Systems and methods to detect shrink events
The integration of separate RFID readers and video surveillance in retail settings allows for the detection and documentation of shrink events, improving loss prevention by correlating RFID data with visual evidence.
Patent Information
- Application Number
- PCT/US2025/010938
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-01-12
- Filing Date
- 2025-01-09
- Publication Date
- 2025-07-17
AI Technical Summary
Retail environments face challenges in detecting shrink events, such as shoplifting, due to the lack of integrated systems that can verify whether merchandise is properly paid for, often due to cost and technological constraints.
Implementing an inferential transaction RFID reader at a restricted access area separate from the transaction terminal and an exit point RFID reader at the egress zone, combined with video surveillance, to identify and generate data files on shrink events by correlating RFID data with image frames and object detection.
Effectively identifies and documents shrink events, providing detailed data for investigation and potential prosecution, enhancing loss prevention in retail environments.
Smart Images

Figure US2025010938_17072025_PF_FP_ABST
Abstract
Description
SYSTEMS AND METHODS TO DETECT SHRINK EVENTSCROSS-REFERENCE TO RELATED APPLICATIONS
[0001] The current application claims priority to, and the benefit of, United States Provisional Application No. 63 / 620,589 filed January 12, 2024 and entitled “SYSTEMS AND METHODS TO DETECT SHRINK EVENTS,” the contents of which are hereby incorporated by reference in their entireties.BACKGROUND
[0002] In a retail environment, lost, stolen, or misplaced merchandises may result in loss revenue for the store . For example, a shoplifter may make a purchase and place additional unpaid merchandise into the shopping bag when leaving the store. While certain technologies (e.g., radio frequency identification (RFID) systems) may be able to detect a merchandise leaving a store (i.e., detecting the associated RFID tag leaving the store), an integrated system that includes both point of sale (POS) and RFID integration may be necessary to ascertain whether the merchandise is a properly paid merchandise or a shoplifted item. However, an integrated system may not be available due to cost and / or technological constraints. Therefore, improvements in loss prevention may be desirable.SUMMARY
[0003] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the DETAILED DESCRIPTION. This summary is not intended to identify key features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
[0004] Systems and methods of shrink detection include an inferential transaction RFID reader located at a restricted access area adjacent to, but separate from and independent of, a transaction terminal in an environment. The inferential transaction RFID reader scans one or more first RFID tags within a pre-transaction zone, e.g., at a location spaced apart from the transaction terminal, and obtains inferential transaction RFID data from each of the one or more first RFID tags. The system and method additionally include an exit point RFID reader positioned at an egress zone that leads out of the environment. The exit point RFID reader scans one or more second RFID tags at the egress zone and obtains exit point RFID data from each of the one or more second RFID tags. A shrinkdetector component compares exit point RFID data from each of the one or more second RFID tags to the inferential transaction RFID data from each of the one or more first RFID tags, and identifies a shrink event for each exit point RFID data that does not have a match with one of the inferential transaction RFID data.
[0005] Additionally, the systems and methods include a video surveillance system that captures one or more image frames of the one or more portions of the environment, including the egress zone, wherein each image frame has a corresponding image time stamp. Further, the exit point RFID reader can generate an exit point timestamp for each exit point RFID data. And, optionally, the inferential transaction RFID reader can generate an inferential transaction time stamp for each of the inferential transaction RFID data. In this case, the system and method may further include a shrink event correlator component to obtain a set of one or more exit image frames having a respective image time stamp that corresponds to the exit point timestamp of the exit point RFID data associated with the shrink event. Optionally, the shrink event correlator may have product and store location information associated with each RFID tag, and the shrink event correlator may additionally obtain a set of one or more environment image frames, from a location within the environment corresponding the product and store location information associated with the exit point RFID data associated with the shrink event. In this case, the set of one or more environment image frames have a respective image time stamp that corresponds to a time period before the exit point time stamp of the exit point RFID data associated with the shrink event.
[0006] Further, the systems and methods include an object detector that identifies one or more exit object information, such as data that identifies an article of clothing associated with a person in the set of one or more exit image frames having the respective image time stamp that corresponds to the exit point timestamp of the exit point RFID data associated with the shrink event. Additionally, the object detector can identify one or more in-store object information, such as data that identifies an article of clothing associated with a person in the set of one or more environment image frames corresponding to the time period before the exit point timestamp of the exit point RFID data associated with the shrink event. Moreover, the object identifier can determine one or more matching object information based on at least a portion of the one or more exit object information being the same as or similar to at least a portion of the one or more instore object information.
[0007] The systems and methods may additionally include a shrink event data packager that generates one or more data files including the exit point RFID data associated with the shrink event, the set of one or more exit image frames having a respective image time stamp that corresponds to the exit point timestamp of the exit point RFID data associated with the shrink event, the set of one or more environment image frames corresponding to the time period before the exit point timestamp of the exit point RFID data associated with the shrink event, and / or the one or more matching object information.BRIEF DESCRIPTION OF THE DRAWINGS
[0008] The features believed to be characteristic of aspects of the disclosure are set forth in the appended claims. In the description that follows, like parts are marked throughout the specification and drawings with the same numerals, respectively. The drawing figures are not necessarily drawn to scale and certain figures may be shown in exaggerated or generalized form in the interest of clarity and conciseness. The disclosure itself, however, as well as a preferred mode of use, further objects and advantages thereof, will be best understood by reference to the following detailed description of illustrative aspects of the disclosure when read in conjunction with the accompanying drawings, wherein:
[0009] FIG. 1 illustrates an example of an environment for implementing loss prevention in accordance with aspects of the present disclosure;
[0010] FIG. 2 illustrates an example of a radio frequency identification (RFID) system in accordance with aspects of the present disclosure;
[0011] FIG. 3 illustrates an example of a method for training a neural network for image analytics in accordance with aspects of the present disclosure;
[0012] FIG. 4 illustrates an example of a method for implementing the loss prevention in accordance with aspects of the present disclosure; and
[0013] FIG. 5 illustrates an example of a computer system in accordance with aspects of the present disclosure.DETAILED DESCRIPTION
[0014] The following includes definitions of selected terms employed herein. The definitions include various examples and / or forms of components that fall within the scope of a term and that may be used for implementation. The examples are not intended to be limiting.
[0015] The term “processor,” as used herein, can refer to a device that processes signals and performs general computing and arithmetic functions. Signals processed by the processor can include digital signals, data signals, computer instructions, processor instructions, messages, a bit, a bit stream, or other computing that can be received, transmitted and / or detected. A processor, for example, can include microprocessors, microcontrollers, digital signal processors (DSPs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform the various functionality described herein.
[0016] The term “bus,” as used herein, can refer to an interconnected architecture that is operably connected to transfer data between computer components within a singular or multiple systems. The bus can be a memory bus, a memory controller, a peripheral bus, an external bus, a crossbar switch, and / or a local bus, among others.
[0017] The term “memory,” as used herein, can include volatile memory and / or nonvolatile memory. Non-volatile memory can include, for example, ROM (read only memory), PROM (programmable read only memory), EPROM (erasable PROM) and EEPROM (electrically erasable PROM). Volatile memory can include, for example, RAM (random access memory), synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), and direct RAM bus RAM (DRRAM).
[0018] In some aspects of the present disclosure, a loss prevention system and method includes detecting a shrink event based on detecting an RFID tag associated with merchandise in an egress zone of a store in combination with failing to detect a corresponding RFID tag in restricted access area spaced apart from and independent of a transaction terminal that processes payment for the merchandise. Additionally, the system and method receive and correlate one or more images that identify one or more features, one or more objects, or environmental information associated with a person triggering the egress event. Additionally, the system and method generate a data file of the shrink event, including data identifying at least one of a time of the shrink event, the merchandise, the one or more features of the person, the one or more objects associated with the person, or the environmental information associated with the person.
[0019] Referring to FIG. 1, in a non-limiting implementation, an example of an environment 100 (e.g., a retail store) for loss prevention according to aspects of thepresent disclosure is shown. The environment may include a merchandise 102 having a radio frequency identification (RFID) tag 104 attached to the merchandise 102. A person 124 may carry the merchandise 102 out of the environment 100 (e.g., after a legitimate purchase or shoplifting). The environment 100 may include a first RFID reader 112-a configured to read the content of an RFID tag 104 as described below. The environment 100 may include a second RFID reader 112-b configured to read the content of the RFID tag 104 as described below. The first RFID reader 112-amay be an inferential transaction RFID reader located at a restricted access area 116 adjacent to a transaction terminal 117 in the environment 100. In other words, the first RFID reader 112-a is spaced apart from and independent of the transaction terminal 117, such that the first RFID reader 112-a obtain the content of the RFID tag 104 separate from any transaction conducted on the transaction terminal 117 to purchase the merchandise 102. In this case, the restricted access area 116 includes an area through which the person 124 traverses before reaching the transaction terminal 117. In some cases, for instance, the restricted access area 116 may be the end of a lane leading to one or more transaction terminals 117, wherein such a lane is separate from other areas of the environment 100, and wherein the first RFID reader 112-a is positioned at or adjacent to the end of the lane. In other aspects, the first RFID reader 112-a may be disposed at the restricted access area 116. For example, the first RFID reader 112-a may be disposed next to the transaction terminal 117. As such, the first RFID reader 112-amay scan the RFID tag 104 at the point of sale (e.g., customers paying for the merchandise 102 at the transaction terminal 117).
[0020] In some aspects, the second RFID reader 112-b may be an exit point RFID reader positioned at an egress zone 118 that leads out of the environment 100. The environment 100 may include a video surveillance system having one or more cameras 110 that capture one or more images 130 in or near the egress zone in the environment 100.
[0021] In some implementations, the environment 100 may include a server 140 and an optional data repository 141. The server 140 may include one or more processors and / or one or more memories as described above. The server 140 may include a communication component 142 that sends and / or receives data to / from other devices (explained below). The server 140 may include a loss detection component 144 configured to determine whether the merchandise 102 is being removed by the person 124 after a legitimate purchase or stolen by the person 124 from the environment 100. The server 140 may include an object detector 146 configured to identify one or more features, one or moreobjects, and / or environmental information associated with the person 124. The object detector 146 may optionally utilize a neural network 300 (FIG. 3) to implement the identification. The server 140 may include shrink event data packager 148 configured to generate shrink data as described below. The server 140 may communicate with the one or more cameras 110, the first RFID reader 112-a, and / or the second RFID reader 112-b via communication links 150, 152, 154. The communication links 150, 152, 154 may be wired or wireless communication channels.
[0022] Aspects of the present disclosure may ascertain, based on a probability assigned, whether the merchandise 102 is removed from the environment 100 as a legitimate purchase or in a shrink event as described below.
[0023] In a first instance, the person 124 may be in possession of the merchandise 102 in the environment 100. The person 124 may pass through the restricted access area 116. As noted, the restricted access area 116 may be adjacent to, but separate from and independent of, a point of sale (POS) area including the transaction terminal 117 for purchasing merchandises in the environment 100. In other aspects, the restricted access area 116 may include the transaction terminal 117. The restricted access area 116 may include one or more lines, lanes, or aisles directing customers of a retail store to the transaction terminal 117 to purchase merchandises. For instance, the transaction terminal 117 may be a POS terminal operated by an employee of the store, or may be a selfcheckout terminal. In other words, the restricted access area 116 may include any area a bona fide purchaser will access on the way to the transaction terminal 117, which is generally an area that a shoplifter will avoid. As the person 124 passes through the restricted access area 116, the first RFID reader 112-a may read the RFID tag 104 as follows.
[0024] In some aspects, the first RFID reader 112-a may transmit an interrogating signal 164 to the RFID tag 104, and receive, in response to the interrogating signal 164, a response signal 166 from the RFID tag 104. The response signal 166 may include an RFID identifier. The first RFID reader 112-a may transmit information associated with the restricted access area event, including the RFID identifier, to the server 140 via the communication link 152. The information associated with the restricted access area event may include the RFID identifier of the RFID tag 104, the time and / or location of the restricted access area event, information of the merchandise 102, and / or other suitable information. After receiving the RFID identifier from the first RFID reader 112-a, theserver 140 may determine that the person 124 has approached the restricted access area 116.
[0025] Next, the person 124 may pass through the egress zone 118 while still in possession of the merchandise 102. The egress zone 118 may be an exit of the environment 100. As the person 124 passes through the egress zone 118, the second RFID reader 112-b may read the RFID tag 104 as follows.
[0026] In some aspects, the second RFID reader 112-b may transmit an interrogating signal 174 to the RFID tag 104, and receive, in response to the interrogating signal 174, a response signal 176 from the RFID tag 104. The response signal 176 may include the RFID identifier. The second RFID reader 112-b may transmit information associated with the egress event (including exit point RFID data), including the RFID identifier, to the server 140 via the communication link 154. The information associated with the egress event may include the RFID identifier of the RFID tag 104, the time and / or location of the egress event, information of the merchandise 102, and / or other suitable information. After receiving the RFID identifier from the second RFID reader 112-b, the server 140 may determine that the person 124 has approached the egress zone 118.
[0027] In some aspects, the restricted access area 116 and the egress zone 118 may be sufficiently far away from away from each other such that the first RFID reader 112-a does not read the RFID tag 104 when the RFID tag 104 (and the merchandise 102) is in the egress zone 118 and the second RFID reader 112-b does not read the RFID tag 104 when the RFID tag 104 (and the merchandise 102) is in the restricted access area 116.
[0028] Next, in some examples, the one or more cameras 110 may capture the one or more images 130. Each of the one or more images 130 may be time stamped to properly associate the one or more images 130 with the person 124 passing through the egress zone 118 at a given time. The one or more cameras 110 may transmit the one or more images 130 to the server 140 via the communication link 150. The object detector 146 may use the one or more images 130 to identify features and / or objects associated with the person 124.
[0029] In an aspect of the present disclosure, the loss detection component 144 of the server 140 may determine that the person 124 has approached both the restricted access area 116 and the egress zone 118 based on the RFID identifier transmitted by the first RFID reader 112-a and the second RFID reader 112-b. As such, the loss detectioncomponent 144 may determine that the person 124 made a legitimate purchase of the merchandise 102 and is a customer.
[0030] In a second instance, the person 124 may be in possession of the merchandise 102 in the environment 100. The person 124 may bypass the restricted access area 116. Consequently, the first RFID reader 112-a may be unable to read the RFID tag 104.
[0031] Next, the person 124 may pass through the egress zone 118 while in possession of the merchandise 102. As the person 124 passesthroughthe egress zone 118, the second RFID reader 112-b may read the RFID tag 104 by transmitting the interrogating signal 174 to the RFID tag 104, and receiving, in response to the interrogating signal 174, the response signal 176 from the RFID tag 104. The response signal 176 may include the RFID identifier. The second RFID reader 112-b may transmit information associated with the egress event (including exit point RFID data), including the RFID identifier, to the server 140 via the communication link 154. The information associated with the egress event may include the RFID identifier of the RFID tag 104, the time and / or location of the egress event, information of the merchandise 102, and / or other suitable information. After receiving the RFID identifier from the second RFID reader 112-b, the server 140 may determine that the person 124 has approached the egress zone 118.
[0032] Next, in some examples, the one or more cameras 110 may capture the one or more images 130. Each of the one or more images 130 may be time stamped to properly associate the one or more images 130 with the person 124 passing through the egress zone 118 at a given time. The one or more cameras 110 may transmit the one or more images 130 to the server 140 via the communication link 150. The object detector 146 may use the one or more images 130 to identify features and / or objects associated with the person 124.
[0033] In some aspect of the present disclosure, the loss detection component 144 of the server 140 may determine that the person 124 bypassed restricted access area 116 and passed through the egress zone 118 based on the RFID identifier transmitted by the second RFID reader 112-b and not by the first RFID reader 112-a. As such, the loss detection component 144 may determine that the person 124 attempted to leave the environment with the merchandise 102 without purchase, and is a potential shoplifter.
[0034] In certain aspects, the object detector 146 may use the one or more images 130 to identify features (e.g., appearance, height, build, gait, hair color, eye color, gender, ethnicity, etc.) and / or objects (e.g., accessories such as hats and glasses, clothing, and / orjewelry worn by the person 124) associated with the person 124. The object detector 146 may use the one or images 130 to identify environmental information associated with the person 124 such as cars driven, potential witnesses, accomplices, etc.
[0035] In some aspects, the shrink event data packager 148 may generate one or more data fdes associated with a shrink event. The one or more data fdes may include information of the merchandise 102 (e.g., costs, numbers, etc.), the exit point RFID data associated with the shrink event, the set of one or more exit image frames having a respective image time stamp that corresponds to the exit point timestamp of the exit point RFID data associated with the shrink event, the set of one or more environment image frames corresponding to the time period before the exit point timestamp of the exit point RFID data associated with the shrink event, and / or the one or more matching object information. The one or more data fdes may be generated based on one or more of the information associated with the egress event, the features identified by the object detector 146 using the one or more images 130, the objects identified by the object detector 146 using the one ormore images 130, and / orthe environmental information identified by the object detector 146 using the one or more images 130.
[0036] In some aspects, the communication component 142 may provide the one or more data files associated with the shrink event to an authorized personnel 170 associated with the environment 100 for further investigation. For example, the authorized personnel 170 may use the information in the one or more data files to identify the identities of the person 124, potential witnesses, and / or accomplices. The authorized personnel 170 may provide the information to law enforcement agencies for prosecution.
[0037] Referring to FIGs. 1 and 2, an example of an RFID system 200 may include the RFID reader 112 (which may be the first RFID reader 112-a or the second RFID reader 112-b) for scanning the RFID tag 104. The RFID reader 112 may include a processor 210 that executes instructions stored in a main memory 212 for performing the functions described herein. The processor 210 and / or the main memory 212 may be implemented as described above.
[0038] The processor 210 may include the RFID component 211 that causes the RFID driver 220 to transmit the interrogating signals 164, 174, via a transmitting coil 222, to the RFID tag 104. The RFID driver 220 may energize the transmitting coil 222 to transmit the interrogating signals 164, 174. The transmitting coil 222 may include one or more inductors that transmit or receive electromagnetic signals.
[0039] Additionally, in some non-limiting examples, the RFID tag 104 may include a controller 240 that generates the response signals 166, 176 in response to receiving the interrogating signals 164, 174. The RFID tag 104 may include a tag coil 242 configured to receive the interrogating signals 164, 174 from the transmitting coil 222.
[0040] During operation, in some implementations, the processor 210 and / or the RFID component 211 may cause the RFID driver 220 to transmit the interrogating signals 164, 174 via the transmitting coil 222. The tag coil 242 of the RFID tag 104 may receive the interrogating signals 164, 174. An electrical current generated from the reception of the interrogating signals 164, 174 may flow to the controller 240 to provide electrical energy to the controller 240.
[0041] In response to receiving the interrogating signals 164, 174, the controller 240 may generate the response signals 166, 176. The response signals 166, 176 may include the RFID identifier that may be associated with a merchandise, such as the merchandise 102. The controller 240 may transmit the response signals 166, 176 via the tag coil 242 back to the reader coil 242.
[0042] In certain implementations, the interrogating signals 164, 174 may be a direct current signal or an alternative current signal. The interrogating signals 164, 174 may use less than 1 milli-Joules (mJ), 0.5 mJ, 0.3 mJ, 0.1 mJ, 0.05 mJ, or 0.01 mJ.
[0043] Turning to FIG. 3, an example of training a neural network 300 for identification may include feature layers 302 that receive training images 312 of features / objects / environment 314. The training images 312 may include images of the features / objects / environment 314 from different angles, under different lighting conditions, partial images of the features / objects / environment 314, etc. The feature layers 302 may be a deep learning algorithm that includes feature layers 302-1, 302-2... , 302- n-1, 302-n. Each of the feature layers 302-1, 302-2... , 302-n-l, 302-n may perform a different function and / or algorithm (e.g., pattern detection, transformation, feature extraction, etc.). In a non-limiting example, the feature layer 302-1 may identify edges of the training images 312, the feature layer 302-2 may identify comers of the training images 312, the feature layer 302-n-l may perform a non-linear transformation, and the feature layer 302-n may perform a convolution. In another example, the feature layer 302-1 may apply an image filter to the training images 312, the feature layer 302-2 may perform a Fourier Transform to the training images 312, the feature layer 302-n-l may perform an integration, and the feature layer 302-n may identify a vertical edge and / or ahorizontal edge. Other implementations of the feature layers 302 may also be used to extract features of the training images 312.
[0044] In certain implementations, the output of the feature layers 302 may be provided as input to a classification layer 304. The classification layer 304 may be configured to identify the features (e.g., appearance, height, build, hair color, ethnicity, etc.), objects (e.g., accessories such as hats and glasses, clothing, and / or jewelry worn by the person 124), and / or environmental information (e.g., cars driven, potential witnesses, accomplices, etc.) associated with the person 124.
[0045] In some implementations, the classification layer 304 may output the ID label. A classification error component 306 may receive the ID label and a ground truth ID as input. The ground truth ID may be the “correct answer” provided by a trainer (not shown) to the neural network 300 during training. For example, the neural network 300 may compare the ID label to the ground truth ID to determine whether the classification layer 304 properly identifies the features / objects / environment associated with the ID label.
[0046] In some instances, the neural network 300 may include a feedback component 308. Based on the ID label and the ground truth ID, the classification error component 306 may output an error into the feedback component 308. The feedback component 308 may receive the error and provide one or more updated parameters 320 to the feature layers 302 and / or the classification layer 304. The one or more updated parameters 320 may include modifications to parameters and / or equations to reduce the error.
[0047] In some examples, the neural network 300 may include a flatten function 330 that generates a final output of the feature extraction step. For example, the flatten function 330 may be an operator that transforms a matrix of features into a vector. The output of the neural network 300 may include a vector describing the features / objects / environment.
[0048] Turning to FIG. 4, an example of a method 400 for loss prevention may be performed by the server 140 and / or one or more of the communication component 142, the loss detection component 144, the object detector 146, and / or the shrink event data packager 148.
[0049] At block 402, the method 400 may include receiving, from a first RFID reader disposed at an egress zone, egress event information associated with the first RFID reader receiving a first RFID response signal from an RFID tag appended to a merchandise.
[0050] At block 404, the method 400 may include receiving, from one or more cameras 110, one or more images 130 associated with an egress event identified in the egress event information.
[0051] At block 406, the method 400 may include determining an occurrence of a shrink event associated with the merchandise based on the egress event information and an absence of restricted access area information that indicates the RFID tag has not been scanned by a second RFID reader disposed at a restricted access area.
[0052] At block 408, the method 400 may include correlating the one or more images with the shrink event. In some aspects, the method 400 may optionally include correlating the one or more images with the shrink event based on a first time of the one or more images and a second time of shrink event. In other aspects, the method 400 may optionally include correlating the one or more images with the shrink event based on a first time of the one or more images, a second time of shrink event, and / or location of the shrink event and the captured images.
[0053] At block 410, the method 400 may include identifying one or more features, one or more objects, or environmental information associated with a person triggering the egress event.
[0054] At block 412, the method 400 may include generating a data file, of the shrink event, including data identifying at least one of a time of the shrink event, the merchandise, the one or more features of the person, the one or more objects associated with the person, or the environmental information associated with the person.
[0055] Aspects of the present disclosure include a method for receiving, from a first RFID reader disposed at an egress zone, egress event information associated with the first RFID reader receiving a first RFID response signal from an RFID tag appended to a merchandise, receiving, from one or more cameras 110, one or more images 130 associated with the egress event, determining an occurrence of a shrink event associated with the merchandise based on the egress event information and an absence of restricted access area information that indicates the RFID tag has not been scanned by a second RFID reader disposed at an restricted access area, correlating the one or more images with the shrink event, identifying one or more features, one or more objects, or environmental information associated with a person triggering the egress event, and generating a data file, of the shrink event, including data identifying at least one of a time of the shrinkevent, the merchandise, the one or more features of the person, the one or more objects associated with the person, or the environmental information associated with the person.
[0056] Aspects of the present disclosure include the method above, wherein the restricted access area includes a transaction terminal in a point of sale area.
[0057] Aspects of the present disclosure include any of the methods above, wherein the restricted access area is adjacent to a transactional terminal in a point of sale area.
[0058] Aspects of the present disclosure include any of the methods above, wherein correlating the one or more images with the shrink event comprises correlating the one or more images with the shrink event based on a first time of the one or more images and a second time of the shrink event.
[0059] Aspects of the present disclosure include any of the methods above, wherein correlating the one or more images with the shrink event comprises correlating the one or more images with the shrink event based on the first time of the one or more images overlaps with the second time of the shrink event.
[0060] Aspects of the present disclosure include any of the methods above, further comprising transmitting the data file of the shrink event to a law enforcement agency.
[0061] Aspects of the present disclosure include any of the methods above, wherein identifying the one or more features comprises identifying the one or more features using a neural network.
[0062] Aspects of the present disclosures may be implemented using hardware, software, or a combination thereof and may be implemented in one or more computer systems or other processing systems. In an aspect of the present disclosures, features are directed toward one or more computer systems capable of carrying out the functionality described herein. An example of such the computer system 500 is shown in FIG. 5. In some examples, the server 140 may be implemented as the computer system 500 shown in FIG. 5. The server 140 may include some or all of the components of the computer system 500.
[0063] The computer system 500 includes one or more processors, such as processor 504. The processor 504 is connected with a communication infrastructure 506 (e.g., a communications bus, cross-over bar, or network). Various software aspects are described in terms of this example computer system. After reading this description, it will become apparent to a person skilled in the relevant art(s) how to implement aspects of the disclosures using other computer systems and / or architectures.
[0064] The computer system 500 may include a display interface 502 that forwards graphics, text, and other data from the communication infrastructure 506 (or from a frame buffer not shown) for display on a display unit 550. Computer system 500 also includes a main memory 508, preferably random access memory (RAM), and may also include a secondary memory 510. The secondary memory 510 may include, for example, a hard disk drive 512, and / or a removable storage drive 514, representing a floppy disk drive, a magnetic tape drive, an optical disk drive, a universal serial bus (USB) flash drive, etc. The removable storage drive 514 reads from and / or writes to a removable storage unit 518 in a well-known manner. Removable storage unit 518 represents a floppy disk, magnetic tape, optical disk, USB flash drive etc., which is read by and written to by removable storage drive 514. As will be appreciated, the removable storage unit 518 includes a computer usable storage medium having stored therein computer software and / or data. In some examples, one or more of the main memory 508, the secondary memory 510, the removable storage unit 518, and / or the removable storage unit 522 may be a non-transitory memory.
[0065] Alternative aspects of the present disclosures may include secondary memory 510 and may include other similar devices for allowing computer programs or other instructions to be loaded into computer system 500. Such devices may include, for example, a removable storage unit 522 and an interface 520. Examples of such may include a program cartridge and cartridge interface (such as that found in video game devices), a removable memory chip (such as an erasable programmable read only memory (EPROM), or programmable read only memory (PROM)) and associated socket, and other removable storage units 522 and interfaces 520, which allow software and data to be transferred from the removable storage unit 522 to computer system 500.
[0066] Computer system 500 may also include a communications circuit 524. The communications circuit 524 may allow software and data to be transferred between computer system 500 and external devices. Examples of the communications circuit 524 may include a modem, a network interface (such as an Ethernet card), a communications port, a Personal Computer Memory Card International Association (PCMCIA) slot and card, etc. Software and data transferred via the communications circuit 524 are in the form of signals 528, which may be electronic, electromagnetic, optical or other signals capable of being received by the communications circuit 524. These signals 528 are provided to the communications circuit 524 via a communications path (e.g., channel) 526. This path526 carries signals 528 and may be implemented using wire or cable, fiber optics, a telephone line, a cellular link, an RF link and / or other communications channels. In this document, the terms “computer program medium” and “computer usable medium” are used to refer generally to media such as the removable storage unit 518, a hard disk installed in hard disk drive 512, and signals 528. These computer program products provide software to the computer system 500. Aspects of the present disclosures are directed to such computer program products.
[0067] Computer programs (also referred to as computer control logic) are stored in main memory 508 and / or secondary memory 510. Computer programs may also be received via communications circuit 524. Such computer programs, when executed, enable the computer system 500 to perform the features in accordance with aspects of the present disclosures, as discussed herein. In particular, the computer programs, when executed, enable the processor 504 to perform the features in accordance with aspects of the present disclosures. Accordingly, such computer programs represent controllers of the computer system 500.
[0068] In an aspect of the present disclosures where the method is implemented using software, the software may be stored in a computer program product and loaded into computer system 500 using removable storage drive 514, hard drive 512, or communications interface 520. The control logic (software), when executed by the processor 504, causes the processor 504 to perform the functions described herein. In another aspect of the present disclosures, the system is implemented primarily in hardware using, for example, hardware components, such as application specific integrated circuits (ASICs). Implementation of the hardware state machine so as to perform the functions described herein will be apparent to persons skilled in the relevant art(s).
[0069] It will be appreciated that various implementations of the above-disclosed and other features and functions, or alternatives or varieties thereof, may be desirably combined into many other different systems or applications. Also that various presently unforeseen or unanticipated alternatives, modifications, variations, or improvements therein may be subsequently made by those skilled in the art which are also intended to be encompassed by the following claims.
Claims
CLAIMSWHAT IS CLAIMED IS:
1. A method of loss prevention in a store, comprising: receiving, from a first RFID reader disposed at an egress zone, egress event information associated with the first RFID reader receiving a first RFID response signal from an RFID tag appended to a merchandise; receiving, from one or more cameras, one or more images associated with an egress event identified in the egress event information; determining an occurrence of a shrink event associated with the merchandise based on the egress event information and an absence of restricted access area information that indicates the RFID tag has not been scanned by a second RFID reader disposed at a restricted access area; correlating the one or more images with the shrink event; identifying one or more features, one or more objects, or environmental information associated with a person triggering the egress event; and generating a data file of the shrink event, including data identifying at least one of a time of the shrink event, the merchandise, the one or more features of the person, the one or more objects associated with the person, or the environmental information associated with the person.
2. The method of claim 1, wherein the restricted access area includes a transaction terminal in a point of sale area.
3. The method of claim 1, wherein the restricted access area is adjacent to a transactional terminal in a point of sale area.
4. The method of claim 1, wherein correlating the one or more images with the shrink event comprises correlating the one or more images with the shrink event based on a first time of the one or more images and a second time of the shrink event.
5. The method of claim 4, wherein correlating the one or more images with the shrink event comprises correlating the one or more images with the shrink event basedon the first time of the one or more images overlaps with the second time of the shrink event.
6. The method of claim 1, further comprising transmitting the data file of the shrink event to a law enforcement agency.
7. The method of claim 1, wherein identifying the one or more features comprises identifying the one or more features using a neural network.
8. A non-transitory computer readable medium having instructions stored therein, that, when executed by one or more processors of a server, cause the one or more processors to: receive, from a first RFID reader disposed at an egress zone, egress event information associated with the first RFID reader receiving a first RFID response signal from an RFID tag appended to a merchandise; receive, from one or more cameras, one or more images associated with an egress event identified in the egress event information; determine an occurrence of a shrink event associated with the merchandise based on the egress event information and an absence of restricted access area information that indicates the RFID tag has not been scanned by a second RFID reader disposed at an restricted access area; correlate the one or more images with the shrink event; identify one or more features, one or more objects, or environmental information associated with a person triggering the egress event; and generate a data file of the shrink event, including data identifying at least one of a time of the shrink event, the merchandise, the one or more features of the person, the one or more objects associated with the person, or the environmental information associated with the person.
9. The non-transitory computer readable medium of claim 8, wherein the restricted access area includes a transaction terminal in a point of sale area.
10. The non-transitory computer readable medium of claim 8, wherein the restricted access area is adjacent to a transactional terminal in a point of sale area.
11. The non-transitory computer readable medium of claim 8, wherein the instructions for correlating the one or more images with the shrink event comprises instructions for correlating the one or more images with the shrink event based on a first time of the one or more images and a second time of the shrink event.
12. The non-transitory computer readable medium of claim 11, wherein the instructions for correlating the one or more images with the shrink event comprises instructions for correlating the one or more images with the shrink event based on the first time of the one or more images overlaps with the second time of the shrink event.
13. The non-transitory computer readable medium of claim 8, further comprises instructions for transmitting the data file of the shrink event to a law enforcement agency.
14. The non-transitory computer readable medium of claim 8, wherein the instructions for identifying the one or more features comprises instructions for identifying the one or more features using a neural network.
15. A server for loss prevention in a store, comprising: one or more memories storing instructions; and one or more processors communicatively coupled with the one or more memories and configured to: receive, from a first RFID reader disposed at an egress zone, egress event information associated with the first RFID reader receiving a first RFID response signal from an RFID tag appended to a merchandise; receive, from one or more cameras, one or more images associated with an egress event identified in the egress event information; determine an occurrence of a shrink event associated with the merchandise based on the egress event information and an absence of restricted access areainformation that indicates the RFID tag has not been scanned by a second RFID reader disposed at a restricted access area; correlate the one or more images with the shrink event; identify one or more features, one or more objects, or environmental information associated with a person triggering the egress event; and generate a data fde of the shrink event, including data identifying at least one of a time of the shrink event, the merchandise, the one or more features of the person, the one or more objects associated with the person, or the environmental information associated with the person.
16. The server of claim 15, wherein: the restricted access area includes or is adj acent to a transaction terminal in a point of sale area.
17. The server of claim 15, wherein the one or more processors are further configured to correlate the one or more images with the shrink event based on a first time of the one or more images and a second time of the shrink event.
18. The server of claim 17, wherein the one or more processors are further configured to correlate the one or more images with the shrink event based on the first time of the one or more images overlaps with the second time of the shrink event.
19. The server of claim 15, wherein the one or more processors are further configured to transmit the data file of the shrink event to a law enforcement agency.
20. The server of claim 15, wherein the one or more processors are further configured to identify the one or more features using a neural network.
Citation Information
Patent Citations
Systems and methods for retracing shrink events
GB2574507A
Method and system for tracking and behavioral monitoring of multiple objects moving through multiple fields-of-view
US20050265582A1
Object tracking and alerts
US20070182818A1
Loss prevention using video analytics
US20210097544A1
Item tracking system
US20220083752A1