Ultra-wideband-based object recognition

Abstract

The present invention discloses an object recognition method and system based on ultra-wideband. The method includes: using a transmitter to send an ultra-wideband signal to an object; using a receiver to receive a reflected signal from the object; and using a processor to determine the identity of the object based on the received reflected signal.

Description

Technical Field

[0001] The present invention relates to object recognition based on ultra-wideband. Background Art

[0002] Operators in warehouses and factories often need to inspect the contents of boxes or packages to ensure quality or conduct inventory. However, the operator may not be able to see the contents of the box or package.

[0003] One existing solution for performing inspections is through manual inspection, which involves the operator opening the boxes and packages for inspection. This solution can be very inconvenient and cumbersome. Another method for performing inspections is weighing the boxes or packages. When the determined weight is within a predetermined range, the object is identified as normal. This solution is rather crude and susceptible to measurement errors. Another method for performing inspections is irradiating the boxes or packages with X-rays. This solution involves large-scale and expensive operations. In addition, the ionizing radiation provided by X-rays may not be suitable for inspecting certain types of goods. Summary of the Invention

[0004] An object of the present invention is to address the above needs, to overcome or substantially improve the above disadvantages, or more generally, to provide an alternative or improved method of object recognition based on ultra-wideband (and related systems).

[0005] According to a first aspect of the present invention, there is provided a method of object recognition based on ultra-wideband, comprising: transmitting an ultra-wideband signal to an object using a transmitter; receiving a reflected signal from the object using a receiver; and determining the identity of the object using a processor based on the received reflected signal.

[0006] Preferably, determining the identity of the object based on the received reflected signal includes determining the presence or absence of the object based on the received reflected signal.

[0007] Preferably, determining the identity of the object includes: comparing the received reflected signal with one or more predetermined signals associated with known object identities; and determining based on the comparison whether the identity of the object is an object identity associated with any of the one or more predetermined signals.

[0008] Preferably, determining whether the identity of the object is an object identity associated with any of the one or more predetermined signals includes: if the received reflected signal matches one of the predetermined signals, determining that the identity of the object is an object identity associated with one of the predetermined signals.

[0009] Preferably, determining whether the identity of an object is an object identity associated with any one of one or more predetermined signals includes: determining that the identity of the object is an object identity associated with one of the predetermined signals based on the best match of the received reflected signal with the one or more predetermined signals.

[0010] Preferably, when the difference between the received reflected signal and one of the predetermined signals is less than a difference threshold, the received reflected signal matches one of the predetermined signals. The difference threshold can be adjustable (e.g., during operation) or can be fixed.

[0011] In an embodiment of the first aspect, the method further includes determining a matching index based on the degree of match of the received reflected signal with the one or more predetermined signals.

[0012] Preferably, the method may further include displaying on a display one or more of the following: the matching index, an indication of the determined object identity, etc.

[0013] In an embodiment of the first aspect, the method further includes recording the determined identity of the object and incrementing a count associated with the identified object identity by one.

[0014] In an embodiment of the first aspect, the method further includes providing an alert when the received reflected signal does not match any of the predetermined signals.

[0015] Preferably, the transmitter and the receiver are arranged in a transceiver unit.

[0016] Preferably, the object is arranged in a container such that the object is not visible.

[0017] According to a second aspect of the present invention, there is provided an ultra-wideband based object identification system, comprising: a transmitter for transmitting an ultra-wideband signal to an object; a receiver for receiving a reflected signal from the object; and a processor for determining the identity of the object based on the received reflected signal.

[0018] Preferably, the processor is arranged to determine the presence or absence of the object based on the received reflected signal.

[0019] Preferably, the processor is arranged to determine the identity of the object by comparing the received reflected signal with one or more predetermined signals associated with known object identities; and to determine whether the identity of the object is an object identity associated with any one of the one or more predetermined signals based on the comparison.

[0020] Preferably, the processor is arranged to determine whether the identity of the object is an object identity associated with any one of one or more predetermined signals by determining that the identity of the object is an object identity associated with one of the predetermined signals if the received reflected signal matches one of the predetermined signals.

[0021] Preferably, the processor is arranged to determine whether the identity of the object is an object identity associated with any one of one or more predetermined signals by determining, based on the best match of the received reflected signal with one or more predetermined signals, that the identity of the object is an object identity associated with one of the predetermined signals.

[0022] Preferably, when the processor determines that the difference between the received reflected signal and one of the predetermined signals is less than a difference threshold, the received reflected signal matches one of the predetermined signals. The difference threshold may be adjustable (e.g., during operation) or may be fixed.

[0023] In an embodiment of the second aspect, the processor is further arranged to determine a matching index based on the degree of match of the received reflected signal with one or more predetermined signals.

[0024] In an embodiment of the second aspect, the system further includes a display operably connected to the processor for displaying one or more of the following: the matching index, an indication of the determined identity of the object, etc.

[0025] Preferably, the processor is further arranged to record the determined identity of the object and increment a count associated with the identified object identity by one.

[0026] Preferably, the transmitter and the receiver are arranged in a transceiver unit.

[0027] Preferably, the object is arranged in a container such that the object is not visible.

[0028] Preferably, the system is integrated in a stand-alone object identification device. More preferably, the object identification device is portable. Description of the Drawings

[0029] Embodiments of the present invention will now be described by way of example with reference to the accompanying drawings, in which:

[0030] Figure 1 is an ultra-wideband-based object identification device in an embodiment of the present invention;

[0031] Figure 2 is a block diagram of an ultra-wideband-based object identification system in an embodiment of the present invention;

[0032] Figure 3 is a transmitter and receiver device of an ultra-wideband-based object identification device in an embodiment of the present invention;

[0033] Figure 4 are the transmitter and receiver devices of the ultra-wideband-based object recognition device in another embodiment of the present invention;

[0034] Figure 5 is a flowchart of the ultra-wideband-based object recognition method in an embodiment of the present invention;

[0035] Figure 6 is in an embodiment of the present invention Figure 5 flowchart of the determination step of;

[0036] Figure 7 is in an embodiment of the present invention Figure 5 flowchart of the determination step of;

[0037] Figure 8A is a graph showing an exemplary reflected received signal from an object;

[0038] Figure 8B is shown in an embodiment of the present invention Figure 5 graph of the output of the ultra-wideband-based object recognition method of; and

[0039] Figure 9 is an ultra-wideband-based object recognition system in an embodiment of the present invention. Detailed implementation mode

[0040] Figure 1 shows an ultra-wideband (UWB)-based object recognition device 100 in an embodiment of the present invention. The device 100 includes a main body 104 and a handle 102 coupled to the main body 104. A user can hold the handle 102 and use the device 100 as a portable device. A UWB transceiver 101 is mounted on the main body 104 for sending signals to an object 10 to be measured and receiving signals reflected from the object 10. In this embodiment, the object 10 is arranged in a box (or package) 12 that hides the object 10.

[0041] Figure 2It is a block diagram of the main components of an ultra-wideband-based object recognition system 200 in an embodiment of the present invention. The system 200 can have different configurations, and it can be implemented in a single device or distributedly implemented in multiple operably connected devices. The system 200 generally includes appropriate components necessary for receiving, storing, and executing appropriate computer instructions, commands, or code. In this embodiment, the main components of the system 200 include a UWB transceiver 201 having a transmitter 201T and a receiver 201R. The transmitter 201T and the receiver 201R can be the same component, or they can be different components. The system 200 also includes a processor 202 and a memory 204. The processor 202 can be formed by one or more CPUs, MCUs, controllers, logic circuits, Raspberry Pi chips, etc. The memory 204 can include one or more volatile memory units (such as random access memory, dynamic random access memory, static random access memory), one or more non-volatile memory units (such as read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, ferroelectric memory, magnetoresistive memory, flash memory, solid-state drive, NAND flash memory, and non-volatile dual in-line memory module), or any combination thereof. The system 200 also includes one or more input devices 206, such as a keyboard, mouse, stylus, image scanner, microphone, tactile input device (such as a touch-sensitive screen), and image / video input device (such as a camera). The system 200 can also include one or more output devices 208, such as one or more displays (such as a monitor), speakers, disk drives, headphones, earphones, printers, 3D printers, etc. The display can include an LCD display, an LED / OLED display, or any other suitable display that may or may not be touch-sensitive. The system 200 can also include one or more disk drives 212, which can include solid-state drives, hard disk drives, optical disk drives, flash drives, and / or tape drives. A suitable operating system can be installed in the system 200, such as installed on the disk drive 212 or in the memory 204. The memory 204 and the disk drive 212 can be operated by the processor 202. The system 200 also includes a communication module 210, which is used to establish one or more communication links (not shown) with one or more other computing devices (such as servers, personal computers, terminals, tablets, phones, or other wireless or handheld computing devices). The communication module 210 can be a modem, a network interface card (NIC), an integrated network interface, a radio frequency transceiver, an optical port, an infrared port, a USB connection, or other wired or wireless communication interfaces. The communication link can be wired or wireless for transmitting commands, instructions, information, and / or data.The transceiver 201, processor 202, memory 204, input device 206, output device 208, communication module 210, and disk drive 212 are interconnected via a bus, a Peripheral Component Interconnect (PCI) (e.g., a serial bus), a Universal Serial Bus (USB), an optical bus, or other similar data and / or power buses. Although not shown, the system may be powered by a DC power source (e.g., a battery cell, a battery pack) or an AC power source (e.g., having a power cord and plug for connection to an AC power outlet). The system may also be connected to one or more external data memories or servers via the communication module 210.

[0042] Those skilled in the art will understand that Figure 2 the system 200 shown in Figure 1 is merely exemplary. The device 100 in

[0043] Figure 3 and Figure 4 are exemplary UWB transmitter and receiver devices of the present invention. In Figure 3 , the UWB transceiver 301 includes nine transmitter and receiver units 301T / R, arranged in a 3-row and 3-column array, and each can operate as both a transmitter and a receiver. In Figure 4 , the UWB transceiver 401 includes four transmitters 401T and four receivers 401R arranged in a Mills cross array, where one horizontal row includes four transmitters 401T and one vertical column includes four receivers 401R. Figure 3 and Figure 4 These UWB transmitter and receiver devices in Figure 1 can be included in the device 100 of Figure 2 and the system 200 of

[0044] Figure 5 FIG. shows a UWB-based object recognition method 500 in an embodiment of the present invention. For simplicity, method 500 is described with reference to only one transmitter and one receiver. However, it should be noted that method 500 can be well applied to embodiments having multiple transmitters and receivers.

[0045] Method 500 begins at step 502, where an ultra-wideband signal is transmitted to an object using a transmitter such as device 100 or system 200. Then, at step 504, a reflected signal (e.g., a waveform) from the object is received at a receiver such as device 100 or system 200. At step 506, a processor such as in device 100 or system 200 determines the identity of the object based on the received signal. Determining the identity of the object may include determining the presence or absence of the object based on the received reflected signal. Method 500 may also include recording the determined identity of the object and incrementing a count associated with the identified object identity using a processor such as in device 100 or system 200.

[0046] Details of determining step 506 will be further described below with reference to Figure 6 and Figure 7 Figure 7.

[0047] Figure 6 An implementation 600 of determination step 500 of Figure 5 Figure 7 is shown. For simplicity, method 600 is described with reference to only one transmitter and one receiver. However, it should be noted that method 600 can be well applied to embodiments with multiple transmitters and receivers.

[0048] Method 600 begins at step 602, where the received reflected signal (from the object) is compared with a predetermined signal associated with a known object identity. The predetermined signal is determined and stored in a memory such as in device 100 or system 200 prior to operation. The comparison in step 602 can be performed by a processor of device 100 or system 200. Then, at step 604, it is determined whether the difference between the received reflected signal and the predetermined signal is less than a threshold. This determination step can be performed by a processor of device 100 or system 200. The threshold can be fixed or adjustable. Step 604 can be considered as determining a match between the received reflected signal and the predetermined signal, or determining the degree of match between the received reflected signal and the predetermined signal.

[0049] If it is determined that the difference is less than the threshold, then at step 606, the identity of the object is determined to be the known object identity associated with the predetermined signal. This determination step can be performed by a processor of device 100 or system 200. Subsequently, at step 608, the count of the identified object identity is incremented, for example, by a processor and a memory of device 100 or system 200. Preferably, device 100 or system 200 maintains the count of the identified object identity for recording.

[0050] Alternatively, if it is determined that the difference is not less than the threshold, then in step 610, it is determined that the identity of the object is not the known object identity associated with the predetermined signal. Subsequently, in step 612, an alert is provided via an input / output device such as device 100 or system 200.

[0051] In some embodiments, method 600 may further include displaying a matching index at a display of device 100 or system 200, the matching index indicating the degree of match of the received reflected signal with the predetermined signal, or an indication of the determined object identity, or both.

[0052] Figure 7 Shows Figure 5 One implementation 700 of determination step 500 is shown. For simplicity, method 700 is described with reference to only one transmitter and one receiver. However, it should be noted that method 700 can be well applied to embodiments having multiple transmitters and receivers.

[0053] Method 700 begins at step 702, where the received reflected signal (from the object) is compared with a plurality of predetermined signals, each predetermined signal being associated with a known object identity. The predetermined signals are determined and stored in a memory of, for example, device 100 or system 200 prior to operation. The comparison in step 702 can be performed by a processor of device 100 or system 200. Then, in step 704, it is determined by a processor of, for example, device 100 or system 200 which of the predetermined signals has a difference from the received reflected signal that is less than the corresponding threshold.

[0054] If it is determined that at least one predetermined signal differs from the received reflected signal by less than the corresponding threshold, the method proceeds to step 706, where it is determined by a processor of, for example, device 100 or system 200 which of the predetermined signals best matches the corresponding threshold with respect to the received reflected signal. The best match can be the predetermined signal having the smallest difference from the corresponding threshold. Once the best match is determined, then in step 708, the identity of the object is determined to be the known object identity associated with the best-matching predetermined signal. And, in step 710, the count of the corresponding identified object identity is incremented by a processor and memory of, for example, device 100 or system 200. Preferably, device 100 or system 200 maintains counts of different object identities associated with the predetermined signals for recording.

[0055] Alternatively, if it is determined in step 704 that none of the predetermined signals differ from the received reflected signal by less than the corresponding threshold, the method proceeds to step 712, where an alert is provided via an input / output device such as device 100 or system 200.

[0056] In some embodiments, method 700 may further include displaying a matching index at a display of device 100 or system 200, the matching index indicating the degree of match of the received reflected signal with a predetermined signal, or an indication of the determined object identity, or both.

[0057] Figure 8A An exemplary reflected received signal from an object is shown, which may be received, for example, by system 200 or device 100 in the above embodiments.

[0058] Figure 8B is in an embodiment of the present invention Figure 5 The output display of the ultra-wideband based object recognition method. The display includes grids of different colors, which represent the matching index between the received signal and the predetermined signal. The middle number "1" represents the determined object identity.

[0059] Figure 9 is an ultra-wideband based object recognition system 900 in an embodiment of the present invention. System 900 has the same or similar structure as Figure 2 system 200 and Figure 1 device 100. System 900 generally includes a UWB transceiver 901 operably connected to an information processing system 950. The UWB transceiver 901 is arranged beside conveyor belt 40 to scan or test the passing object 10. The UWB transceiver 901 is operably connected to the information processing system 950. The information processing system 950 includes a processor, a memory, an input / output device, a disk drive, a communication module, etc., such as Figure 2 those in system 200. Figure 9 The information processing system 950 of is operably connected to a remote server 20 for storing and retrieving information and data (e.g., data measured or recorded by system 900). In this embodiment, if system 900 does not determine a match, the conveyor system may take a responsive action. For example, object 10 may be removed from conveyor belt 40, or may be separated from objects that can be identified or classified. In some embodiments, the conveyor system may separate the objects that have passed through system 900 according to the identified object classification (e.g., by guiding them to different stations).

[0060] Although not necessary, the embodiments described with reference to the accompanying drawings may be implemented as an application programming interface (API) or a series of libraries used by developers, or may be included in another software application, such as a terminal or a personal computer. Generally, since program modules include routines, programs, objects, components, and data files that assist in performing specific functions, those skilled in the art will understand that the functions of a software application may be distributed over multiple routines, objects, or components to achieve the same functions required herein.

[0061] It should also be understood that, in cases where the methods and systems of the present invention are fully or partially implemented by a computing system, any suitable computing system architecture may be used. This will include stand-alone computers, network computers, and dedicated or non-dedicated hardware devices. In cases where the terms "computing system" and "computing device" are used, these terms are intended to include any suitable apparatus of a computer or information processing hardware capable of implementing the described functions.

[0062] Those skilled in the art will understand that many variations and / or modifications can be made to the present invention as shown in the specific embodiments without departing from the spirit or scope of the present invention as broadly described. For example, the ultra-wideband-based object identification devices, systems, and methods of the present invention can be applied to testing: objects arranged in boxes or packages that conceal the objects, objects not arranged in any boxes or packages, and objects arranged in boxes or packages where the boxes or packages only allow partial visibility of the objects. The ultra-wideband-based object identification devices, systems, and methods can be implemented on a stand-alone device (e.g., Figure 1 embodiments), or implemented distributively on multiple devices (e.g., Figure 9 embodiments). The UWB transceivers can take different forms, orientations, quantities, shapes, and sizes. The number of transmitters and receivers can be selected according to the application (e.g., the required resolution). The display of the matching index and the indication of the determined object identity can take different forms. The features in different embodiments can be selectively regrouped to provide new embodiments. For example, the methods in the above embodiments can be applied to system 200, device 100, or system 900 in a similar manner. The method embodiments can be fully implemented in system 200, device 100, or system 900. Or, they can be selectively implemented in system 200, device 100, or system 900. In embodiments having multiple transmitter and receiver elements, the method can also be arranged to utilize the analysis of the received reflected signals (e.g., waveforms) with the most information. Dynamic analysis of multiple received reflected signals received at the same receiver can be performed to reduce analysis and measurement errors. In Figure 9 embodiments, the information processing system can be a desktop computer, a smart phone, a tablet computer, a laptop computer, etc.

[0063] Accordingly, the described embodiments of the present invention should be considered in all respects to be illustrative and not restrictive.

Claims

1. An ultra-wideband-based object identification method for merchandise inspection, comprising: Transmitting ultra-wideband signals to an object passing on a conveyor belt using a plurality of transmitters; Receiving reflected signals from the object using a plurality of receivers; And Determining the identity of the object based on the received reflected signals using a processor, wherein the determination includes: Comparing the received reflected signals with one or more predetermined signals related to known object identities to create a comparison; and Based on the comparison, determining whether the identity of the object is an object identity associated with any one of the one or more predetermined signals, wherein determining whether the identity of the object is an object identity associated with any one of the one or more predetermined signals includes: if the received reflected signal matches one of the one or more predetermined signals, determining that the identity of the object is an object identity associated with the one of the one or more predetermined signals; Determining the degree of match between the received reflected signals and the one or more predetermined signals; Using the processor to determine a match index based on the degree of match between the received reflected signals and the corresponding one or more predetermined signals; On a display operably connected to the processor, displaying the match index indicating the degree of match and an indication of the determined identity of the object, wherein the match index is represented by grids of different colors; and Classifying the object based on the determined identity of the object by guiding the object to a station related to the determined identity or removing the object from the conveyor belt when the received reflected signal of the object is not associated with any of the one or more predetermined signals, Wherein the plurality of transmitters and the plurality of receivers are arranged in a Mills cross array, which has a horizontal row of transmitters and a vertical column of receivers.

2. The ultra-wideband-based object recognition method according to claim 1, wherein, Determining the identity of the object based on the received reflected signals includes: Determining the presence or absence of the object based on the received reflected signals.

3. The ultra-wideband-based object recognition method according to claim 1, wherein, Determining whether the identity of the object is an object identity associated with any one of the one or more predetermined signals includes: Based on the best match between the received reflected signals and the one or more predetermined signals, determining that the identity of the object is an object identity associated with one of the predetermined signals.

4. The ultra-wideband-based object recognition method according to claim 1, wherein, When the difference between the received reflected signal and the one of the predetermined signals is less than a difference threshold, the received reflected signal matches the one of the predetermined signals.

5. The ultra-wideband-based object recognition method according to claim 4, wherein, The difference threshold is adjustable.

6. The method for identifying an object based on ultra-wideband according to claim 4, wherein, The difference threshold is fixed.

7. The ultra-wideband-based object identification method according to any one of claims 1 to 6, further comprising recording the determined identity of the object and incrementing a count associated with the identified object identity.

8. The ultra-wideband-based object identification method according to any one of claims 1 to 6, further comprising providing an alarm when the received reflected signal does not match all of the predetermined signals.

9. The ultra-wideband-based object recognition method according to any one of claims 1 to 6, wherein, The plurality of transmitters and the plurality of receivers are arranged in a transceiver unit.

10. The ultra-wideband-based object recognition method according to any one of claims 1 to 6, wherein, The object is arranged in a container such that the object is not visible.

11. A UWB-based object identification system for merchandise inspection, comprising: a plurality of transmitters for transmitting UWB signals to an object passing on a conveyor belt; a plurality of receivers for receiving reflected signals from the object; and a processor for determining the identity of the object based on the received reflected signals; and a display, the display being operably connected to the processor; wherein the processor is arranged to: compare the received reflected signals with one or more predetermined signals associated with known object identities to create a comparison; and based on the comparison, determine whether the identity of the object is an object identity associated with any of the one or more predetermined signals; if the received reflected signal matches one of the one or more predetermined signals, determine that the identity of the object is the object identity associated with the one of the one or more predetermined signals; determine a matching index based on the degree of match between the received reflected signal and the corresponding one or more predetermined signals; wherein the display is arranged to display the matching index indicating the degree of match and an indication of the determined identity of the object through a grid of different colors; wherein the plurality of transmitters and the plurality of receivers are arranged in a MIMO array having a horizontal row of transmitters and a vertical column of receivers; wherein the object is classified based on the determined identity of the object by guiding the object by the conveyor belt to a station associated with the determined identity or removing the object from the conveyor belt when the received reflected signal of the object is not associated with any of the one or more predetermined signals.

12. The ultra-wideband-based object recognition system according to claim 11, wherein, The processor is arranged to determine the presence or absence of the object based on the received reflected signals.

13. The ultra-wideband-based object recognition system according to claim 11, wherein, The processor is arranged to determine whether the identity of the object is an object identity associated with any of the one or more predetermined signals by: based on the best match between the received reflected signal and the one or more predetermined signals, determine that the identity of the object is the object identity associated with one of the predetermined signals.

14. The ultra-wideband-based object recognition system according to claim 11, wherein, When the processor determines that the difference between the received reflected signal and one of the predetermined signals is less than a difference threshold, the received reflected signal matches the one of the predetermined signals.

15. The ultra-wideband-based object recognition system according to claim 14, wherein, The difference threshold is adjustable.

16. The ultra-wideband-based object recognition system according to claim 14, wherein, The difference threshold is fixed.

17. The ultra-wideband-based object recognition system according to any one of claims 11 to 16, wherein, The processor is further arranged to record the determined identity of the object and increment a count associated with the identified object identity.

18. The ultra-wideband-based object recognition system according to any one of claims 11 to 16, wherein, The plurality of transmitters and the plurality of receivers are arranged in a transceiver unit.

19. The ultra-wideband-based object recognition system according to any one of claims 11 to 16, wherein, The object is arranged in a container such that the object is not visible.

20. The ultra-wideband-based object recognition system according to any one of claims 11 to 16, wherein, The system is integrated in a portable object identification device.

Images