Pest detection system and method

Abstract

The subject matter of the present invention relates to a pest detection system that employs infrared emitters and detectors to look for changes in incident light indicative of wing flutter of various pests. The emitters and detectors are placed on one or more printed circuit boards such that infrared light projected from the emitters can be received by one or more detectors. Based on the signals generated by the detectors, the system of the subject matter of the present invention can determine whether a pest is flying between the emitters and detectors. To conserve power, the emitters, the detectors, or both can be driven by pulse width modulation. The method of the subject matter of the present invention involves determining the presence of a pest by signal filtering and interpretation.

Description

Technical Field

[0001] The field of this invention is light-based pest detection systems and methods. Background Technology

[0002] The background description includes information that may help in understanding the invention. This does not imply an admission that any information provided in this application is prior art or related to the invention, nor does it imply that any publication specifically or implicitly referenced is prior art.

[0003] Agriculture is one of the oldest and most important industries in human history. Throughout human history, there has been a continuous effort to reduce the impact of pests and diseases in order to improve the health and nutritional content of food and increase crop yields. Pest detection is crucial for improving crop yields. Pests are often the biggest threat to successful crop production, and depending on the crop type and growth stage, some estimates suggest that early pest detection can reduce yield losses by as much as 20-40%.

[0004] In the past, pest detection required farmers to walk through the fields to visually inspect for pests damaging crops. However, with industrialization, farmland has increased to the point that walking around the farm is impractical. In fact, even driving around the farm is impractical, as it would require farmers to spend too much time on such a tedious task. Therefore, efforts have been made to develop automated pest detection systems.

[0005] In some efforts, visual inspection systems have been developed. However, these systems are not perfect. Visual inspection systems use cameras to periodically take photos or record videos, for example, of pests attracted to traps. However, many of these systems still require human operators to view the images and perform pest detection, requiring human users to, for example, calculate the number of pests captured in the traps. Acoustic pest detection has also been implemented, where electromechanical listening devices are used to determine when pests exceed a certain threshold by listening to increases in noise levels associated with various pests.

[0006] However, these systems have shortcomings in terms of power consumption, accuracy, and the need for manual inspection. Therefore, it has not yet been realized that infrared light can be used to detect pests through systems designed to automatically detect wingbeat frequencies associated with flying insects. Summary of the Invention

[0007] This invention provides devices, systems, and methods for pest detection using infrared light. In one aspect of the subject matter, a pest detection system includes: a first printed circuit board (PCB) portion and a second PCB portion, wherein a space exists between the first PCB portion and the second PCB portion; at least one transmitter disposed on the first PCB portion; at least one detector disposed on the second PCB portion, wherein the at least one transmitter is oriented toward the at least one detector, and wherein the at least one detector is oriented toward the at least one transmitter; and a pulse width modulation controller configured to drive at least one of the at least one transmitter and at least one detector.

[0008] In some embodiments, the first PCB portion and the second PCB portion are part of a single PCB. In some embodiments, the single PCB is V-shaped, having a first arm and a second arm, wherein the first arm includes the first PCB portion and the second arm includes the second PCB portion. The single PCB is ring-shaped, having a first side and a second side, wherein the first side includes the first PCB portion and the second side includes the second PCB portion. In some embodiments, the pulse width modulation controller operates at a duty cycle of 10% to 90% and a frequency greater than 240 Hz. At least one detector may include a photodiode, and at least one emitter may be configured to project infrared light (e.g., wavelengths of 700 nm to 1400 nm). In some embodiments, at least one detector is configured to detect infrared light (e.g., wavelengths of 700 nm to 1400 nm).

[0009] In another aspect of the subject matter of the invention, a pest detection system includes: a first printed circuit board (PCB) portion and a second PCB portion, wherein a space exists between the first PCB portion and the second PCB portion; a wide-angle transmitter disposed on the first PCB portion; a set of detectors disposed on the second PCB portion, wherein the wide-angle transmitter is oriented toward the set of detectors, and wherein each of the set of detectors is oriented toward the wide-angle transmitter; and a pulse width modulation controller configured to drive the wide-angle transmitter and the detectors.

[0010] In some implementations, the first and second PCB sections are part of a single PCB, and the pulse width modulation controller can be configured to operate with a duty cycle of 10% to 90% and a frequency greater than 240 Hz. Each detector in the group can be a photodiode, and the wide-angle emitter can be configured to project infrared light (e.g., wavelengths of 700 nm to 1400 nm). Similarly, each detector in the group can be configured to detect infrared light (e.g., wavelengths of 700 nm to 1400 nm).

[0011] It should be understood that the disclosed subject matter offers many advantageous technical effects, including the ability to detect the presence of pests while eliminating false alarms and achieving higher accuracy than existing systems.

[0012] Various objects, features, aspects and advantages of the subject matter of the invention will become more apparent from the following detailed description of preferred embodiments and the accompanying drawings, in which similar numbers denote similar components. Attached Figure Description

[0013] Figure 1 A ring-shaped pest detection system is shown.

[0014] Figure 2 A ring-shaped pest detection system set inside a fly trap is shown.

[0015] Figure 3 A cross-sectional view of a fly trap is shown.

[0016] Figure 4 A V-shaped pest detection system is shown.

[0017] Figure 5 The housing of the V-shaped pest detection system is shown.

[0018] Figure 6 The components of the housing are shown.

[0019] Figure 7 A reflective pest detection system is shown.

[0020] Figure 8 A perspective view of a portion of a reflective pest detection system is shown.

[0021] Figure 9 A wide-angle transmitter is shown.

[0022] Figure 10 A pest detection system implementing a wide-angle emitter is shown.

[0023] Figure 11 The relative radiation intensity of the wide-angle emitter at different angles is shown.

[0024] Figure 12 This is a flowchart of how pests can be detected.

[0025] Figure 13 An example signal with a threshold for the amplitude of the detected signal is shown.

[0026] Figure 14 A schematic diagram of an onboard signal classifier is shown.

[0027] Figure 15 It shows how signal waveforms can be measured.

[0028] Figure 16 An example signal with several measurements is shown.

[0029] Figure 17 A schematic diagram illustrating how pests can be detected using the system of the subject of this invention is shown. Detailed Implementation

[0030] The following discussion provides example embodiments of the subject matter of this invention. While each embodiment represents a single combination of elements of the invention, the subject matter of the invention is considered to include all possible combinations of the disclosed elements. Therefore, if one embodiment includes elements A, B, and C, and a second embodiment includes elements B and D, then the subject matter of the invention is considered to include other remaining combinations of A, B, C, or D, even if not explicitly disclosed.

[0031] As stated in the specification of this application and the following claims, unless the context clearly specifies otherwise, the meanings of “a” and “the” include the plural. Furthermore, as stated in the specification of this application, unless the context clearly specifies otherwise, the meaning of “in” includes both “in” and “on”.

[0032] Furthermore, as stated in this application, unless the context otherwise requires, the term "connection" includes a direct connection (where two connected elements are in contact with each other) and an indirect connection (where at least one other element is located between the two elements). Therefore, the terms "connection" and "connected to" are synonyms.

[0033] In some embodiments, the figures used to describe and claim certain embodiments of the invention representing the quantity and properties of components (e.g., concentration, reaction conditions, etc.) should be understood to be modified by the term "about" in certain circumstances. Therefore, in some embodiments, the numerical parameters set forth in the specification and appended claims are approximate values ​​and may vary depending on the desired properties sought to be obtained in a particular embodiment. In some embodiments, numerical parameters should be interpreted based on the number of significant figures reported and by applying common rounding techniques. Although the numerical ranges and parameters illustrating a broad range of some embodiments of the invention are approximate values, the values ​​set forth in the specific examples are reported as precisely as possible. The numerical values ​​given in some embodiments of the invention may contain certain errors that are necessarily caused by the standard deviation found in their respective test measurements. Furthermore, unless the context otherwise requires, all ranges set forth herein should be interpreted to include their endpoints, and open ranges should be interpreted to include only commercially useful values. Similarly, unless the context otherwise requires, all lists of numerical values ​​should be considered to include intermediate values.

[0034] It should be noted that any language relating to computers should be understood to include any suitable combination of computing devices, including servers, interfaces, systems, databases, agents, peers, engines, controllers, or other types of computing devices operating individually or in combination. It should be understood that computing devices include processors configured to execute software instructions stored on tangible, non-transient computer-readable storage media (e.g., hard disk drives, solid-state drives, RAM, flash memory, ROM, etc.). The software instructions preferably configure the computing device to provide roles, responsibilities, or other functions, as discussed below with respect to the disclosed apparatus. In particularly preferred embodiments, various servers, systems, databases, or interfaces exchange data using standardized protocols or algorithms that may be based on HTTP, HTTPS, AES, public-key-private-key exchange, web service APIs, known financial transaction protocols, or other electronic information exchange methods. Data exchange is preferably performed via packet-switched networks, the Internet, LANs, WANs, VPNs, or other types of packet-switched networks. The following description includes information that may aid in understanding the invention. This does not imply an admission that any information provided in this application is prior art or related to the invention, nor does it imply that any publication specifically or implicitly referenced is prior art.

[0035] Embodiments of the subject matter of this invention generally relate to pest detection via the emission and detection of electromagnetic radiation. As an insect (e.g., a fly) passes between a transmitter and a corresponding detector, the fly's wingbeats are detected, allowing the system of the subject matter of this invention to determine the wingbeat frequency. Therefore, each system includes at least one transmitter / detector pair (although different transmitter-to-detector ratios are also considered and described below). For the detector, a photodiode is used instead of a phototransistor for several reasons. For embodiments of the subject matter of this invention, the photodiode provides an improved linear response, resulting in a more stable system than one built using a phototransistor, and consumes less power compared to a phototransistor. Therefore, the photodiode is more sensitive to incident light, has a better linear response over a wider light range, and can handle less current compared to a phototransistor. For these reasons, embodiments of the subject matter of this invention implement a photodiode instead of a phototransistor (although it is still contemplated that a poorer system could be built using a phototransistor). To further save power, pulse width modulation can be implemented on the transmitter and detector to make them turn on synchronously.

[0036] For the reasons mentioned above, photodiodes are more accurate than phototransistors in detecting pests of all sizes. Because phototransistors have a slower response time, they are not suitable for detecting small insects, for example, those with wingbeat frequencies exceeding 700 Hz.

[0037] The emitter used in embodiments of the subject matter of this invention comprises an LED configured to emit infrared light. The considered infrared wavelength range is 700 nm–1400 nm. In a preferred embodiment, infrared light of approximately 940 nm is emitted, thus the spectral response range of the photodiode used as a detector can be 840 nm–1100 nm. The spectral response range of the photodiode of the subject matter of this invention can be matched to the spectral response range of any emitter used, and therefore the range can also include 700 nm–1400 nm. Some advantages of implementing infrared light emission include that infrared emitters consume less power than, for example, laser emitters, and that visible light causes unwanted changes in pest behavior. Furthermore, visible light attracts unwanted pests. Additionally, visible light systems are susceptible to solar radiation, which generates noise and hinders normal system operation.

[0038] Embodiments of the subject matter of this invention can be arranged in various different ways. For example, Figure 1 A ring configuration of the pest detection system 100 is shown. A set of transmitters 102 is positioned on one side opposite a set of detectors 104, both mounted on the same printed circuit board (PCB) 106. Although Figure 1 The invention is shown on a single PCB, but it is conceivable that PCB 106 may be divided into multiple sections without departing from the subject matter of the invention. Emitters on one side are configured to project infrared light onto detectors, such that signals generated by one or more detectors can be interpreted by a microprocessor to determine whether a pest has been detected. The infrared light projection is based on a two-dimensional representation of the light propagating from each emitter, as shown below. Figure 1 As shown. This visualization is for demonstration purposes only, as infrared light is invisible to humans.

[0039] A ring configuration can be used in implementations such as fruit fly detection, where the pest detection system 100 can be placed within, for example, a funnel-based fly trap. The pest detection system 100 has four transmitters and five detectors, although it can be as few as one transmitter and one detector. There is no upper limit to the number of transmitters or detectors, although design and functional considerations may result in a number between 1 and 20 (e.g., depending on ring diameter, desired sensitivity, etc.). Positioning the transmitters closer to the detectors, as well as a higher density of transmitters and detectors, can improve sensitivity, which is important for some pests such as small insects. Sensitivity can be improved by minimizing existing blind spots (e.g., blind spots where pests can pass between the transmitters and detectors but not through the emitter cone of one of the transmitters). Signal integrity remains high because the transmitters and detectors are physically closer (e.g., 3-10 cm, preferably about 4.5 cm) (e.g., signal strength drops more at longer distances compared to shorter distances). Gain and filter adjustments can be made from the default design to be more sensitive to smaller insect sizes and higher frequencies. Furthermore, the transmitter current can be reduced because the transmitters are closer to the detectors.

[0040] For example, filtering can be performed in the frequency domain by adding a bandpass filter. A bandpass filter has a lower limit and an upper limit. The lower limit can range from 50 to 300 Hz, and the upper limit can range from 1000 to 2000 Hz. In a preferred embodiment, the lower limit is approximately 120 Hz, and the upper limit is approximately 1500 Hz (each limit + / - 10%). The wing vibrations of smaller insects are typically within this range. Other filtering in the time domain can be used to eliminate additional noise.

[0041] There is a correlation between gain and current, where light emission from the emitter is a function of current. Higher gain amplifies noise but can also improve the performance of systems with low current driving one or more emitters (e.g., producing less light). On the other hand, increasing the emitter current to produce more infrared light can reduce sensitivity for smaller insects due to excessive infrared emission. The system of the subject of this invention is configured to measure the relative change in light intensity received at one or more detectors as a pest passes between a detector and an emitter. If too much light is emitted, the detector saturates, making it unable to detect small changes. Therefore, the gain and current of a given system depend on a variety of factors, including pest size, distance between the emitter and detector, detector saturation level, etc.

[0042] like Figure 2 As shown, the pest detection system 100 is positioned around the entrance 202 of the trap 200 where pests (e.g., flies) enter. The pests enter the bottom of the trap and cross the entrance as they enter the trap. Figure 3 yes Figure 2The diagram shows a side sectional view of the trap 200. The sectional view reveals that the trap 200 has been modified to include a landing point 204 for, for example, flies to land on. A problem with this type of trap configuration is that sometimes pests walk past rather than fly over the entrance 202 to enter the trap 200, and because the system of the subject of this invention relies on wingbeats to determine the presence of pests, if a pest walks, it will not be counted. The landing point 204 improves counting accuracy by providing a place for pests such as flies to land just outside the entrance 202, making it more likely that pests will fly past rather than walk over the entrance.

[0043] In another embodiment, the pest detection system may include a PCB configured in a V-shape. Figure 4 A pest detection system 400 with a PCB configured at right angles is shown, but other angles ranging from 10° to 170° can be implemented without departing from the subject matter of the invention. The right-angle configuration provides a balance that allows the transmitter 402 to pair with the detector 404 in a manner that minimizes blind spots. Figure 4 As shown, each side of the V-shaped PCB includes a transmitter-detector-detector pattern. Each transmitter corresponds to two adjacent detectors on the opposite side of the V. The transmitters can be configured to project infrared light according to, for example, a cone or a portion of a cone. Because each transmitter emits outward-projected infrared light that propagates away from its source, each transmitter is paired with two detectors. The number of detectors paired with each transmitter can vary depending on the diffusion angle associated with the transmitter (e.g., the apex angle of the transmitter's emitted light cone) and the distance between the transmitter and the detectors. Each of the two detectors paired with a single transmitter is configured to primarily receive or only receive infrared light from that transmitter. In some embodiments, more than two (e.g., up to 10 or more) detectors are paired with a single transmitter. While there is no theoretical limit to the number of detectors per transmitter, practical limitations may arise due to factors such as transmitter distribution and distance from the transmitter; for example, the transmitter may not project enough light to reach the detector with sufficient intensity, or the detector may be located outside the transmitter's projected light area. As mentioned above, the intensity of the infrared light received at the detector affects system performance.

[0044] Figure 5An example housing 500 that can be used with the V-shaped PCB 400 is shown. A pest enters through an opening 502 on one side of the housing 500, and the V-shaped PCB is positioned therein, with the pest flying between the V-shaped portion and the transmitter / detector. Because the housing 500 is shaped with a triangular apex portion, the V-shaped PCB can be configured to fit into the interior of the apex. In some embodiments, the V-shaped PCB is located near the opening 502, but it can be located at any desired location along the length of the housing 500. The advantage of having the V-shaped PCB near the opening is that pests are more likely to fly over rather than walk through the entrance of the detector / transmitter, thus improving accuracy. Figure 5 A solar panel 504 is also shown on the top of the top portion, which can optionally be used to power the system.

[0045] Figure 6 It shows from Figure 5 The disassembled housing 500 reveals several components, including a main body 506, an electronics compartment 508, a solar panel 504, a rear panel 510, and a cover 512 that encloses the electronics compartment 508. The electronics compartment 508 forms an internal space surrounded by the cover 512 and is configured to house, for example, a battery 514 and a microprocessor 516, which has sufficient I / O for a V-shaped PCB. A switch 518 and an indicator LED 520 extend through the walls of the electronics compartment 508. The switch 518 can be configured to turn the system on or off, and the indicator LED 520 can be configured to perform one or more different functions, such as turning on when the system is on, flashing or turning off when counting pests, etc. The solar panel 504 can be attached to either side of the top of the housing 500. In some embodiments, the electronics compartment 508 may be waterproof when the cover 512 is attached to prevent water damage to sensitive electronic components. In a partially waterproof embodiment of the electronic compartment 508, the electronic compartment 508 may be located at the bottom of the housing 500 to minimize water contact. Finally, the rear panel 510 is triangular in shape to match the shape of the housing 500. It includes a mesh section 522 to prevent pests from completely passing through and exiting from the other side.

[0046] In some implementations, the transmitter can be paired with a detector having one or more reflective surfaces to improve the detection area. For example, Figure 7 A pest detection system 700 is shown, having two parallel reflective surfaces—a first reflective surface 702 and a second reflective surface 704—which are configured as plates (e.g., assuming...). Figure 7 If drawn in the xy plane, they extend in the z direction. The transmitter 706 and detector 708 can be located at the midpoint along the height of the reflector. Figure 8A perspective view of PCB 710 is shown, with the second reflective surface 704 connected to it. The positions of emitter 706 and detector 708 can be seen from this figure. Figure 7 In the illustrated embodiment, transmitter 706 and detector 708 are connected to the same PCB 710, with a second reflective surface 704 disposed between them. Transmitter 706 projects infrared light towards detector at an angle, where the angle θ measured from the second reflective surface 704 can be 10 to 80° (preferably 40 to 60°). Detector 708 receives the infrared light after it has been reflected once or multiple times between the first reflective surface 702 and the second reflective surface 704. Figure 7 As shown, light is reflected twice from the first reflective surface 702 and once from the second reflective surface 704. The reflective surfaces of the subject matter of this invention need to be capable of reflecting infrared light so that, for a given configuration, they can reflect light from the emitter back to the detector at least once, but... Figure 7 The multiple reflections shown do not deviate from the subject matter of this invention.

[0047] In some implementations, a single transmitter can be used in conjunction with a set of detectors, where the transmitter is specifically designed to project a wider infrared cone than a typical transmitter in an LED package. For example, Figure 9 A transmitter 900 is shown, configured to project a wide and flat infrared beam. To increase its projection angle, the transmitter 900 includes a wide-angle lens portion 902.

[0048] Figure 10 It shows the use of, as Figure 9 The pest detection system 1000 is shown with a dedicated transmitter 1002. The PCB 1004 is a single piece, but in some embodiments, the PCB portion can be divided into multiple pieces as needed (e.g., one for the transmitter and another for the detector). In this embodiment, the transmitter 1002 is configured according to an example... Figure 11 The diagram shows the projected light. Figure 11 A transmitter configured to project infrared light of sufficient intensity for pest detection within a 150° (-75° to 75°) range is described. The range may vary depending on the transmitter configuration. For example, a transmitter in a similar package could be configured to project within a range of 180° to 45°. Thus, transmitter 1002 projects infrared light at a 150° angle, which is received by detector 1006.

[0049] To accommodate the wide projection angle (e.g., 150°) of the transmitter 1002, Figure 10Seven detectors 1006 are shown positioned opposite the transmitter 1002 to receive light from it. The detectors 1006 are shown to be evenly spaced, but this is not necessary; the detector density can vary depending on the light intensity at different projection angles. Furthermore, although seven detectors are shown, fewer detectors are conceivable (e.g., as few as two or three), and theoretically, there is no maximum number of detectors per transmitter.

[0050] The linear density of the area projected by the detector along the emitted infrared light can vary. The detector-to-emitter ratio can be a function of the emitter angle, the distance between the emitter and detector, the size of the pest, etc. Like the emitter, the detector also has an angle at which it can receive incident light. For example, a wide-angle receiver can detect light fluctuations caused by pests not directly in front of it. The passage of a pest in front of the detector also affects detection performance. For example, if a pest passes near the detector, it typically needs to be closer to the detector, but if it passes at a moderate distance (e.g., farther from the detector than in the previous example), the detector can indicate the pest's presence over a wider range of locations. Because the detector essentially detects light based on a detection cone (similar to a cone of light projected from the emitter), if the pest is closer to the detector, it is closer to the apex of the cone, making the area where the pest can be detected smaller than if the pest is farther away. In some implementations, the distance between detectors can be less than 1.5 times the size of the pest to be detected. This configuration minimizes the number of pests that should be counted but are not.

[0051] As described above, embodiments of the subject matter of this invention are configured to detect the presence of pests (i.e., insects). This is achieved by irradiating infrared light from one or more emitters to one or more detectors. In some embodiments, some or all of the emitters and detectors are activated via pulse width modulation (PWM). Driving the emitters via PWM results in energy savings by ensuring they are only on for certain periods of time rather than always being on. Furthermore, synchronizing the PWM driving of the emitters and detectors ensures that the detectors are activated only when the emitters produce light emission, thereby saving power.

[0052] Duty cycle parameters (e.g., duty cycle and frequency) can be static or adaptive. For example, if the system of the subject of this invention is configured to monitor a moth with a wingbeat frequency of 60 Hz, the detection sampling frequency needs to be at least 120 Hz. For a detection sampling frequency of 120 Hz, there are at least 120 "on" periods, therefore a duty cycle frequency of 240 Hz should be implemented. Duty cycles of 10% to 90% can be implemented, and the duty cycle percentage can be dynamically varied as needed. In some embodiments, a higher duty cycle (e.g., ≥50%) can be associated with a lower duty cycle frequency, and vice versa. The duty cycle frequency should be at least twice the detection sampling frequency, which should be at least twice the wingbeat frequency of the pest being detected. In adaptive systems, the duty cycle parameter can vary according to various environmental factors to detect different pests. For example, when setting the duty cycle, factors such as location, time of day, time of year, relative humidity, and temperature can be considered, as all of these factors contribute to the likelihood of specific types of pests appearing. In a static system, the duty cycle can be set and then kept constant. In such systems, the duty cycle frequency should be set high enough to detect pests with high wingbeat frequencies, such as fruit flies, mosquitoes, and midges.

[0053] The duty cycle parameter can be adjusted by the user via software (e.g., providing input to set the duty cycle or on / off ratio) or hardware (e.g., rotating one or more adjustment dials to set the duty cycle parameter). In some implementations, the duty cycle parameter can be adjusted according to environmental factors as described above, but the duty cycle frequency can also be adjusted remotely by the user via software. In some implementations, the duty cycle parameter can vary based on location and the known pests present at that location, for example, by extracting information from a database maintained by a local environmental service department (public or private). Dynamically defining the duty cycle parameter according to pest type can improve efficiency.

[0054] Figure 12 The steps shown describe how information from a detector can be used to determine the presence of pests. In step 1200, an analog signal from the detector is monitored. The detector of the subject of this invention is a photodiode, which generates an electrical signal (e.g., voltage, current, or both) when it receives light. Specifically, these photodiodes can be selected based on their sensitivity to infrared light. Thus, when the emitter projects infrared light, the detector receives that infrared light, thereby generating a raw analog signal.

[0055] In step 1202, as described above, analog signals outside the target range are largely eliminated by hardware frequency filtering using, for example, a bandpass filter. Certain frequencies or frequency ranges are blocked because the wingbeat frequencies of pests are typically outside or near these ranges. For example, for moths whose wingbeat frequencies are typically in the 50 to 80 Hz range, hardware filtering is set to eliminate frequencies below 40 Hz and above 100 Hz, while for smaller insects such as fruit flies and mosquitoes whose wingbeat frequencies are typically in the 200 to 1200 Hz range, a bandpass filter can be implemented to eliminate frequencies below 200 Hz and above 1500 Hz. It may be desirable to maintain frequencies from 40 Hz to about 1500 Hz, and all ranges in between are explicitly envisioned in this application as feasible in embodiments of the subject matter of this invention, allowing the range to be determined based on the wingbeat frequency of the type of pest to be detected. Once the range of wingbeat frequencies is known, appropriate filtering can be implemented. While bandpass filtering is useful, in some embodiments, it is only necessary to eliminate frequencies below a threshold; therefore, each of the lower limits described above should be interpreted as also disclosing an upper limit for the filter to remove all frequencies below that value.

[0056] After passing through a hardware filter, the signal is digitized in step 1204. With signal digitization, a multi-step filtering process can be implemented to minimize false pest detections while reducing processing costs. Although these steps are described sequentially, some or all of them may be performed in a different order than those described. First, the analog signal from the detector is sent (e.g., continuously during generation) to an analog-to-digital converter (ADC). The digitization sampling frequency of the ADC of the subject matter of this invention can be, for example, 4 kHz to 10 kHz. In some embodiments, a sampling frequency of approximately 8 kHz is sufficient.

[0057] Then, in step 1206, the digitized signal is continuously monitored for potential pest signals. To monitor potential pest signals, two signal amplitude thresholds are set, one high and one low. For example, it has been found that setting the thresholds to -0.6 and 0.6 is sufficient for pest detection when the signal amplitude is normalized to the range of -1 to 1. Amplitude normalization is not mandatory, although it can make the system of the subject matter of this invention more robust (e.g., better able to manipulate detectors that output different signal amplitudes). In embodiments without normalization, these thresholds can still be implemented by performing some basic mathematics based on the measured amplitude range of a given detector or group of detectors (e.g., the maximum amplitude can be associated with 1, and the minimum amplitude can be associated with -1).

[0058] When the digital signal value from the ADC exceeds any threshold a certain number of times in consecutive digitization blocks (e.g., exceeding the threshold 2-3 times consecutively, or in some embodiments 2-6 times consecutively), this indicates the presence of potential pests. Detecting consecutive digital signal values ​​exceeding any threshold can improve performance by eliminating false alarms. Once a digital signal value has been observed to have exceeded a certain threshold a predetermined number of times consecutively, a certain number of digital signal values ​​are recorded. In some embodiments, 1024 samples are recorded, but the number of samples recorded can range from 256 to 8192. The number of digital signal values ​​to be recorded can vary depending on several factors, including the ADC sampling rate. Figure 13 An example recorded signal is shown, represented as the relationship between amplitude and a block of digital signal (in this case, the recorded sample is 1024 in length). The figure shows where the digital signal value exceeds a normalized amplitude threshold (e.g., + / - 0.6).

[0059] Another way to express how many digital signal values ​​should be recorded is to specify the recording duration. Because the number of digital signal values ​​captured over a given time depends on, for example, the sampling frequency of the ADC, specifying the capture time may be more robust. For example, if the ADC sampling rate is approximately 8 kHz and 1024 digital signal values ​​are recorded, it means the system records for approximately 0.125 seconds. This can be expressed as follows:

[0060] Number of digital signal values ​​ / ADC sampling rate (Hz) = Elapsed recording time

[0061] Therefore, the elapsed time should be 0.05-0.3 seconds (preferably about 0.125 seconds), but without departing from the subject matter of the invention, it can be recorded for up to 1-3 seconds. These ranges of elapsed time improve the system's ability to detect pests because sufficient time must be captured to confirm that the pest has indeed passed the detector, and the signal is not merely captured noise. It is worth noting that any number of digital signal values ​​recorded should be an integer, and higher ADC sampling rates generally improve system performance (although performance and power consumption should be balanced). For example, if an ADC with a sampling rate of 4 kHz is used, the number of digital signal values ​​to be recorded should be about 512.

[0062] Therefore, when the recorded signal includes consecutive digital signal values ​​exceeding the threshold normalized amplitude value, this indicates the presence of pests, and not just some random electrical noise. Although random electrical noise can exceed the threshold, it is much less common for noise to exceed the threshold in two consecutive samples. However, in some cases, noise can exceed the threshold in multiple consecutive digital signal values. Further filtering can be implemented to eliminate these types of false alarms.

[0063] Therefore, in step 1206, the system determines whether the signal in the recorded sample indicates pests or noise. Figure 14 This illustrates how to achieve this using an onboard classifier. The onboard classifier can be implemented as software, hardware, or some combination of both. First, the recorded samples are passed to the onboard classifier, which must select which type of classifier to use based on, for example, the expected pest type. The expected pest type can be determined in various ways, including by location, observation, etc. (as described above regarding the duty cycle parameter). This involves feature extraction and model selection. In feature extraction, the system examines one or more peaks from the recorded signal, calculates the properties of these peaks, and then calculates the statistical results of the peak properties. Next, an appropriate model is applied to determine the presence of a pest. For example, if a moth is indicated as a possible pest, a moth model can be used to analyze features to determine whether to count the moth. The results of this analysis are then saved to storage (e.g., whether pests are counted or noise is ignored), and can be used to improve detection through, for example, machine learning. During step 1208, it is determined whether the signal indicates a pest or noise. Once the above results are saved to storage, the number of detected pests can be counted according to step 810. If any redundant counts exist, these redundancies can be eliminated according to step 812, although this step is optional, as redundancy can be eliminated throughout the process of determining the presence of pests as described above and in more detail below.

[0064] Therefore, classification involves feature extraction as described above, which is computed in the time domain. In some implementations, the goal of classification is to identify all peaks in the signal that exceed an upper threshold of the normalized amplitude, and then combine consecutive peaks whose valleys in between do not exceed a lower threshold. From there, peak characteristics are computed, which involves determining the peak width. The peak width can describe the distance along the x-axis between the preceding and following valleys of a particular peak, where units along the x-axis represent discrete digital signal values. Height is also computed, where the height is measured based on the signal amplitude (e.g., normalized to -1 to 1), and the peak height is measured in units along the y-axis between the analyzed valleys and peaks. Figure 15 This demonstrates how to measure width and height. Finally, sharpness can be calculated, where sharpness is the height of the peak divided by the width of the peak.

[0065] Therefore, the system of the present invention can be configured to calculate the total number of peaks in a recorded signal, as well as the maximum sharpness, average sharpness, maximum height, average height, maximum width, and average width. All or some of these values ​​can be used with machine learning algorithms, as, for example, as a training set, to improve classification. Figure 16 An example signal is shown, with different peaks labeled, along with the maximum sharpness, average sharpness, average height, average width, and peak threshold. In this figure, the amplitude is not normalized to the range of -1 to 1.

[0066] Figure 17A system diagram is shown, in which the system is configured to perform the above and Figure 12 The steps shown are all or part of the steps described above. All the details above are also relevant here. The analog sensor described above is a pulse-width modulated infrared detector. The signal from the sensor is converted from analog to digital using an ADC that samples at, for example, 8 kHz. From there, a comparator (e.g., ADS1115) monitors for consecutive blocks of digital signals exceeding an amplitude threshold. If no consecutive digital signal values ​​are detected, monitoring continues. When a certain number of consecutive digital signal values ​​exceed the amplitude threshold (e.g., 2 to 6, inclusive), the system wakes up and receives 1024 recorded digital signals. Figure 17 This is also referred to as a "sample." Time, temperature, and relative humidity can then be recorded, and an onboard classifier is used to determine whether the recorded digital signal values ​​indicate a pest. Humidity, time, and temperature can all be used to improve detection and can be stored along with other data, such as to aid machine learning. When a pest is detected, information is stored in the pest storage; when noise is detected, information is stored in the noise storage. Both the pest storage and the noise storage can be saved to any type of computer-readable media, whether locally or remotely via a network connection.

[0067] Therefore, specific systems and methods relating to pest detection have been disclosed. However, it will be apparent to those skilled in the art that further modifications can be made beyond those already described without departing from the inventive concept of this application. Therefore, the subject matter of the invention is not limited unless it conforms to the spirit of this disclosure. Furthermore, in interpreting this disclosure, all terms should be interpreted as broadly as possible in light of the context. In particular, the term "comprising" should be interpreted in a non-exclusive manner as referring to an element, component, or step, indicating that the mentioned element, component, or step may be present, used, or combined with other elements, components, or steps not expressly mentioned.

Claims

1. A pest detection system, comprising: A first printed circuit board (PCB) portion and a second PCB portion, wherein there is a space between the first PCB portion and the second PCB portion; At least one transmitter is disposed on the first PCB portion; At least one detector is disposed on the second PCB section; At least one of the transmitters is oriented toward at least one detector; At least one of the detectors is oriented toward at least one transmitter; A pulse width modulation controller configured to drive at least one of at least one transmitter and at least one detector; The first PCB section and the second PCB section are both parts of a single PCB; and Each PCB is V-shaped, having a first arm and a second arm, wherein the first arm includes a first PCB portion and the second arm includes a second PCB portion; The transmitter and detector are driven by synchronous PWM, and pulse width modulation is applied to the transmitter and detector to make them turn on synchronously at the same time; The system monitors continuous digital signal blocks that exceed the amplitude threshold using a comparator. When a number of continuous digital signal values ​​exceed the amplitude threshold, the system wakes up and receives digital signals.

2. The system of claim 1, wherein the pulse width modulation controller operates at a duty cycle of 10% to 90% and a frequency greater than 240 Hz.

3. The system of claim 1, wherein at least one detector comprises a photodiode.

4. The system of claim 1, wherein at least one transmitter is configured to project infrared light.

5. The system of claim 3, wherein at least one transmitter is configured to project infrared light with a wavelength of 700 nm to 1400 nm.

6. The system of claim 5, wherein at least one detector is configured to detect infrared light.

7. The system of claim 5, wherein at least one detector is configured to detect infrared light with a wavelength of 700 nm to 1400 nm.

8. A pest detection system, comprising: A first printed circuit board (PCB) portion and a second PCB portion, wherein there is a space between the first PCB portion and the second PCB portion; A wide-angle transmitter is mounted on the first PCB section; A set of detectors is installed on the second PCB section; The wide-angle emitter is oriented towards this group of detectors; Each detector in this group is oriented towards the wide-angle transmitter; and A pulse width modulation controller configured to drive a wide-angle transmitter and detector; The transmitter and detector are driven by synchronous PWM, and pulse width modulation is applied to the transmitter and detector to make them turn on synchronously at the same time; The system monitors continuous digital signal blocks that exceed the amplitude threshold using a comparator. When a number of continuous digital signal values ​​exceed the amplitude threshold, the system wakes up and receives digital signals.

9. The system of claim 8, wherein the first PCB portion and the second PCB portion are part of a single PCB.

10. The system of claim 8, wherein the pulse width modulation controller operates at a duty cycle of 10% to 90% and a frequency greater than 240 Hz.

11. The system of claim 8, wherein each detector in the group of detectors comprises a photodiode.

12. The system of claim 8, wherein the wide-angle emitter is configured to project infrared light.

13. The system of claim 12, wherein the wide-angle emitter is configured to project infrared light with wavelengths of 700 nm to 1400 nm.

14. The system of claim 13, wherein each detector in the group of detectors is configured to detect infrared light.

15. The system of claim 13, wherein each detector in the group of detectors is configured to detect infrared light in the wavelength range of 700 nm to 1400 nm.

16. A pest detection system, comprising: A first printed circuit board (PCB) portion and a second PCB portion, wherein there is a space between the first PCB portion and the second PCB portion; At least one transmitter is disposed on the first PCB portion; At least one detector is disposed on the second PCB section; At least one of the transmitters is oriented toward at least one detector; At least one of the detectors is oriented toward at least one transmitter; A pulse width modulation controller is configured to drive at least one of at least one transmitter and at least one detector; and At least one of the detectors is configured to detect infrared light; The transmitter and detector are driven by synchronous PWM, and pulse width modulation is applied to the transmitter and detector to make them turn on synchronously at the same time; The system monitors continuous digital signal blocks that exceed the amplitude threshold using a comparator. When a number of continuous digital signal values ​​exceed the amplitude threshold, the system wakes up and receives digital signals.

17. The system of claim 16, wherein the first PCB portion and the second PCB portion are part of a single PCB.

18. The system of claim 17, wherein the individual PCB is V-shaped, having a first arm and a second arm, wherein the first arm includes a first PCB portion and the second arm includes a second PCB portion.

19. The system of claim 17, wherein the single PCB is annular, having a first side and a second side, wherein the first side includes a first PCB portion and the second side includes a second PCB portion.

20. The system of claim 16, wherein the pulse width modulation controller operates at a duty cycle of 10% to 90% and a frequency greater than 240 Hz.

21. The system of claim 16, wherein at least one detector comprises a photodiode.

22. The system of claim 16, wherein at least one transmitter is configured to project infrared light.

23. The system of claim 22, wherein at least one transmitter is configured to project infrared light with a wavelength of 700 nm to 1400 nm.

24. The system of claim 22, wherein at least one detector is configured to detect infrared light in the wavelength range of 700 nm to 1400 nm.

25. A pest detection system, comprising: A first printed circuit board (PCB) portion and a second PCB portion, wherein there is a space between the first PCB portion and the second PCB portion; At least one transmitter is disposed on the first PCB portion; At least one detector is disposed on the second PCB section; At least one of the transmitters is oriented toward at least one detector; At least one of the detectors is oriented toward at least one transmitter; A pulse width modulation controller configured to drive at least one of at least one transmitter and at least one detector; The first PCB section and the second PCB section are both parts of a single PCB; and Each PCB is ring-shaped, having a first side and a second side, wherein the first side includes a first PCB portion and the second side includes a second PCB portion; The transmitter and detector are driven by synchronous PWM, and pulse width modulation is applied to the transmitter and detector to make them turn on synchronously at the same time; The system monitors continuous digital signal blocks that exceed the amplitude threshold using a comparator. When a number of continuous digital signal values ​​exceed the amplitude threshold, the system wakes up and receives digital signals.

26. The system of claim 25, wherein the pulse width modulation controller operates at a duty cycle of 10% to 90% and a frequency greater than 240 Hz.

27. The system of claim 26, wherein at least one transmitter is configured to project infrared light with a wavelength of 700 nm to 1400 nm.

28. The system of claim 25, wherein at least one detector comprises a photodiode.

29. The system of claim 25, wherein at least one transmitter is configured to project infrared light.

30. The system of claim 29, wherein at least one detector is configured to detect infrared light.

31. The system of claim 29, wherein at least one detector is configured to detect infrared light in the wavelength range of 700 nm to 1400 nm.

Images