CN109887161B - Anti-theft method and system for unmanned sales counter and unmanned sales counter with anti-theft function - Google Patents
Anti-theft method and system for unmanned sales counter and unmanned sales counter with anti-theft function Download PDFInfo
- Publication number
- CN109887161B CN109887161B CN201910051355.6A CN201910051355A CN109887161B CN 109887161 B CN109887161 B CN 109887161B CN 201910051355 A CN201910051355 A CN 201910051355A CN 109887161 B CN109887161 B CN 109887161B
- Authority
- CN
- China
- Prior art keywords
- door
- opening
- unmanned
- counter
- closing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Burglar Alarm Systems (AREA)
Abstract
The invention relates to the technical field of unmanned vending, in particular to an anti-theft method and an anti-theft system for an unmanned vending cabinet and the unmanned vending cabinet with an anti-theft function. The method comprises the following steps: the visual door opening and closing detection algorithm judges the change angle of the container door, compares the change angle of the container door with a preset angle and obtains a comparison result, and judges the opening and closing state of the container door based on the comparison result; detecting the generation state of an order of an unmanned sales counter; the running state of the unmanned sales counter is judged according to the opening and closing state of the counter door and the generation state of the order; when the operation state is abnormal, the unmanned sales counter sends alarm information, and the opening and closing state of the door of the goods cabinet is judged by a visual door opening and closing detection algorithm, so that the door opening and closing mode of the door of the goods cabinet is judged more quickly and accurately, and the behavior of lock cheating is avoided; and the running state of the unmanned sales counter is judged by combining the opening and closing state of the counter door and the generation state of the order, so that the real-time sales condition of the unmanned sales counter can be accurately judged, and the condition that the commodity is stolen due to artificial interference is avoided.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of unmanned vending, in particular to an anti-theft method and system for an unmanned vending cabinet and the unmanned vending cabinet with an anti-theft function.
[ background of the invention ]
In order to meet the requirements of the vast management end, convenience is provided, and unmanned automatic sales cabinets appear in succession. The unmanned automatic sales counter is arranged in different places, and the taking out and payment of the goods are all operated by the consumers. In the process of operation of the unmanned automatic sales counter, some faults often occur easily, for example, the existing method of sensing the opening or closing of the counter door by using the electromagnetic switch is adopted, when a lawless person maliciously damages the counter door and steals, other magnetic adsorption pieces are often adsorbed on the electromagnetic switch of the counter door, and the system mistakenly takes the action of cheating locking that the counter door is closed, so that the existing electromagnetic switch sensing system cannot accurately judge the real-time state of the unmanned automatic sales counter, and the commodity is stolen. The existing monitoring system for the sales counter is often complex or not fast enough to provide a lot of opportunities for vandals.
[ summary of the invention ]
In order to overcome the defect that the feedback of the existing unmanned sales counter to the abnormal condition lags behind, the invention provides an anti-theft method and system for the unmanned sales counter and the unmanned sales counter with the anti-theft function.
In order to solve the technical problem, an anti-theft method for an unmanned sales counter is provided, wherein the unmanned sales counter comprises a counter door, and the anti-theft method for the unmanned sales counter comprises the following steps: s1, judging the change angle of the container door based on a visual door opening and closing detection algorithm, comparing the change angle of the container door with a preset angle to obtain a comparison result, and judging the opening and closing state of the container door based on the comparison result; s2, detecting the generation state of the order of the unmanned sales counter; s3, judging the running state of the unmanned sales counter by combining the opening and closing state of the door of the cabinet and the generation state of the order, further judging whether a new order is generated or not when judging that the door of the cabinet is opened, if so, outputting the running state of the unmanned sales counter to be normal, and if not, outputting the running state of the unmanned sales counter to be abnormal; or when the container door is judged to be closed, further judging whether a new order is generated, if so, outputting that the running state of the unmanned sales container is abnormal, and if not, outputting that the running state of the unmanned sales container is normal; s4, when the running state is abnormal, alarming information is sent out; controlling the recording, starting or ending of the analysis video based on the opening and closing state of the cargo cabinet door, starting the recording and analysis video when the cargo cabinet door is judged to be opened, and ending the recording and analysis video when the cargo cabinet door is closed; and the recorded analysis video is stored in combination with the corresponding time axis.
Preferably, the step S1 includes at least the following steps: step S11, selecting a key area of the multi-frame image; step S12, comparing the pixel difference of key areas in the multi-frame images based on a visual door opening and closing detection algorithm, and obtaining a pixel difference value; and step S13a, obtaining a connected domain related to the change of the container door based on the pixel difference value, acquiring the changed angle of the container door based on the connected domain, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
Preferably, the step S1 further includes the steps of: step S11, obtaining multi-frame images and selecting key areas of the multi-frame images; step S12, comparing the pixel difference of key areas in the multi-frame images based on a visual door opening and closing detection algorithm, and obtaining a pixel difference value; and step S13b, analyzing the key area in the multi-frame image by using an edge detection algorithm to obtain the changed angle of the container door, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
Preferably, the step S1 further includes the steps of: step S11', selecting key areas of multi-frame images; and step S12', analyzing the key area of the multi-frame image by using an edge detection algorithm to obtain the changed angle of the container door, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
Preferably, the step S1 further includes the steps of: step S11', judging the changed angle of the container door based on the visual door opening and closing detection algorithm, comparing the changed angle of the container door with a preset angle and obtaining a comparison result; step S12' of obtaining the auxiliary detection signal of the container door switch; step S13', the opening and closing state of the cargo door is further judged by combining the comparison result and the auxiliary detection signal of the cargo door opening and closing; the steps S11 "and S12" may be performed simultaneously or the execution sequence may be interchanged.
Preferably, the anti-theft method for the unmanned counter further comprises the steps of: controlling the recording, opening or ending of the analysis video based on the opening and closing state of the cargo cabinet door output by the visual door opening and closing detection algorithm, opening the recording and analysis video when judging that the cargo cabinet door is opened, and ending the recording and analysis video when the cargo cabinet door is closed; and combining the recorded analysis video with the corresponding time axis for storage.
In order to solve the above technical problems, the present invention further provides an anti-theft system for an unmanned sales counter, wherein the unmanned sales counter includes a counter door, the anti-theft system for the unmanned sales counter includes: the visual door opening and closing detection module is configured for judging the opening and closing state of the cargo cabinet door; the order detection module is configured for detecting the generation state of the order of the unmanned sales counter; the judging module is used for judging the running state of the unmanned sales counter by combining the opening and closing state of the door of the goods cabinet and the generation state of the order, further judging whether a new order is generated or not when the judging module judges that the door of the goods cabinet is opened, if so, outputting the normal running state of the unmanned sales counter, and if not, outputting the abnormal running state of the unmanned sales counter; or when the judging module judges that the container door is closed, further judging whether a new order is generated, if so, outputting the abnormal running state of the unmanned sales container, and if not, outputting the normal running state of the unmanned sales container; and the alarm system is configured to send alarm information when the operation state of the unmanned goods receiving cabinet is abnormal.
Preferably, the unmanned counter theft prevention system further comprises: the camera shooting control module is used for controlling the analysis video recording opening or closing based on the opening and closing state of the cargo cabinet door output by the visual door opening detection module; and the camera shooting storage module is used for combining the recorded analysis video with the corresponding time axis for storage.
The invention also provides an unmanned sales counter with an anti-theft function for solving the technical problems, wherein the unmanned sales counter comprises a counter body, a goods counter door connected with the counter body in an opening and closing manner, at least one camera module arranged on the counter body and a trigger switch arranged on the counter body and the counter door in a matching manner; the unmanned sales counter further comprises an electronic device, the electronic device comprising:
a control system for controlling the unmanned sales counter, the control system further comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement any of the methods described above.
Compared with the prior art, the opening and closing state of the door of the cargo cabinet is judged based on the visual door opening and closing detection algorithm, so that the door opening and closing mode of the door of the cargo cabinet is judged more simply, quickly and accurately, and some lock cheating behaviors are avoided; and the operation state of the unmanned sales counter is judged by combining the opening and closing state of the counter door and the generation state of the order, the real-time sales condition of the unmanned sales counter can be accurately judged, the artificial interference phenomenon is avoided, when the operation state is abnormal, the unmanned sales counter sends alarm information, the management end of the unmanned sales counter can be timely informed to timely handle the problem, and the economic loss is reduced.
The visual door opening and closing detection algorithm judges the opening and closing state of the cargo cabinet door based on the pixel difference of key areas in multi-frame images, can well reduce the range of image processing areas, improves the processing efficiency, can quickly capture door opening or closing signals, and quickly monitors the opening and closing state.
Whether the container door is opened or closed is preliminarily judged through pixel difference among the multi-frame images, and the opening or closing state of the container door is further judged by combining edge information of the container door, so that the result of door opening and closing state judgment is more accurate.
The unmanned counter theft prevention method further includes the steps between step S1 and step S2: the opening and closing state of the door of the cargo container is further judged based on the auxiliary signal detection structure for opening and closing the door of the cargo container; alternatively, before step S1, the opening/closing state of the door of the container may be determined by the auxiliary signal detection structure of the opening/closing of the door of the container, so as to check whether there is a fraudulent locking operation, and to determine the operation state of the unmanned sales container through more accurate analysis.
The analysis video is recorded and controlled to be opened or closed based on the opening and closing state of the cargo cabinet door output by the visual door opening and closing detection algorithm, when the cargo cabinet door is judged to be opened, the recorded analysis video is opened, when the cargo cabinet door is closed, the recorded analysis video is combined with the corresponding time axis of the recorded analysis video for storage, the time length of the analysis video can be well controlled, the management end can find the corresponding analysis video in time and carry out evidence obtaining and investigation when receiving abnormal signals, the video evidence is provided for subsequent processing, and therefore the reason of theft or failure can be investigated in time.
The unmanned sales counter anti-theft system and the unmanned sales counter with the anti-theft function have the same technical effects as the method.
[ description of the drawings ]
FIG. 1 is a schematic structural diagram of an unmanned sales container with anti-theft function according to a first embodiment of the present invention;
FIG. 2 is a schematic view showing the structure of an unmanned sales container with anti-theft function according to a first embodiment of the present invention when the door of the container is opened;
FIG. 3 is a block diagram of a control system in an unmanned sales container with anti-theft function according to a first embodiment of the present invention;
FIG. 4 is a flow chart of the anti-theft method for the unmanned counter according to the second embodiment of the present invention;
FIG. 5 is a detailed flowchart of the step S1 of the anti-theft method for unmanned counter according to the second embodiment of the present invention;
FIG. 6 is a schematic diagram of a selected key area in the anti-theft method for an unmanned aerial vehicle according to a second embodiment of the present invention;
FIG. 7 is a diagram illustrating a state of a door of an unmanned aerial vehicle in the anti-theft method for an unmanned aerial vehicle according to the second embodiment of the present invention;
FIG. 8 is a diagram illustrating a state where a cabinet door of an unmanned sales cabinet is opened in the anti-theft method for an unmanned sales cabinet according to the second embodiment of the present invention;
FIG. 9 is a detailed flowchart of the first modification of step S1 in the anti-theft method for unmanned aerial vehicles according to the second embodiment of the present invention;
FIG. 10 is a detailed flowchart of step S1 in the second modification of the anti-theft method for unmanned counter according to the second embodiment of the present invention;
FIG. 11 is a detailed flowchart of step S1 in the third modification of the anti-theft method for unmanned aerial vehicles according to the second embodiment of the present invention;
FIG. 12 is a flowchart illustrating the details of step S3 in the anti-theft method for an unmanned aerial vehicle according to the second embodiment of the present invention;
FIG. 13 is a flowchart illustrating the details of step S4 in the anti-theft method for an unmanned aerial vehicle according to the second embodiment of the present invention;
FIG. 14 is a block diagram of an anti-theft system for an unmanned counter according to a third embodiment of the present invention;
FIG. 15 is a schematic diagram of a module included in a visual door opening and closing detection module in the anti-theft system for unmanned counter according to the third embodiment of the present invention;
FIG. 16 is a block diagram of a computer system suitable for use with a server implementing an embodiment of the invention.
The attached drawings indicate the following:
10. an unmanned sales counter; 101. a cabinet body; 102. a cargo cabinet door; 103. a camera module; 104. a trigger switch; 107. a control system; 1071. a processor; 1072. a storage device; m, a key area; n, a background area; 20. an unmanned counter anti-theft system; 201. a visual door opening and closing detection module; 2011. a pixel detection module; 2012. an edge detection module; 202. an order detection module; 203. a decision module; 204. an alarm system; 205. a camera control module; 206. a camera storage module; 800. a computer system; 801. a Central Processing Unit (CPU); 802. a memory (ROM); 803. a RAM; 804. a bus; 805. an I/O interface; 806. an input section; 807. an output section; 808. a storage section; 809. a communication section; 810. a driver; 811. a removable media.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1 and 2, a first embodiment of the present invention provides an unmanned sales container 10 with anti-theft function. The unmanned sales counter 10 comprises a counter body 101, a counter door 102 rotatably connected with the counter body 101, and at least one camera module 103 mounted on the counter body 101. The opening and closing state of the cargo cabinet door 102 is detected by the camera module 103.
In some embodiments, the unmanned sales container 10 further comprises a toggle switch 104 mounted on the cabinet body 101 and the container door 102, respectively. Opening or closing of the cargo door 102 is accomplished by controlling the separation or contact of the trigger switches 104 on the cabinet 101 and the cargo door 102. In some embodiments, a camera module 103 is installed on the top of the cabinet 101 near the side of the cabinet door 102 for taking real-time images of the unmanned sales counter 10. Optionally, the installation angle of the shooting module 103 is adjusted, so that the shooting module 103 can well shoot the video image of the corresponding area when the cargo cabinet door 102 is in the open-close state, and the management end can monitor the operation status of the unmanned sales cabinet 10 according to the recorded video image. For example, when the unmanned sales counter 10 is abnormal, the management end may call the video image to analyze, check whether theft or other abnormal conditions occur, and take emergency measures to avoid unnecessary economic loss.
Optionally, in order to monitor the selling condition of the goods in the cabinet 101 conveniently, that is, identify which product the consumer purchases, so as to provide the purchased goods information and the corresponding cost information, a plurality of camera modules (not shown) may be further disposed inside the cabinet 101 or outside the cabinet 101 to monitor the shopping condition of the consumer in real time at multiple angles.
In some embodiments, the trigger switch 104 can be an electromagnetic switch, and in order to control the opening and closing of the trigger switch 104, the unmanned counter 10 further includes a switch control module 105 electrically connected to the trigger switch 104. The operation of the switch control module 105 can be controlled according to the state of the consumer purchasing the goods in the unmanned sales counter 10. For example, when a consumer uses a mobile phone to scan a two-dimensional code on the unmanned sales counter 10 for shopping, the switch control module 105 drives the counter door 102 to open. The container door 102 is typically closed manually by the consumer after the consumer has purchased and taken the item.
Optionally, in order to avoid forgetting to close the door during the purchase process of the consumer, an automatic door closing time may be set, and when the door is opened for more than the set time, the switch control module 105 drives the cargo cabinet door 102 to close automatically, so as to avoid causing unnecessary economic loss.
With continued reference to FIG. 2, the self-service container 10 further includes a control system 107 disposed on the cabinet. Of course, the control system 107 may also be disposed within the cabinet 102 or elsewhere.
Referring to fig. 3, the control system 107 is used for controlling the unmanned sales counter 10, so that the unmanned sales counter 10 can sell goods normally or send an alarm signal to remind the management terminal when the unmanned sales counter 10 is abnormal. The control system 107 includes: one or more processors 1071 and a storage device 1072, the storage device 1072 being used to store one or more programs, which can be executed by the one or more processors 1071 to ensure that the unmanned sales counter 10 sells goods normally, or to send alarm information to notify a management terminal when an abnormal situation occurs in the unmanned sales counter 10.
Referring to fig. 4, a second embodiment of the present invention provides an anti-theft method for an unmanned counter, wherein any one of the steps of the method can be executed by one or more processors provided by the first embodiment, and the method comprises the following steps:
s1, judging the change angle of the container door based on a visual door opening and closing detection algorithm, comparing the change angle of the container door with a preset angle to obtain a comparison result, and judging the opening and closing state of the container door based on the comparison result;
in this step, the visual door opening and closing detection algorithm is obtained through pre-training. The preset angle is set manually, for example, the preset angle can be 30 degrees, 50 degrees or other angles, and when the angle of the cargo cabinet door reaches or is larger than the preset angle, the cargo cabinet door is considered to be in an open state. Similarly, the closed state of the container door can also be determined by a preset angle, and the corresponding preset angle for closing the door is different from the preset angle for opening the door, for example, may be 5 °, 10 ° or other angles.
Referring to fig. 5, in the second embodiment of the present invention, the step S1 at least includes the following steps:
step S11, selecting a key area of the multi-frame image;
step S12, comparing the pixel difference of key areas in the multi-frame images based on a visual door opening and closing detection algorithm, and obtaining a pixel difference value; and
and S13a, obtaining a connected domain related to the change of the container door based on the pixel difference value, acquiring the changed angle of the container door based on the connected domain, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
In step S11, a plurality of frames of images are captured by the capture module. The key area is a local area which is selected by the management terminal and can reflect the door opening state and the door closing state in the video image most. As shown in fig. 6 and 7, the key region M is selected mainly to improve the efficiency of image analysis and increase the accuracy of analysis. The key area M is the area of the top of the cabinet and the top of the container door close to the cabinet in each frame of image. Therefore, it can be understood that the entire image of each frame of image may be analyzed without setting the key region.
In step S12, the visual door opening and closing detection algorithm is based on the comparison between the pixels of the multi-frame image and the selected background pixels, and when the difference between the pixels exceeds the set threshold, it is determined that a door opening action has occurred. The selected background is the area where the position and pixels do not change when the door is opened or closed, such as the background area N shown in FIG. 7, where the background area N is the area on the top of the cabinet near the side of the door of the container. After the background area N is selected, the pixels of the background area N are obtained, the multi-frame image is compared with the background area N frame by frame according to the time sequence, and when the difference value between the pixels of the key area in a certain frame image and the pixels of the background area N exceeds a preset threshold value, it is considered that a door opening action occurs, such as an angle a shown in fig. 7. At this time, it cannot be determined whether the door is open, and the definition of the opening of the container door is that the angle of the door of the container at least reaches the angle for the management end to take the goods for transaction, such as the angle B in fig. 8.
Therefore, it is necessary to further perform step S13a, wherein the obtaining of the connected domain related to the container door change based on the pixel difference value means that when the pixel difference value exceeds the set threshold, the frame of image is subjected to pixel analysis to obtain the connected domain, the angle of the container door change is obtained based on the connected domain, the angle of the container door change is compared with the preset angle, and the opening and closing state of the container door is determined based on the comparison result. The connected domain refers to an image region which is formed by pixels with the same pixel point classification information and adjacent positions in the image to be processed, the same pixel point classification information can be understood as the same pixel value, for example, the pixel values of the door edge region range of the cargo cabinet door are the same, and the pixels with the same pixel value form a connected region. In this step, after the changed angle of the door of the cargo cabinet is obtained, when the angle is larger than the preset angle, the door is considered to be opened or closed, and is in a stage of selecting a commodity by a consumer or finishing an order.
Referring to fig. 9, in a first modification of the step S1 according to the second embodiment of the present invention, the step S13a may be replaced by the following step S13 b:
and step S13b, analyzing the key area in the image by using an edge detection algorithm to obtain the angle of the container door change, comparing the angle of the container door change with a preset angle, and judging the opening and closing state of the container door based on the comparison result. In this step, the image is the current frame image when the pixel difference value exceeds the set threshold value by comparing the pixels of the background area frame by frame.
The edge detection algorithm is mainly realized through a canny operator and a sobel operator. In the present embodiment, the canny operator is used as an example for explanation.
The method mainly comprises the following steps:
t01, performing graying processing on key areas of the multi-frame images;
t02, carrying out Gaussian filtering processing on the grayed image to obtain a smooth image; and
t03, setting a high threshold value and a low threshold value as edge detection parameters;
t04, obtaining the edge of the cargo door and the edge of the top of the cabinet in contact with the cargo door based on the edge detection parameters to further obtain the cargo door variation angle, as shown by the included angle B in FIG. 8.
In step T03, the threshold is set as an edge detection parameter that can retain valid edge feature information and exclude redundant information to obtain a varying angle of the door. The high and low threshold values can be obtained by artificial multiple experiments.
Referring to fig. 10, in a second embodiment of the present invention, in step S1, in a second modification, the step S1 includes the following steps:
step S11', selecting key areas of multi-frame images; and
and step S12', analyzing the key area of the multi-frame image by using an edge detection algorithm to obtain the changed angle of the container door, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
The definition of the edge detection algorithm in step S12' is the same as that in step S13b, and is not described herein again.
It should be particularly noted that, in this embodiment, it is not necessary to calculate a pixel difference between a multi-frame image and a background area, that is, an open-close door angle is directly obtained through an edge detection algorithm, and it is only necessary to directly determine whether the cargo cabinet door is open or closed through the open-close door angle.
Step S1 in the second embodiment of the present invention in modification three, as shown in fig. 11, step S1 in the unmanned counter theft prevention method may be replaced with step S1 ", wherein step S1" includes the steps of:
step S11', judging the changed angle of the container door based on the visual door opening and closing detection algorithm, comparing the changed angle of the container door with a preset angle and obtaining a comparison result;
step S12' of obtaining the auxiliary detection signal of the container door switch; and
and step S13' of further determining the opening and closing state of the cargo door by combining the comparison result and the auxiliary detection signal of the cargo door opening and closing.
The steps S11 "and S12" may be performed simultaneously or the execution sequence may be interchanged.
In step S1 ″, the visual open/close door detection algorithm is the same as that of the first, second and third embodiments, and will not be described herein again.
In step S12 ″, the auxiliary detection signal of the container door switch may be obtained based on monitoring the touch switch disposed on the container door, that is, when the touch switch disposed on the container body is detected to be in contact with the touch switch disposed on the container door, the detection signal corresponds to the closing information; when the touch switch on the cabinet body is separated from the touch switch arranged on the door of the container, the touch switch is correspondingly an opening signal.
Only when the auxiliary detection signal is output that the touch switch on the container door is opened and the visual switch detection module also detects that the container door is in an open state, the container door is considered to be in the open state;
similarly, only when the touch switch on the auxiliary detection signal output position container door is closed and the visual switch detection module also detects that the container door is closed, the container door is considered to be in a closed state.
Referring to fig. 4 again, the anti-theft method for the unmanned counter further includes the following steps:
step S2, detecting the generation state of the order of the unmanned sales counter;
in this step, the generation state of the order of the unmanned sales container may be detected based on a visual inspection model. Specifically, the difference between the two image images before and after the consumer takes the commodity to be purchased can be used for judging whether a new order is generated. Specifically, the difference of the images can be analyzed by extracting the image information in the pictures through a neural network.
Optionally, it is also possible to detect whether a new order is generated based on a weight detection model. For example, when a consumer takes a commodity, the weight detection model senses the weight change, and the detected weight change value can determine that the unmanned sales counter generates a new order.
It should be noted that, in the present invention, the generation of the new order may be determined based on the two-dimensional code scanned by the user or other interaction manner with the unmanned sales counter, and the completion of the new order is also determined based on the two-dimensional code scanned by the user or other interaction manner with the unmanned sales counter.
Referring to fig. 4 again, the anti-theft method for the unmanned counter further includes the steps of:
step S3, judging the running state of the unmanned sales counter by combining the opening and closing state of the cabinet door and the generation state of the order;
referring to fig. 12, in detail, in the step S3, the determining process includes the following steps:
step S31: judging whether the cargo cabinet door is in an open state or not,
if the determination result in the step S31 is yes, that is, if the cargo door is in the open state, the process proceeds to step S32: judging whether a new order is generated;
if a new order is generated, the process proceeds to step S38: the output running state is normal;
if no new order is generated, the process proceeds to step S33: and outputting abnormal operation state, executing step S34 in one step, and uploading alarm information to an alarm system.
If the determination result in step S31 is negative, that is, if the cargo door is in the closed state, the process proceeds to step S35: judging whether a new order is generated;
if a new order is generated, the process proceeds to step S36: outputting abnormal operation state, executing step S37 in one step, and uploading alarm information to an alarm system;
if no new order is generated, the process proceeds to step S38: and outputting the abnormal operation state.
In some other embodiments, step S39 (not shown) is further included between step S35 and step S36, and the method loops to determine whether there is a new order within a preset time range, if there is no order within the preset time range, step S38 is executed, and if there is an order within the preset time range, step S36 and step S37 are executed. The preset time is considered as the set time for automatically closing after unlocking, and the automatic closing of the container door can be controlled by a touch switch system.
Based on the setting of the step S39, the anti-theft method for unmanned counter can be applied to a variety of different application scenarios.
Referring to fig. 4 again, the anti-theft method for the unmanned counter further includes the steps of:
and step S4, when the running state is abnormal, the unmanned sales counter sends alarm information.
Referring to fig. 13, in some embodiments, the step S4 of the anti-theft method for an unmanned counter according to the visual door opening and closing detection algorithm further includes the following steps:
recording an analysis video, and controlling the recording opening or ending of the analysis video based on the opening and closing state of the cargo cabinet door output by the visual door opening and closing detection algorithm, wherein the method specifically comprises the following steps:
step S41, when the door of the cargo cabinet is judged to be opened, the recorded and analyzed video is opened;
step S42, when the container door is closed, ending recording the analysis video; and
and step S43, combining the recorded analysis video with the corresponding time axis and storing the analysis video.
The recorded analysis video is combined with the corresponding time axis, when the storage is convenient and the operation state of the container is abnormal, the management terminal timely calls the corresponding video for analysis and troubleshooting.
Referring to fig. 14, a third embodiment of the present invention provides an unmanned sales counter theft prevention system 20 that can be installed on the unmanned sales counter 10 provided in the first embodiment, and can be used to control the operating state of the unmanned sales counter 10. The unmanned counter theft prevention system 20 includes a visual door opening and closing detection module 201, an order detection module 202, a decision module 203, and an alarm system 204, and specifically,
and the visual door opening and closing detection module 201 is configured to determine the opening and closing state of the cargo cabinet door 102. Referring to fig. 15, the visual switch door detection module 201 specifically includes a pixel detection module 2011 and an edge detection module 2012. The pixel detection module 2011 primarily determines the opening and closing state of the cargo cabinet door 102 based on the pixel difference between multiple frames of images in the real-time video captured by the camera module 103 disposed at the top of the cargo cabinet 101.
After it is determined that the door opening or closing of the cargo cabinet door 102 occurs, the edge detection module 2012 further analyzes the door opening or closing angle, and when the door opening or closing angle exceeds a certain threshold, it is determined that the cargo cabinet door 102 is opened or closed.
Referring again to FIG. 14, the order detection module 202 is configured to detect the generation status of the order of the unmanned sales counter 10. The order detection module 202 is implemented mainly based on a visual detection model, and specifically, can determine whether a new order is generated according to a difference between two image images before and after a commodity to be purchased is taken by a consumer. Specifically, the difference of the images can be analyzed by extracting the image information in the pictures through a neural network.
Optionally, the order detection module 202 may also detect whether a new order is generated based on the weight detection model. For example, when a consumer removes an item, the weight detection model senses a weight change and detects that a new order is generated.
Referring again to fig. 14, the determination module 203 is configured to determine the operation state of the unmanned sales container 10 by combining the opening/closing state of the container door 102 and the generation state of the order. The operation state specifically includes a state when the unmanned sales counter 10 is sold normally and an operation state when the unmanned sales counter 10 is abnormal.
The operating states in the case of an abnormal situation are, for example: due to the human interference with the trigger switch 104, the trigger switch 104 is in an abnormal off state after the order is completed, which causes the article to be stolen.
The determination manner of the determination module 203 is specifically as follows: when the visual door opening and closing detection module 201 determines that the cargo cabinet door 102 is opened, the order detection module 202 further determines whether a new order is generated, if so, the operation state of the unmanned sales container 10 is output to be normal, and if not, the operation state of the unmanned sales container 10 is output to be abnormal;
or, when it is determined that the locker door 102 is closed, it is further determined whether a new order is generated, if a new order is generated, the operation state of the unmanned sales container 10 is output to be abnormal, and if no new order is generated, the operation state of the unmanned sales container 10 is output to be normal.
Further, when the determination module 203 determines that the operation state of the unmanned sales counter 10 is abnormal, the determination module 203 uploads alarm information to the alarm system 204, and the alarm system 204 sends an alarm to notify the management terminal of removing the fault in time, so that the economic loss is reduced.
Referring again to FIG. 14, the alarm system 204 is configured to give an alarm when the operation state of the unmanned cargo container 10 is abnormal.
Referring to fig. 14, in some other embodiments, the unmanned counter theft prevention system 20 further includes a camera control module 205 and a camera storage module 206. The camera control module 205 is configured to control the camera module 103 arranged at the top of the cabinet 103 to record and analyze video based on the opening and closing state of the container door 102 output by the visual door opening detection module 201. The analysis video only collects videos in the time period from door opening to door closing, and the time is generally short and is dozens of seconds, minutes or even shorter. The management end analyzes the analysis video to judge the operation condition of the unmanned sales counter 10.
And the camera storage module 206 is configured to combine the recorded analysis video with a corresponding time axis thereof and store the analysis video. The recorded analysis video is stored by combining with the time axis, so that the management terminal can conveniently find out the corresponding video for analysis according to the time node, and can timely find out the reasons of abnormal conditions and timely make corresponding rescue measures.
Referring now to fig. 16, a block diagram of a computer system 800 suitable for use in implementing a terminal device/server of an embodiment of the present application is shown. The terminal device/server shown in fig. 10 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 16, the computer system 800 includes a Central Processing Unit (CPU)801 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data necessary for the operation of the system 800 are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, a mouse, and the like; an output section 807 including a signal such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 808 including a hard disk and the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. A drive 810 is also connected to the I/O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as necessary, so that a computer program read out therefrom is mounted on the storage section 808 as necessary.
According to embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 809 and/or installed from the removable medium 811. The computer program performs the above-described functions defined in the method of the present application when executed by the Central Processing Unit (CPU) 801. It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may 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.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "for example" programming language or similar programming languages. The program code may execute entirely on the management-side computer, partly on the management-side computer, as a stand-alone software package, partly on the management-side computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the administrative side computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor comprises a visual door opening detection module, an order detection module, a judgment module and an alarm system. Where the names of the units do not in some cases constitute a limitation on the units themselves, for example, the visual open and closed door detection algorithm may also be described as "for detecting the open or closed state of a cargo door". As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be present separately and not assembled into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: the opening and closing state of the goods cabinet door is judged based on a visual opening and closing detection algorithm, the order detection module detects the generation state of the order of the unmanned sales cabinet, the judgment module further judges the running state of the unmanned sales cabinet by combining the opening and closing state of the goods cabinet door and the generation state of the order, and the alarm system sends alarm information based on the abnormal running state of the unmanned goods cabinet.
Compared with the prior art, the opening and closing state of the door of the cargo cabinet is judged based on the visual door opening and closing detection algorithm, so that the door opening and closing mode of the door of the cargo cabinet is judged more simply, quickly and accurately, and some lock cheating behaviors are avoided; and the operation state of the unmanned sales counter is judged by combining the opening and closing state of the counter door and the generation state of the order, the real-time sales condition of the unmanned sales counter can be accurately judged, the artificial interference phenomenon is avoided, when the operation state is abnormal, the unmanned sales counter sends alarm information, the management terminal can be timely informed of the problem to be processed, and the economic loss is reduced.
The visual door opening and closing detection algorithm judges the opening and closing state of the cargo cabinet door based on the pixel difference of key areas in multi-frame images, can well reduce the range of image processing areas, improves the processing efficiency, can quickly capture door opening or closing signals, and quickly monitors the opening and closing state.
Whether the container door is opened or closed is preliminarily judged through pixel difference among the multi-frame images, and the opening or closing state of the container door is further judged by combining edge information of the container door, so that the state judgment of opening and closing the container door is more accurate.
The unmanned counter theft prevention method further includes the steps between step S1 and step S2: the opening and closing state of the door of the cargo container is further judged based on the auxiliary signal detection structure for opening and closing the door of the cargo container; alternatively, before step S1, the opening/closing state of the container door may be determined by the auxiliary signal detection structure of the container door opening/closing, so as to better detect whether there is a fraudulent locking operation, and to more accurately analyze the operation state of the unmanned sales container.
The analysis video is recorded and controlled to be opened or closed based on the opening and closing state of the cargo cabinet door output by the visual door opening and closing detection algorithm, when the cargo cabinet door is judged to be opened, the recorded analysis video is opened, when the cargo cabinet door is closed, the recorded analysis video is combined with the corresponding time axis of the recorded analysis video, the analysis video is stored, the time length of the analysis video can be well controlled, and when the management end receives an abnormal signal, the corresponding analysis video analysis reason can be found in time, and faults can be eliminated in time.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. An anti-theft method for an unmanned sales counter is characterized in that: the unmanned sales counter comprises a counter door, and the anti-theft method of the unmanned sales counter comprises the following steps:
s1, judging the change angle of the container door based on a visual door opening and closing detection algorithm, comparing the change angle of the container door with a preset angle to obtain a comparison result, and judging the opening and closing state of the container door based on the comparison result;
s2, detecting the generation state of the order of the unmanned sales counter;
s3, judging the running state of the unmanned sales counter by combining the opening and closing state of the door of the cabinet and the generation state of the order, further judging whether a new order is generated or not when judging that the door of the cabinet is opened, if so, outputting the running state of the unmanned sales counter to be normal, and if not, outputting the running state of the unmanned sales counter to be abnormal;
or when the container door is judged to be closed, further judging whether a new order is generated, if so, outputting that the running state of the unmanned sales container is abnormal, and if not, outputting that the running state of the unmanned sales container is normal; and
s4, when the running state is abnormal, sending alarm information; controlling the recording, starting or ending of the analysis video based on the opening and closing state of the cargo cabinet door, starting the recording and analysis video when the cargo cabinet door is judged to be opened, and ending the recording and analysis video when the cargo cabinet door is closed; and the recorded analysis video is stored in combination with the corresponding time axis.
2. The anti-theft method for unmanned counter according to claim 1, characterized in that: the step S1 includes at least the following steps:
step S11, selecting a key area of the multi-frame image;
step S12, comparing the pixel difference of key areas in the multi-frame images based on a visual door opening and closing detection algorithm, and obtaining a pixel difference value; and
and S13a, obtaining a connected domain related to the change of the container door based on the pixel difference value, acquiring the changed angle of the container door based on the connected domain, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
3. The anti-theft method for unmanned counter according to claim 1, characterized in that: the step S1 further includes the steps of:
step S11, obtaining multi-frame images and selecting key areas of the multi-frame images;
step S12, comparing the pixel difference of key areas in the multi-frame images based on a visual door opening and closing detection algorithm, and obtaining a pixel difference value; and
and S13b, analyzing the key area in the multi-frame image by using an edge detection algorithm to obtain the changed angle of the container door, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
4. The anti-theft method for unmanned counter according to claim 1, characterized in that: the step S1 further includes the steps of:
step S11', selecting key areas of multi-frame images; and
and step S12', analyzing the key area of the multi-frame image by using an edge detection algorithm to obtain the changed angle of the container door, comparing the changed angle of the container door with a preset angle, and judging the opening and closing state of the container door based on the comparison result.
5. The anti-theft method for unmanned counter according to claim 1, characterized in that: the step S1 further includes the steps of:
step S11', judging the changed angle of the container door based on the visual door opening and closing detection algorithm, comparing the changed angle of the container door with a preset angle and obtaining a comparison result;
step S12' of obtaining the auxiliary detection signal of the container door switch;
step S13', the opening and closing state of the cargo door is further determined by combining the comparison result and the auxiliary detection signal of the cargo door opening and closing,
the steps S11 "and S12" may be performed simultaneously or the execution sequence may be interchanged.
6. An unmanned sales counter anti-theft system which characterized in that: wherein, unmanned sales counter includes the goods cupboard door, unmanned sales counter anti-theft system includes:
the visual door opening and closing detection module is configured for judging the opening and closing state of the cargo cabinet door;
the order detection module is configured for detecting the generation state of the order of the unmanned sales counter;
the judging module is used for judging the running state of the unmanned sales counter by combining the opening and closing state of the door of the goods cabinet and the generation state of the order, further judging whether a new order is generated or not when the judging module judges that the door of the goods cabinet is opened, if so, outputting the normal running state of the unmanned sales counter, and if not, outputting the abnormal running state of the unmanned sales counter;
or when the judging module judges that the container door is closed, further judging whether a new order is generated, if so, outputting the abnormal running state of the unmanned sales container, and if not, outputting the normal running state of the unmanned sales container; and
and the alarm system is configured to send out alarm information when the operation state of the unmanned goods receiving cabinet is abnormal.
7. The unmanned counter theft prevention system of claim 6, wherein: the anti-theft system for the unmanned counter further comprises:
the camera shooting control module is used for controlling the analysis video recording to be opened or closed based on the opening and closing state of the cargo cabinet door output by the visual door opening and closing detection module;
and the camera shooting storage module is used for combining the recorded analysis video with the corresponding time axis for storage.
8. The utility model provides an unmanned sales counter with theftproof function which characterized in that: the unmanned sales counter comprises a counter body, a counter door connected with the counter body in an opening and closing mode and at least one camera module arranged on the counter body; the unmanned sales counter further comprises a control device electrically connected with the camera module, and the control device further comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910051355.6A CN109887161B (en) | 2019-01-19 | 2019-01-19 | Anti-theft method and system for unmanned sales counter and unmanned sales counter with anti-theft function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910051355.6A CN109887161B (en) | 2019-01-19 | 2019-01-19 | Anti-theft method and system for unmanned sales counter and unmanned sales counter with anti-theft function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109887161A CN109887161A (en) | 2019-06-14 |
| CN109887161B true CN109887161B (en) | 2020-10-09 |
Family
ID=66926310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910051355.6A Active CN109887161B (en) | 2019-01-19 | 2019-01-19 | Anti-theft method and system for unmanned sales counter and unmanned sales counter with anti-theft function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109887161B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110853269B (en) * | 2019-11-20 | 2021-06-22 | 四川研宝科技有限公司 | Door state detection method and device |
| CN111178145A (en) * | 2019-12-06 | 2020-05-19 | 深圳市中电数通智慧安全科技股份有限公司 | Method and device for identifying illegal operation, terminal equipment and computer storage medium |
| CN113837400B (en) * | 2020-06-08 | 2024-04-16 | 菜鸟智能物流控股有限公司 | Fault processing and device for logistic object delivery device |
| CN111968309A (en) * | 2020-08-25 | 2020-11-20 | 武汉迪航科技有限公司 | Automatic change equipment and intelligence control system |
| CN112580432B (en) * | 2020-11-23 | 2023-09-22 | 江苏省新通智能交通科技发展有限公司 | Gate dislocation detection method and detection system |
| CN112967442A (en) * | 2021-01-29 | 2021-06-15 | 湖南擎谱数字科技有限公司 | Vending machine goods anti-theft device and control method thereof |
| CN113465144A (en) * | 2021-06-24 | 2021-10-01 | 惠州华京电子科技有限公司 | Guest room disinfection regulation and control method and purifier |
| CN113960943B (en) * | 2021-09-23 | 2024-06-21 | 德迅创新(深圳)有限公司 | Door state detection method based on multi-bin public service intelligent device |
| CN114241680A (en) * | 2021-12-16 | 2022-03-25 | 广州乐摇摇信息科技有限公司 | Intelligent medicine selling system based on Internet of things |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4117465A (en) * | 1977-04-07 | 1978-09-26 | Timblin Stanley W | Alarm system for vending machines |
| US6420972B1 (en) * | 2000-10-18 | 2002-07-16 | Wms Gaming, Inc. | Door monitor for a gaming machine |
| CN103986906B (en) * | 2014-05-08 | 2017-05-10 | 杭州同尊信息技术有限公司 | Door opening and closing detection method based on monitoring videos |
| CN108877040A (en) * | 2018-06-04 | 2018-11-23 | 北京无人店科技有限公司 | Automatic monitoring method, device, electronic equipment and the computer readable storage medium of open unmanned counter |
| CN108961545A (en) * | 2018-06-14 | 2018-12-07 | 深圳市丰宜科技有限公司 | Shelf monitor system and shelf monitor method |
| CN108831017A (en) * | 2018-08-03 | 2018-11-16 | 杭州比智科技有限公司 | Intelligent goods selling equipment and method |
| CN108922029A (en) * | 2018-08-15 | 2018-11-30 | 济南每日优鲜便利购网络科技有限公司 | Vending equipment and its control method |
-
2019
- 2019-01-19 CN CN201910051355.6A patent/CN109887161B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109887161A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109887161B (en) | Anti-theft method and system for unmanned sales counter and unmanned sales counter with anti-theft function | |
| JP6550105B2 (en) | Verification of fraudulent behavior in self checkout terminals | |
| US20200279310A1 (en) | Notification system and methods for use in retail environments | |
| US20100114617A1 (en) | Detecting potentially fraudulent transactions | |
| US8429016B2 (en) | Generating an alert based on absence of a given person in a transaction | |
| US10366379B2 (en) | Remote weigh station with delayed fraud intervention | |
| CN110363626B (en) | Behavior mode monitoring method for unmanned container, electronic equipment and unmanned container | |
| CN110084959A (en) | Unmanned retail cabinet and its working method, user terminal with monitoring function | |
| CN109711359B (en) | Vending machine control method, vending machine control device and computer-readable storage medium | |
| US20160351022A1 (en) | Device fraud indicator detection and reporting | |
| KR101850376B1 (en) | POS terminal monitoring system and Method for controlling the same | |
| KR20170112315A (en) | System for mornitoring cash drawer of store using pos terminal and camera in store | |
| CN114419781A (en) | Method for reminding that camera equipment is shielded, vending terminal, storage medium and device | |
| CN115546703B (en) | Risk identification method, device and equipment for self-service cash register and storage medium | |
| CN117876958B (en) | Unattended market operation management system and method | |
| US20240177576A1 (en) | Imaging Systems and Methods for Monitoring Items in Predetermined Areas | |
| CN117115978A (en) | Self-service cashing loss prevention method, device and equipment | |
| CN116957726A (en) | Order processing method, order processing device, electronic equipment and storage medium | |
| CN114005068A (en) | Method and device for monitoring movement of goods | |
| CN118506274A (en) | Cash register loss prevention application method and monitoring system | |
| CN112001349A (en) | Data auditing method and system and electronic equipment | |
| CN117789381A (en) | Abnormality recognition method, apparatus, device and storage medium | |
| CN117953428A (en) | Method, device, equipment, storage medium and product for alarming falling objects | |
| KR101212466B1 (en) | Video monitoring method | |
| CN113593142A (en) | Automatic Teller Machine (ATM) patrolling method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |