, treating the object as the target object.

[0101] In this embodiment, the objects are of different sizes and shapes. Objects whose positions change in multiple frames of overhead images are marked with identification frames. Whether the identification frame is located in the object identification area is used as a criterion for judging the target object, thereby reducing the possibility of correctly calculating the number of target objects due to irregular size or shape of the objects, thereby improving the accuracy of counting the number of target objects in the refrigeration equipment.

[0102] Combination Figure 6As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0103] S610, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0104] S620: The refrigeration device determines the intersection point between the door boundary and the cabinet boundary based on the multiple frames of overhead images.

[0105] S630, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0106] S640: The refrigeration device uses the portion of the top view image including the cabinet boundary as an object recognition area.

[0107] S650, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S660; if the result is no, continue to execute S650.

[0108] S660: The refrigeration device detects the objects whose positions have changed based on the multiple frames of overhead images.

[0109] S670: The refrigeration device marks the objects whose positions have changed in the multiple frames of the overhead view image with an identification frame.

[0110] S680: When the identification frame is located in the object identification area, the refrigeration device regards the object as a target object.

[0111] S690, the refrigeration device generates a movement trajectory of the target object according to the location information of the target object.

[0112] S691, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0113] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2.

[0114] Optionally, determine whether the target frame is located in the object identification area in the following manner: establish a coordinate system of the object identification area with the intersection point as the origin based on multiple frames of overhead view images; obtain the coordinates of the object identification area and the identification frame; and determine that the identification frame is located in the object identification area when the coordinate value of the identification frame is less than the coordinate value of the object identification area.

[0115] In this embodiment, whether the identification frame is located within the object identification area is determined by comparing the coordinate values ​​of the identification frame and the coordinate values ​​of the object identification area. The determination process is rapid and this method does not require overly complex calculations or judgment logic, thereby increasing the speed at which the refrigeration equipment makes determinations.

[0116] Combination Figure 7 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0117] S710, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0118] S720: The refrigeration device determines a junction point between a door boundary and a cabinet boundary based on the multiple frames of overhead images.

[0119] S730, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0120] S740: The refrigeration device uses a portion of the top view image including the cabinet boundary as an object recognition area.

[0121] S750, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S760; if the result is no, continue to execute S750.

[0122] S760, the refrigeration device detects the object whose position has changed according to the multiple frames of overhead images.

[0123] S770, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0124] S780, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0125] S790, the refrigeration device obtains the coordinates of the object identification area and the identification frame.

[0126] S791, when the coordinate value of the recognition frame is smaller than the coordinate value of the object recognition area, the refrigeration device determines that the recognition frame is located in the object recognition area and regards the object as a target object.

[0127] S792, the refrigeration device generates a movement trajectory of the target object according to the location information of the target object.

[0128] S793, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0129] Among them, m is the number of frames of the image of the recognition area, m0 is the image frame number threshold and m 0 ≥2.

[0130] Optionally, the step of obtaining the coordinates of the object recognition area and the recognition frame includes: obtaining the coordinates of a pair of diagonal points of the object recognition area, denoted as (x A ,y A )、(x B ,y B ); Get the coordinates of one pair of diagonal points of the recognition box as (x 0 ,y 0 )、(x 1 ,y 1 ); wherein the obtained object recognition area corresponds to the diagonal point of the recognition frame.

[0131] In this embodiment, only the coordinate sizes of a pair of diagonal points of the object identification area and the identification frame need to be compared, rather than comparing the coordinate sizes of the four points of the object identification area and the identification frame one by one, which simplifies the judgment logic and improves the judgment efficiency when the method is executed.

[0132] Combination Figure 8 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0133] S810, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0134] S820: The refrigeration device determines a junction point between a door boundary and a cabinet boundary based on the multiple frames of overhead images.

[0135] S830, the refrigeration equipment control junction point is extended into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0136] S840: The refrigeration device uses a portion of the top view image including the cabinet boundary as an object recognition area.

[0137] S850, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S860; if the result is no, continue to execute S850.

[0138] S860, the refrigeration device detects the object whose position has changed according to the multiple frames of overhead images.

[0139] S870, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0140] S880, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0141] S890, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0142] S891, the refrigeration device obtains the coordinates of a pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0143] S892: When the coordinate value of the recognition frame is smaller than the coordinate value of the object recognition area, the refrigeration device determines that the recognition frame is located in the object recognition area and regards the object as a target object.

[0144] S893, the refrigeration device generates a movement trajectory of the target object according to the location information of the target object.

[0145] S894, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0146] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0147] Optionally, when the coordinate value of the recognition frame is smaller than the coordinate value of the object recognition area, the step of determining that the recognition frame is located in the object recognition area includes: A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In this case, it is determined that the recognition frame is within the object recognition area.

[0148] In this embodiment, the coordinates of the diagonal points of the recognition frame and the diagonal points of the object recognition area are compared, which is independent of the size or shape of the object as long as the coordinates meet the conditions. 0 and x 1 are all greater than the horizontal coordinate x of a diagonal point in the object recognition area A , and is smaller than the horizontal coordinate x of the other diagonal point of the object recognition areaB , the ordinate y of a pair of diagonal points of the recognition box 0 and 1 are all greater than the y coordinate of a diagonal point in the object recognition area A , and is smaller than the ordinate y of the other diagonal point of the object recognition area B , which means that the recognition box is located in the object recognition area.

[0149] Combination Fig. 9 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0150] S910, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0151] S920: The refrigeration device determines a junction point between a door boundary and a cabinet boundary based on the multiple frames of overhead images.

[0152] S930, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0153] S940: The refrigeration device uses a portion of the top view image including the cabinet boundary as an object recognition area.

[0154] S950, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S960; if the result is no, continue to execute S950.

[0155] S960, the refrigeration device detects the object whose position has changed according to the multiple frames of overhead images.

[0156] S970, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0157] S980, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0158] S990, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0159] S991, the refrigeration device obtains the coordinates of a pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0160] S992, Refrigeration equipment in x A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In the case of , it is determined that the recognition frame is located within the object recognition area and the object is regarded as the target object.

[0161] S993, the refrigeration device generates a movement trajectory of the target object according to the location information of the target object.

[0162] S994, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0163] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0164] Optionally, the step of generating the motion trajectory of the target object according to the position information of the target object includes: marking the position of the target object in each frame of the overhead image, and generating the motion trajectory of the target object according to the position of the target object in each frame of the overhead image.

[0165] In this embodiment, the position of the target object in each frame of the overhead image is marked to generate the target object's motion trajectory to calculate the number of target objects. In the related art, the target objects are marked with rectangular frames to calculate the number of target objects, which is easy to fail to detect because the rectangular frame is too small or the speed of taking the object is too fast. Therefore, by calculating the number of target objects through the target object's motion trajectory, the number of target objects is reduced, thereby improving the accuracy of the target object number statistics.

[0166] Combination Fig.10 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0167] S1010, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0168] S1020: The refrigeration device determines a junction point between a door boundary and a cabinet boundary based on the multiple frames of overhead images.

[0169] S1030, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0170] S1040: The refrigeration device uses a portion of the top view image including the cabinet boundary as an object recognition area.

[0171] S1050, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S1060; if the result is no, continue to execute S1050.

[0172] S1060, the refrigeration device detects objects whose positions have changed based on the multiple frames of overhead images.

[0173] S1070, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0174] S1080, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0175] S1090, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0176] S1091, the refrigeration device obtains the coordinates of a pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0177] S1092, Refrigeration equipment in x A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In the case of , it is determined that the recognition frame is located within the object recognition area and the object is regarded as the target object.

[0178] S1093, the refrigeration device marks the position of the target object in each frame of the overhead image, and generates a movement trajectory of the target object according to the position of the target object in each frame of the overhead image.

[0179] S1094, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0180] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0181] Optionally, the step of generating a motion trajectory of the target object according to the position of the target object in each frame of the target image includes: connecting the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image as the motion trajectory of the target object.

[0182] In this embodiment, the position of the target object in the current frame overhead image and the position of the target object in the previous frame overhead image are connected as the movement trajectory of the target object and then the number of target objects is calculated, thereby reducing the situation where the target object is not detected and further improving the accuracy of the target object quantity statistics in the refrigeration equipment.

[0183] Combination Fig.11 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0184] S1110, the refrigeration device obtains multiple frames of overhead images of the identification area in response to the counting request; wherein the identification area includes the object identification area and the mirror area of ​​the object identification area.

[0185] S1120: The refrigeration device determines a junction point between a door boundary and a cabinet boundary based on the multiple frames of overhead images.

[0186] S1130, the refrigeration equipment controls the intersection point to extend into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0187] S1140: The refrigeration device uses a portion of the top view image including the cabinet boundary as an object recognition area.

[0188] S1150, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S1160; if the result is no, continue to execute S1150.

[0189] S1160, the refrigeration device detects objects whose positions have changed based on the multiple frames of overhead images.

[0190] S1170, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0191] S1180, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0192] S1190, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0193] S1191, the refrigeration device obtains the coordinates of one pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0194] S1192, Refrigeration equipment in x A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In the case of , it is determined that the recognition frame is located within the object recognition area and the object is regarded as the target object.

[0195] S1193, the refrigeration device marks the position of the target object in each frame of the overhead image, and connects the position of the target object in the current frame of the overhead image with the position of the target object in the previous frame of the overhead image as the movement trajectory of the target object.

[0196] S1194, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0197] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0198] Optionally, the target object position in the current frame of the overhead image and the target object position in the previous frame of the overhead image are both located in the tracking chain.

[0199] In this embodiment, synchronous tracking of the target object can be achieved by generating a tracking chain, and tracking failure will not occur due to occlusion of the target object, which has higher reliability. The position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image are both located in the tracking chain, which can reduce the situation where the target object cannot be identified in a certain frame of the image because it is blocked.

[0200] Combination Fig.12 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0201] S1210, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0202] S1220: The refrigeration device determines the intersection point between the door boundary and the cabinet boundary based on the multiple frames of overhead images.

[0203] S1230, the refrigeration equipment control junction point is extended into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0204] S1240: The refrigeration device uses a portion of the top view image including the cabinet boundary as an object recognition area.

[0205] S1250, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S1260; if the result is no, continue to execute S1250.

[0206] S1260, the refrigeration equipment detects objects whose positions have changed based on the multiple frames of overhead images.

[0207] S1270, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0208] S1280, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0209] S1290, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0210] S1291, the refrigeration device obtains the coordinates of a pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0211] S1292, Refrigeration equipment in x A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,yA <y 1 <y B In the case of , it is determined that the recognition frame is located within the object recognition area and the object is regarded as the target object.

[0212] S1293, the refrigeration equipment marks the position of the target object in each frame of the overhead image, and connects the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image as the movement trajectory of the target object; wherein the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image are both located in the tracking chain.

[0213] S1294, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0214] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0215] Optionally, a tracking chain is generated as follows: the target object position in the next frame of the overhead image is predicted based on the target object position in the current frame of the overhead image and the target object position in the previous frame of the overhead image; the target object position in each frame of the overhead image and the predicted target object position in the next frame of the target image are connected in sequence to generate a tracking chain.

[0216] In this embodiment, the predicted target object position can better reflect the actual motion state of the target object, thereby achieving continuous tracking of the target object and generating a tracking chain. The target object may not be detected in a certain frame due to occlusion or image quality. The target object position in the next frame of the overhead image is predicted based on the target object position in the current frame of the overhead image and the target object position in the previous frame of the overhead image, and the predicted target object position is made to coincide with the actual target object position in the next frame as much as possible. In the case where the target object cannot be detected in a certain frame of the image, the predicted target object position is used instead of the actual target object position to prevent the motion trajectory of the target object from being disconnected, so that the quantity of the target food can be calculated.

[0217] Combination Fig.13 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0218] S1310, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0219] S1320: The refrigeration device determines the intersection point between the door boundary and the cabinet boundary based on the multiple frames of overhead images.

[0220] S1330, the refrigeration equipment control junction point is extended into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0221] S1340: The refrigeration device uses a portion of the top view image including the cabinet boundary as an object recognition area.

[0222] S1350, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S1360; if the result is no, continue to execute S1350.

[0223] S1360, the refrigeration device detects objects whose positions have changed based on the multiple frames of overhead images.

[0224] S1370, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0225] S1380, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0226] S1390, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0227] S1391, the refrigeration device obtains the coordinates of a pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0228] S1392, Refrigeration equipment in x A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In the case of , it is determined that the recognition frame is located within the object recognition area and the object is regarded as the target object.

[0229] S1393, the refrigeration device predicts the position of the target object in the next frame of the overhead image according to the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image.

[0230] S1394, the refrigeration device sequentially connects the target object position in each frame of the overhead image and the predicted target object position in the next frame of the target image to generate a tracking chain.

[0231] S1395, the refrigeration equipment marks the position of the target object in each frame of the overhead image, and connects the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image as the movement trajectory of the target object; wherein the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image are both located in the tracking chain.

[0232] S1396, the refrigeration device calculates the number of the target objects according to the movement trajectory of the target objects.

[0233] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0234] Optionally, the step of calculating the number of target objects according to the movement trajectory of the target objects includes: calculating the number of target objects when the target objects intersect with the warning line.

[0235] In this embodiment, when the movement track of the target object intersects with the warning line, it indicates that the target object is taken out or put back. In this case, the number of target objects is calculated to correctly count the target objects, thereby improving the accuracy of the target object number statistics.

[0236] Combination Fig.14 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0237] S1410, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0238] S1420: The refrigeration device determines the intersection point between the door boundary and the cabinet boundary based on the multiple frames of overhead images.

[0239] S1430, the refrigeration equipment control intersection point is extended into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0240] S1440, the refrigeration device uses the partial top view image including the cabinet boundary as the object recognition area.

[0241] S1450, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S1460; if the result is no, continue to execute S1450.

[0242] S1460, the refrigeration equipment detects objects whose positions have changed based on the multiple frames of overhead images.

[0243] S1470, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0244] S1480, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0245] S1490, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0246] S1491, the refrigeration device obtains the coordinates of one pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0247] S1492, Refrigeration equipment in x A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In the case of , it is determined that the recognition frame is located within the object recognition area and the object is regarded as the target object.

[0248] S1493, the refrigeration device predicts the position of the target object in the next frame of the overhead image according to the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image.

[0249] S1494, the refrigeration device sequentially connects the target object position in each frame of the overhead image and the predicted target object position in the next frame of the target image to generate a tracking chain.

[0250] S1495, the refrigeration equipment marks the position of the target object in each frame of the overhead image, and connects the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image as the movement trajectory of the target object; wherein the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image are both located in the tracking chain.

[0251] S1496, the refrigeration device calculates the quantity of the target object when the target object intersects the warning line.

[0252] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0253] Optionally, the step of calculating the number of target objects includes: when the direction of the movement trajectory of the target object is away from the object identification area, the number of target objects is reduced by 1; or when the direction of the movement trajectory of the target object is close to the object identification area, the number of target objects is increased by 1.

[0254] In this embodiment, when the moving track direction of the target object is away from the object identification area, it means that the target object is taken out, and the number of the target objects is reduced by 1 during the counting process.

[0255] If the target food's moving track is close to the object identification area, it means that the target item has been put back. In this case, the number of target items is increased by 1 during the counting process. The number of target items is calculated by the different moving track directions of the target items, so that the target items can be correctly counted, thereby improving the accuracy of the target item count in the refrigeration equipment.

[0256] Combination Fig.15 As shown, the embodiment of the present disclosure provides another counting method for refrigeration equipment, comprising:

[0257] S1510, the refrigeration device obtains multiple frames of overhead images of a recognition area in response to a counting request; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area.

[0258] S1520: The refrigeration device determines a junction point between a door boundary and a cabinet boundary based on the multiple frames of overhead images.

[0259] S1530, the refrigeration equipment control intersection point is extended into a line in a direction perpendicular to the cabinet boundary, dividing the top view image into two parts.

[0260] S1540, the refrigeration device uses the partial top view image including the cabinet boundary as the object recognition area.

[0261] S1550, the refrigeration device determines whether m is greater than or equal to m 0 If the result is yes, go to S1560; if the result is no, continue to execute S1550.

[0262] S1560, the refrigeration device detects the objects whose positions have changed based on the multiple frames of overhead images.

[0263] S1570, the refrigeration device marks the objects whose positions have changed in the multiple frames of overhead images with identification frames.

[0264] S1580, the refrigeration device establishes a coordinate system of the object recognition area based on the multiple frames of overhead images with the intersection point as the origin.

[0265] S1590, the refrigeration device obtains the coordinates of a pair of diagonal points in the object identification area as (x A ,y A )、(x B ,y B ).

[0266] S1591, the refrigeration device obtains the coordinates of one pair of diagonal points of the identification frame as (x 0 ,y 0 )、(x 1 ,y 1 ).

[0267] S1592, Refrigeration equipment in x A <x 0 <x B ,y A <y 0 <y B And x A <x 1 <x B ,y A <y 1 <y B In the case of , it is determined that the recognition frame is located within the object recognition area and the object is regarded as the target object.

[0268] S1593, the refrigeration device predicts the position of the target object in the next frame of the overhead image according to the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image.

[0269] S1594, the refrigeration device sequentially connects the target object position in each frame of the overhead image and the predicted target object position in the next frame of the target image to generate a tracking chain.

[0270] S1595, the refrigeration equipment marks the position of the target object in each frame of the overhead image, and connects the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image as the movement trajectory of the target object; wherein the position of the target object in the current frame of the overhead image and the position of the target object in the previous frame of the overhead image are both located in the tracking chain.

[0271] S1596: When the target object intersects the warning line and the moving track of the target object is away from the object identification area, the number of the target object is reduced by 1.

[0272] S1597, when the target object intersects the warning line and the moving track direction of the target object is close to the object identification area, the number of the target object is increased by 1.

[0273] Among them, m is the number of frames of the image of the recognition area, m 0 is the image frame number threshold and m 0 ≥2, the obtained object recognition area corresponds to the diagonal point of the recognition box.

[0274] Combination Fig.16 As shown, the embodiment of the present disclosure provides a counting device 200 for refrigeration equipment, including a processor 100 and a memory 101. Optionally, the device 200 may also include a communication interface 102 and a bus 103. The processor 100, the communication interface 102, and the memory 101 may communicate with each other through the bus 103. The communication interface 102 may be used for information transmission. The processor 100 may call the logic instructions in the memory 101 to execute the counting method for refrigeration equipment of the above embodiment.

[0275] In addition, the logic instructions in the memory 101 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0276] The memory 101 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 100 executes the functional application and data processing by running the program instructions / modules stored in the memory 101, that is, the counting method for refrigeration equipment in the above embodiment is implemented.

[0277] The memory 101 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 101 may include a high-speed random access memory and may also include a non-volatile memory.

[0278] Combination Fig.17As shown, an embodiment of the present disclosure provides a refrigeration device 100, including: a main body, a camera (not shown in the figure), and the above-mentioned counting device 200 for the refrigeration device. The first camera is arranged on the top wall of the main body and is configured to collect a top view image. The counting device 200 for the refrigeration device is installed on the main body. The installation relationship described here is not limited to placement inside the main body, but also includes installation connections with other components of the product 100, including but not limited to physical connections, electrical connections or signal transmission connections, etc. Those skilled in the art can understand that the counting device 200 for refrigeration equipment can be adapted to a feasible main body, thereby realizing other feasible embodiments.

[0279] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned counting method for refrigeration equipment.

[0280] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0281] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0282] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

Claims

1. A counting method for refrigeration equipment, characterized in that: include: In response to a counting request, acquiring an image of a recognition area; wherein the recognition area includes an object recognition area and a mirror image area of ​​the object recognition area; Determine an object identification area in the identification area; When m≥m0, the number of target objects is calculated based on the object recognition area; Wherein, m is the number of frames of the image of the recognition area, m0 is the image frame number threshold and m0≥2.

2. The counting method for refrigeration equipment according to claim 1, characterized in that: The images of the identified areas include: Multiple overhead images of the identified area.

3. The counting method for refrigeration equipment according to claim 2, characterized in that: The step of determining the object identification area in the identification area includes: Based on multiple frames of overhead images, determine the intersection point between the door boundary and the box boundary; The control intersection point is extended into a line in the direction perpendicular to the box boundary, dividing the top view image into two parts; The part of the top view image containing the box boundary is used as the object recognition area.

4. The counting method for refrigeration equipment according to claim 3, characterized in that: The step of calculating the number of target objects based on the object recognition area includes: Determine the movement trajectory of the target object in the object recognition area; According to the movement trajectory of the target objects, the number of target objects is calculated.

5. The counting method for refrigeration equipment according to claim 4, characterized in that: The step of determining the movement trajectory of the target object in the object recognition area includes: Detect objects with changed positions based on multiple frames of overhead images; When the object whose position has changed is within the object recognition area, the object is regarded as a target object; According to the location information of the target object, the movement trajectory of the target object is generated.

6. The counting method for refrigeration equipment according to claim 5, characterized in that: When the object with changed position is located in the object identification area, the step of treating the object as a target object comprises: Mark objects whose positions change in multiple frames of overhead images with identification frames; When the recognition frame is located within the object recognition area, the object is regarded as a target object.

7. The counting method for refrigeration equipment according to claim 5, characterized in that: The step of generating a motion trajectory of the target object according to the position information of the target object comprises: The position of the target object in each frame of the overhead image is marked, and the motion trajectory of the target object is generated according to the position of the target object in each frame of the overhead image.

8. A counting device for refrigeration equipment, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the counting method for refrigeration equipment according to any one of claims 1 to 7 when running the program instructions.

9. A refrigeration device, comprising a body, characterized in that: Also includes: A camera, disposed on the top wall of the body, configured to collect a top-view image; The counting device according to claim 8 is arranged on the main body.

10. A computer-readable storage medium storing program instructions, characterized in that: When the program instructions are executed, the computer is used to execute the counting method for refrigeration equipment according to any one of claims 1 to 7.

Images