Pest detection system and method

Abstract

The present subject matter is directed to a pest detection system that implements an infrared emitter along with a detector that looks for variations in the incident light indicative of wing flapping from various pests. The emitters and detectors are arranged on one or more printed circuit boards such that infrared light projected from the emitter can be received by the one or more detectors. Based on signals generated by the detectors, the system of the present subject matter can determine whether a pest has flown between the emitter and the detector. To conserve power, the emitter, the detector, or both can be driven by pulse width modulation. Methods of the present subject matter are directed to determining the presence of pests by signal filtering and interpretation.

Description

[Technical field]

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

[0002] The Background Description includes information that may be helpful in understanding the present invention. No admission is made that any of the information provided in this application is prior art or relevant to the invention claimed herein, or that any publication referenced, expressly or implicitly, is prior art.

[0003] Agriculture is one of mankind's oldest and remains one of its most important enterprises. Throughout human history, efforts have been made to minimize the impact of pests and diseases, to enhance the healthiness and nutrient content of food, and to increase crop yields. When it comes to increasing crop yields, pest detection is crucial. Pests tend to pose the greatest threat to good crop production, and depending on the type of crop and the growth stage, early pest detection can reduce yield losses by up to 20-40%, by some estimates.

[0004] In the past, pest detection required farmers to walk their fields to visually inspect for pests that may harm crops. However, with industrialization, farmland has expanded to such an extent that walking the farm is not possible. In fact, even driving around the farm is not possible as it would require farmers to spend a tremendous amount of time on repetitive tasks. Hence, there have been efforts to develop automated pest detection systems.

[0005] Some efforts have developed visual detection systems; however, these systems are incomplete. In visual detection systems, cameras are implemented to periodically take pictures or take videos of pests, for example, attracted to a trap. However, many of these systems still require a human operator to view the images for pest detection, and require a human user to, for example, count the number of pests captured in the trap. Acoustic pest detection has also been implemented, in which an electromechanical listening device is used to determine when a pest is flying through some entrance by listening for increases in noise levels associated with various pests.

[0006] However, all of these systems are deficient, e.g., with respect to power consumption, accuracy, elimination of the need for human inspection, etc. Thus, it has not yet been recognized that pest detection can be accomplished using infrared light via systems designed to automatically detect wing beat frequencies associated with flying pests. Summary of the Invention [Means for solving the problem]

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

[0008] In some embodiments, the first PCB portion and the second PCB portion are part of a single PCB, and in some embodiments, the single PCB is V-shaped with a first arm and a second arm, the first arm including the first PCB portion and the second arm including the second PCB portion. The single PCB is annular with a first side and a second side, the first side including the first PCB portion and the second side including the second PCB portion. In some embodiments, the pulse width modulation controller operates at a duty cycle between 10% and 90% and a frequency greater than 240 Hz. The at least one detector can include a photodiode, and the at least one emitter can be configured to project infrared light (e.g., at a wavelength between 700 nm and 1,400 nm). In some embodiments, the at least one detector is configured to detect infrared light (e.g., at a wavelength between 700 nm and 1,400 nm).

[0009] In another aspect of the present subject matter, a pest detection system includes a first printed circuit board (PCB) portion and a second PCB portion, where a space exists between the first PCB portion and the second PCB portion, a wide-angle emitter disposed on the first PCB portion, a set of detectors disposed on the second PCB portion, where the wide-angle emitter is oriented to face the set of detectors and where each detector in the set of detectors is oriented to face the wide-angle emitter, a set of detectors, and a pulse-width modulation controller configured to drive the wide-angle emitter and the detectors.

[0010] In some embodiments, the first PCB portion and the second PCB portion are part of a single PCB, and the pulse width modulation controller can be configured to operate at a duty cycle between 10% and 90% and a frequency greater than 240 Hz. Each detector in the set of detectors can be a photodiode, and the wide angle emitter can be configured to project infrared light (e.g., wavelengths between 700 nm and 1,400 nm). Each detector in the set of detectors can be similarly configured to detect infrared light (e.g., wavelengths between 700 nm and 1,400 nm). Effect of the Invention

[0011] It should be appreciated that the subject matter of the present disclosure provides many advantageous technical effects, including the ability to detect the presence of pests while discarding false positives with improved accuracy over existing systems.

[0012] Various objects, features, aspects and advantages of the present subject matter will become more apparent from the following detailed description of preferred embodiments, taken in conjunction with the accompanying drawings, in which like numerals represent like elements and in which: [Brief description of the drawings]

[0013] [Figure 1] 1 shows a circular pest detection system. [Diagram 2] 1 shows a ring-shaped pest detection system placed within a fly trap. [Diagram 3] A cutaway view of the fly trap is shown. [Figure 4] 1 shows a V-shaped pest detection system. [Diagram 5] 1 shows a housing for a V-shaped pest detection system. [Figure 6] 1 shows the components of the housing. [Figure 7] 1 shows a reflective pest detection system. [Figure 8] 1 shows a perspective view of a portion of a reflective pest detection system. [Figure 9] A wide angle emitter is shown. [Figure 10] 1 shows a pest detection system implementing a wide-angle emitter. [Figure 11] 4 shows the relative radiant intensity over different angles for a wide angle emitter. [Figure 12] 1 is a flow chart illustrating how pests can be detected. [Figure 13] An example signal is shown along with a threshold for the detected signal amplitude. [Figure 14] 1 shows a schematic diagram for an on-board signal classifier. [Figure 15] This shows how the signal waveform can be measured. [Figure 16] An example signal is shown along with some measured waveforms. [Figure 17] 1 shows a diagram illustrating how the system of the present subject matter treats pests. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] The following description provides example embodiments of the subject matter of the present invention. Although each embodiment represents a single combination of inventive elements, the subject matter of the present invention is considered to include all possible combinations of the elements disclosed. Thus, if one embodiment includes elements A, B, and C, and a second embodiment includes elements B and D, the subject matter of the present invention is considered to include other remaining combinations of A, B, C, or D, even if not explicitly disclosed.

[0015] As used throughout this description and the claims which follow, the meanings of "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Also, as used in this description, the meaning of "in" includes "in" and "on," unless the context clearly dictates otherwise.

[0016] Also, as used in the description of this application, and unless the context clearly dictates otherwise, the term "coupled to" is intended to include both direct coupling (where the two elements that are coupled to each other contact each other) and indirect coupling (where at least one additional element is disposed between the two elements). Thus, the terms "coupled to" and "coupled with" are used synonymously.

[0017] In some embodiments, the numbers expressing amounts of ingredients, properties such as concentrations, reaction conditions, and the like, used to describe and claim certain embodiments of the present invention, should be understood in some cases as being modified by the term "about". Accordingly, in some embodiments, the numerical parameters set forth in the specification and the appended claims are approximations that may vary depending on the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed by taking into account the number of reported significant digits and applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters defining the broad scope of some embodiments of the present invention are approximations, the numerical values ​​set forth in the specific examples are reported as precisely as practicable. The numerical values ​​presented in some embodiments of the present invention may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements. Moreover, unless the content clearly indicates otherwise, all ranges set forth in this application should be construed as inclusive of their endpoints, and open-ended ranges should be construed as including only commercially practical values. Similarly, all lists of values ​​should be considered to include intermediate values ​​unless indicated to the contrary.

[0018] It should be noted that any language directed to computers should be read 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 as a whole. It should be understood that a computing device includes a processor configured to execute software instructions stored on a tangible, non-transitory computer-readable storage medium (e.g., hard drive, solid state drive, RAM, flash, ROM, etc.). The software instructions preferably configure the computing device to provide the roles, responsibilities, or other functions described below with respect to the disclosed devices. In a particularly preferred embodiment, the various servers, systems, databases, or interfaces exchange data using standardized protocols or algorithms, perhaps based on HTTP, HTTPS, AES, public-private key exchange, web services APIs, known financial transaction protocols, or other methods of electronic information exchange. Data exchange is preferably performed over a packet-switched network, the Internet, a LAN, a WAN, a VPN, or other types of packet-switched networks. The following description includes information that may be helpful in understanding the present invention. No admission is made that any of the information provided in this application is prior art or relevant to the present claimed invention, or that any publication referenced, expressly or implicitly, is prior art.

[0019] Embodiments of the present subject matter are generally directed to pest detection via electromagnetic radiation emission and detection. When a pest, e.g., a fly, passes between an emitter and a corresponding detector, the flapping of the fly's wings is detected, allowing the system of the present subject matter to determine the flapping frequency. Thus, each system includes at least one emitter / detector pair (although different ratios of emitters to detectors are also contemplated and described below). With respect to the detectors, photodiodes are implemented instead of phototransistors for various reasons. With respect to embodiments of the present subject matter, photodiodes provide an improved linear response resulting in a more stable system than one created using phototransistors, and they also result in lower power consumption compared to phototransistors. Photodiodes are therefore more responsive to incident light, have a better linear response to a wider range of light, and may pass less current compared to phototransistors. For these reasons, embodiments of the present subject matter implement photodiodes instead of phototransistors (although it is still contemplated that the sub-system may be created using phototransistors). To further conserve power consumption, pulse width modulation can be implemented on both the emitter and detector such that they are synchronized to turn on at the same time.

[0020] For the reasons mentioned above, photodiodes are more accurate than phototransistors for pest detection across a wide range of pest sizes. Phototransistors have a slower response time, so phototransistors are not good at detecting small insects, for example those with flapping frequencies above 700 Hz.

[0021] Emitters used in embodiments of the present subject matter include LEDs configured to emit infrared light. IR wavelengths considered may range from 700 nm to 1,400 nm. In a preferred embodiment, IR light is emitted at about 940 nm, so the spectral response range for the photodiodes acting as detectors may span from 840 nm to 1,100 nm. The spectral response range for the photodiodes of the present subject matter may match whatever emitter is used, so the range may also include 700 nm to 1,400 nm. Some advantages of implementing IR light emission include that IR emitters consume less power than, for example, laser emitters, and that visible light produces undesirable changes in pest behavior. Additionally, visible light may attract undesirable pests. Moreover, visible light systems may be affected by solar radiation, which introduces noise that may interfere with proper system function.

[0022] Embodiments of the present subject matter can be arranged in a variety of different ways. For example, FIG. 1 illustrates an annular configuration of a pest detection system 100. A set of emitters 102 are disposed on opposite sides of a set of detectors 104, all of which are disposed on the same printed circuit board (PCB) 106. Although shown on a single PCB in FIG. 1, it is contemplated that the PCB 106 can be split into multiple components without departing from the present subject matter. The emitters on one side are configured to project infrared light towards the detectors, so that a signal generated by one or more of the detectors can be interpreted by a microprocessor to determine whether a pest has been detected. The infrared light projection is illustrated in FIG. 1 according to a two-dimensional representation of the light spreading from each emitter. Since infrared light is invisible to the human eye, this visualization is provided for illustrative purposes only.

[0023] The annular configuration can be used, for example, in an embodiment directed to fruit fly detection, where the pest detection system 100 can be placed, for example, in a funnel-based fly trap. The pest detection system 100 features four emitters and five detectors, although there could be as few as one emitter and one detector. There is no upper limit to the number of emitters or detectors, but the number could range from 1 to 20 depending on design and functional considerations (e.g., depending on annulus diameter, desired sensitivity, etc.). Bringing the emitters closer to the detectors, as well as a higher density of emitters and detectors, can improve sensitivity, which can be crucial for certain pests, such as midges. Sensitivity can be improved by minimizing blind spots (e.g., spots where a pest can pass between an emitter and a detector without passing through the emission cone from one of the emitters) that may otherwise be present. Because the emitter and detector are physically close to each other (e.g., 3-10 cm, preferably about 4.5 cm), signal integrity remains high (e.g., signal strength decreases more for longer distances compared to shorter distances). Gain and filter adjustments can be made from the default design to increase sensitivity to smaller insect sizes and higher frequencies. Additionally, because the emitter is closer to the detector, emitter current can be reduced.

[0024] Filtering may occur in the frequency domain, for example by adding a bandpass filter. The bandpass filter is characterized by a lower limit and an upper limit. The lower limit may be in the range of 50-300 Hz and the upper limit may be in the range of 1000-2000 Hz. In a preferred embodiment, the lower limit is about 120 Hz and the upper limit is about 1500 Hz (+ / - 10% for each limit). Small insect flapping generally falls within this range. Additional filtering in the time domain may be useful to filter out other noises.

[0025] There is a correlation between gain and current, and light emission from an emitter is a function of current. Higher gain may amplify noise, but may also improve performance in systems where a low current drives one or more emitters (e.g., less light is produced). Increasing the current to the emitter to generate more IR light, on the other hand, may cause problems with small insects, since too much IR light emitted may reduce sensitivity. The subject system of the present invention is configured to measure the relative change in light intensity received at one or more detectors that occurs when a pest passes between the detector and the emitter. If too much light is emitted, the detectors may reach saturation, making them unable to detect small changes. Thus, the gain and current for a given system depend on a variety of factors, including pest size, distance between emitter and detector, saturation level for the detector, etc.

[0026] As shown in FIG. 2, the pest detection system 100 is shown positioned around an entrance 202 through which pests (e.g., flies) enter the trap 200. Pests enter at the bottom of the trap and pass through the entrance as they progress toward the interior of the trap. FIG. 3 shows a side cutaway view of the trap 200 shown in FIG. 2. The cutaway view shows that the trap 200 has been modified to include a landing spot 204, for example, for flies to land on. The problem with this type of trap configuration is that sometimes pests will walk across the entrance 202 to enter the trap 200, rather than flying, and because the system of the present subject matter relies on wing flapping to determine whether a pest is present, if the pest walks it will not be counted. The landing spot 204 improves counting accuracy by giving pests, such as flies, a place to land just outside the entrance 202, making it much more likely that the pest will fly through the entrance rather than walk.

[0027] In another embodiment, the pest detection system can include a PCB configured in a V-shape. Although FIG. 4 shows a pest detection system 400 with a PCB configured at a right angle, other angles ranging from 10° to 170° can be implemented without departing from the subject matter of the present invention. The right angle configuration provides balance so that emitters 402 can be paired with detectors 404 in a manner that minimizes blind spots. As shown in FIG. 4, each side of the V-shaped PCB includes an emitter-detector-detector pattern. Each emitter corresponds to two adjacent detectors on opposite sides of the V. The emitters can be configured to project infrared light according to, for example, a cone, or a portion of a cone. Each emitter emits infrared light that projects outward and spreads away from its source, so that each emitter is paired with two detectors. The number of detectors paired with each emitter may vary according to, for example, the diffusion angle associated with the emitter (e.g., the apex angle relative to the emitter's cone of emitted light) and the distance between the emitter and the detector. Each of the two detectors paired with a single emitter is configured to receive infrared light primarily or exclusively from that emitter. In some embodiments, three or more detectors are paired with a single emitter (e.g., up to 10 or more). While there is no theoretical limit to the number of detectors per emitter, practical limitations may arise due to considerations such as emitter diffusion and distance from the emitter, where, for example, the emitter cannot project enough light to reach the detector with sufficient intensity or the detector is placed outside the region of the emitter's projected light. As previously mentioned, the intensity of the IR light received at the detector may affect the performance of the system.

[0028] FIG. 5 illustrates an example housing 500 that can be used with the V-shaped PCB 400. Pests enter through an opening 502 on the side of the housing 500, within which the V-shaped PCB is located, and the pests fly between the emitters / detectors within the V-shaped portion. Because the housing 500 is formed with a triangular roof portion, the V-shaped PCB can be positioned such that it is attached to the inside of the roof. In some embodiments, the V-shaped PCB is positioned near the opening 502, but can be positioned anywhere along the length of the housing 500 that is desired. The advantage of positioning the V-shaped PCB near the opening is that the pests are more likely to fly through the entrance of the detector / emitter, rather than walk, improving accuracy. FIG. 5 also illustrates a solar panel 504 positioned on the roof portion, which can optionally be used to power the system.

[0029] FIG. 6 shows the housing 500 from FIG. 5 exploded. Several components are visible, including the main body 506, the electronics compartment 508, the solar panel 504, the rear panel 510, and the lid 512 that covers the electronics compartment 508. The electronics compartment 508 forms an interior space enclosed by the lid 512, which is configured to hold, for example, a battery 514 and a microprocessor 516 with sufficient I / O for a V-shaped PCB. A switch 518 and an indicator LED 520 penetrate 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 lighting up when the system is on, flashing when pests are counted, etc. The solar panel 504 can be mounted on either side of the roof of the housing 500. In some embodiments, the electronics compartment 508 can be watertight when the lid 512 is installed to prevent water damage to sensitive electronics. The electronics compartment 508 may be located on the bottom of the housing 500 to minimize water ingress in embodiments where the electronics compartment 508 is not completely watertight. Finally, the rear portion 510 is triangular in shape to match the shape of the housing 500. It includes a mesh portion 522 that prevents pests from passing all the way through and out the other side.

[0030] In some embodiments, one emitter can be paired with a detector with one or more reflective surfaces implemented to improve the detection area. For example, FIG. 7 shows a pest detection system 700 with two parallel reflective surfaces - a first reflective surface 702 and a second reflective surface 704 - configured as a plate (e.g., extending in the z direction assuming FIG. 7 is drawn in the xy plane). The emitter 706 and the detector 708 can be positioned at the midpoint along the height of the reflective plate. FIG. 8 shows a perspective view of a PCB 710 to which the second reflective surface 704 is coupled. From this view, the positioning of the emitter 706 and the detector 708 can be seen. In the embodiment shown in FIG. 7, the emitter 706 and the detector 708 are connected to the same PCB 710 with the second reflective surface 704 located between them. Emitter 706 projects infrared light at an angle toward the detector, where the angle θ can be between 10 and 80° (preferably between 40 and 60°) measured from second reflective surface 704, and detector 708 receives the infrared light after the light has bounced one or more times between first reflective surface 702 and second reflective surface 704. As shown in FIG. 7, the light bounces twice off first reflective surface 702 and once off second reflective surface 704. The reflective surface of the present subject matter needs to be able to reflect enough infrared light such that it can bounce the light from the emitter back to the detector at least once for a given configuration, although multiple bounces as shown in FIG. 7 do not depart from the subject matter of the present invention.

[0031] In some embodiments, a single emitter can be used in association with a set of detectors, where the emitter is specially designed to project a wider cone of infrared light than a typical emitter in an LED package. For example, Figure 9 shows an emitter 900 that is configured to project a wide, flat cone of infrared light. To increase its projection angle, the emitter 900 includes a wide-angle lens portion 902.

[0032] FIG. 10 illustrates a pest detection system 1000 implementing a dedicated emitter 1002 similar to that shown in FIG. 9. Although the PCB 1004 is shown as a single piece, in some embodiments the PCB portion can be multiple pieces (e.g., one for the emitter and one for the detector) if desired. In this embodiment, the emitter 1002 is configured to project light, for example, according to the graph shown in FIG. 11, which illustrates an emitter configured to emit infrared light at sufficient intensity over 150° (-75° to 75°) for pest detection. The range can vary according to the emitter configuration. For example, an emitter in a similar package can be configured to project over a range from 180° to 45°. The emitter 1002 thus projects infrared light at 150°, which is received by the detector 1006.

[0033] To accommodate the wide projection angle of the emitter 1002 (e.g., 150°), Figure 10 shows seven detectors 1006 disposed across from the emitter 1002 so that they are positioned to receive light from the emitter 1002. Although the detectors 1006 are shown equally spaced, this is not a requirement and detector density may vary depending on the light intensity at different projection angles. Moreover, although seven detectors are shown, it is contemplated that fewer detectors (e.g., as few as two or three) could be implemented and there is theoretically no upper limit to the number of detectors per emitter.

[0034] The linear density of detectors along the range of the area onto which the emitted IR light is projected can vary. The ratio of detectors to emitters can be a function of emitter angle, distance between emitter and detector, pest size, etc. Like emitters, detectors have angles at which they can receive incident light. For example, wide-angle receivers can detect light fluctuations caused by pests that are not directly in front of them. Where the pest crosses in front of the detector can also affect detector performance. For example, if the pest crosses close to the detector, the pest should generally be close to the front of the detector, but if the pest crosses at a medium distance (e.g., farther from the detector than in the previous example), the detector can indicate the presence of the pest for a wider range of locations. Since the detector essentially detects light according to a cone of detection (similar to the cone of projected light from the emitter), the closer the pest is to the detector, the closer the pest is to the apex of the cone, and the area over which the pest can be detected will be smaller than if the pest is farther away. In some embodiments, the distance between the detectors can be less than 1.5 times the size of the pest to be detected. This configuration can minimize the number of uncounted pests that would otherwise be counted.

[0035] Embodiments of the present subject matter, as discussed above, are configured to detect the presence of pests, i.e., insects. This is accomplished by shining infrared light from one or more emitters to one or more detectors. In some embodiments, some or all of the emitters and detectors are operated by pulse width modulation (PWM). Driving the emitters with PWM saves energy by ensuring that the emitters are on only a percentage of the time instead of always on. Additionally, driving both the emitters and detectors with synchronized PWM ensures that the detectors are only operated when the emitters are generating a light projection, thus saving power.

[0036] Duty cycle parameters (e.g., duty cycle and frequency) can be static or adaptive. For example, if the system of the present subject matter is configured to monitor moths with a flapping frequency of 60 Hz, a detection sampling frequency of at least 120 Hz is required. For a detection sampling frequency of 120 Hz, there should be at least 120 "on" periods, and thus 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 changed as needed. In some embodiments, a higher duty cycle (e.g., ≧50%) can be associated with a lower duty cycle frequency, while a lower duty cycle (e.g., ≦50%) can be associated with a higher duty cycle frequency. The duty cycle frequency should be at least twice the detection sampling frequency, and the detection sampling frequency should be at least twice the flapping frequency of the pest to be detected. In an adaptive system, the duty cycle parameters can be changed based on various environmental factors as part of an effort to detect different pests. For example, factors such as location, time of day, season, relative humidity, temperature, etc., may be taken into account when setting the duty cycle, as all of these factors may contribute to the likelihood that a particular type of pest is present. In a static system, the duty cycle can be set and then left unchanged. In such a system, the duty cycle frequency should be set high enough to facilitate detection of pests with high flapping frequencies, such as fruit flies, mosquitoes, and gnats.

[0037] Adjustment of the duty cycle parameters can be done by the user via software (e.g., providing inputs to set the duty cycle or on / off ratio) or hardware (e.g., turning one or more adjustment dials to set the duty cycle parameters). In some embodiments, the duty cycle parameters can be adjusted as described above with respect to environmental factors, but the duty cycle frequency can also be adjusted remotely by the user via software. In some embodiments, the duty cycle parameters can be altered according to location and current pests known to be present at the location, which can be determined, for example, by pulling information from a database maintained by a local environmental service (public or private). Dynamically defining the duty cycle parameters according to the type of pest can increase efficiency.

[0038] The steps shown in Figure 12 explain how information from a detector can be used to determine if pests are present. In step 1200, an analog signal from the detector is monitored. The detectors of the present subject matter are photodiodes that generate an electrical signal (e.g., voltage, current, or both) when they receive light. These photodiodes can be selected specifically for their sensitivity to infrared light. Thus, when the emitter projects infrared light, the detector receives the light and thereby generates a raw analog signal.

[0039] At step 1202, analog signals that are not within the target range are largely removed by hardware frequency filtering, for example using a band pass filter, as described above. Certain frequencies or frequency ranges are blocked because pests typically do not have flapping frequencies within or near those ranges. For example, for moths, whose flapping frequencies range from approximately 50 to 80 Hz, hardware filtering can be set to remove frequencies below 40 Hz and above 100 Hz, while for small insects such as fruit flies and mosquitoes, whose flapping frequencies typically range from 200 to 1200 Hz, a band pass filter can be implemented to remove frequencies below 200 Hz and above 1500 Hz. It may be desirable to keep the frequency in the range from 40 Hz to about 1500 Hz, with all ranges in between being expressly contemplated in this application as feasible in embodiments of the inventive subject matter, whereby the range can be determined based on the flapping frequency of the type of pest to be detected. Once the range of flapping frequencies is known, appropriate filtering can be implemented. While band-pass filtering can be useful, in some embodiments only frequencies below a threshold need to be removed, so any lower limits mentioned above should also be interpreted as disclosure of upper limits for a filter that will remove all frequencies below that value.

[0040] After passing through the hardware filter, the signal is digitized in step 1204. Once the signal is digitized, a multi-step filtering process can be implemented to minimize false positive pest detections while keeping processing costs low. Although these steps are described in sequence, some or all of the steps can be completed in a different order than they are written. First, the analog signal from the detector is sent (e.g., continuously, as it is generated) to an analog-to-digital converter (ADC). The ADC of the present subject matter can have a digitization sampling frequency of, for example, 4 kHz to 10 kHz. In some embodiments, a sampling frequency of about 8 kHz is suitable.

[0041] The digitized signal is then continuously monitored for potential pest signals in step 1206. Two signal amplitude thresholds, high and low, are set to monitor for potential pest signals. For example, it has been found that setting the thresholds at -0.6 and 0.6 is suitable for pest detection when signal amplitudes are normalized to a range of -1 to 1. Amplitude normalization is not required, but normalization makes the system of the present subject matter more robust (e.g., better able to deal with detectors that output different signal amplitudes). In embodiments where normalization does not occur, these thresholds may nevertheless be implemented by performing some basic mathematics depending on the range of amplitudes measured for a given detector or set of detectors (e.g., the maximum amplitude may be associated with 1 and the minimum amplitude may be associated with -1).

[0042] If the digital signal value from the ADC exceeds any threshold value several times within a consecutive digitized block (e.g., the threshold is exceeded 2-3 consecutive times or 2-6 consecutive times in some embodiments), it indicates the presence of a potential pest. Looking for consecutive digital signal values ​​that exceed any threshold value can improve performance by eliminating false positives. Once a digital signal value is observed to exceed any threshold value any required consecutive number of times, some 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 8,192. The number of digital signal values ​​recorded can vary depending on several factors, including the ADC sampling rate. FIG. 13 shows an example recorded signal (in this case for a 1024-long recorded sample) graphed as amplitude versus digital signal block. The graph shows where the digital signal values ​​exceed a normalized amplitude threshold (e.g., + / - 0.6).

[0043] Another way to express how many digital signal values ​​should be recorded is to state the period of time to record. Stating the period of time to record may be more robust, since the number of digital signal values ​​to capture in a certain period of time depends, for example, on the ADC sampling frequency. For example, if the ADC has a sampling rate of about 8 kHz and 1024 digital signal values ​​are recorded, it means that the system is recording an elapsed time of about 0.125 seconds. This can be expressed as follows:

number

[0044] Thus, the elapsed time should be in the range of 0.05 to 0.3 seconds (preferably about 0.125 seconds), but up to 1 to 3 seconds can be recorded without departing from the subject matter of the present invention. These ranges for the elapsed time improve the system's ability to detect pests, since enough time needs to be captured to ensure that a pest is really passing through the detector and that the signal was not simply capturing noise. In particular, any value for the number of digital signal values ​​recorded should be an integer, and a higher ADC sampling rate generally improves 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 ​​recorded should be about 512.

[0045] As a result, if the recorded signal contains consecutive digital signal values ​​that exceed the normalized amplitude threshold, it indicates that pests are present and not just some random electrical noise. Although random electrical noise may exceed the threshold, it is less common for the noise to exceed the threshold for two consecutive samples. Nevertheless, in some cases, the noise may exceed the threshold for multiple consecutive digital signal values. Further filtering can be implemented to remove those types of false positives.

[0046] Thus, in step 1206, the system determines whether the signal in the recorded sample is indicative of a pest or noise. FIG. 14 shows how this can be done using an on-board classifier. The described on-board classifier can be implemented as software, hardware, or some combination of software and hardware. First, the recorded sample is passed to the on-board classifier, which must select which type of classifier to use, for example, based on the expected pest type. The expected pest type can be determined in a variety of ways, including by location, observation, etc. (as discussed above with respect to the duty cycle parameter). This involves feature extraction, followed by model selection. In feature extraction, the system looks at one or more peaks from the recorded signal, calculates characteristics of those peaks, and then calculates statistical results of the peak characteristics. An appropriate model is then applied to determine whether a pest is present. For example, if moths are indicated as possible pests, a model for moths can be used to analyze the features and determine whether to count the moths. The results of this analysis are then stored in memory (e.g., whether pests are counted or noise is ignored, the results are stored) and can be used to improve detection, for example, by machine learning. A determination of whether the signal is indicative of pests or noise is made during step 1208. And once the aforementioned results are stored in memory, the number of detected pests can be counted according to step 810. If there are any redundant counts, those redundant amounts can be removed according to step 812, although this step is optional since the redundant amounts can be removed through the process of determining the presence of pests as described above and in additional detail below.

[0047] Classification therefore involves feature extraction as previously described, which is calculated in the time domain. In some embodiments, the objective of classification is to identify all peaks in the signal that exceed an upper limit for the normalized amplitude, and then combine consecutive peaks whose troughs between them do not exceed a lower limit. From there, peak characteristics are calculated, which involves determining the peak width. Peak width can describe the distance along the x-axis between the previous and next valleys of a particular peak, with units along the x-axis representing discrete digital signal values. Height is also calculated, with the height measured according to the signal amplitude (e.g., normalized between -1 and 1), and the height relative to the peak measured as units along the y-axis between the trough and the peak being analyzed. Figure 15 shows how width and height are measured. Finally, sharpness can be calculated, which is the height of the peak divided by its width.

[0048] The subject system of the present invention can thus be configured to calculate the total number of peaks in the 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, for example as a training set to improve classification. Figure 16 shows an example signal in which different peaks are recorded, as well as the maximum sharpness, average sharpness, average height, average width, and peak threshold. In this figure, the amplitudes are not normalized to fall within the range of -1 to 1.

[0049] FIG. 17 shows a system schematic, the system shown configured to perform all or part of the steps described above and shown in FIG. 12. All the details above are also relevant here. The analog sensor describes the pulse width modulated IR detector described above. The signal from that sensor is converted from analog to digital using, for example, an ADC sampling at 8 kHz. From there, a comparator (e.g., ADS1115) monitors for consecutive digital signal blocks that exceed an amplitude threshold. If no consecutive digital signal values ​​are detected, monitoring continues. If several consecutive digital signal values ​​exceed an amplitude threshold (e.g., between 2 and 6, inclusive), the system wakes up to receive 1024 recorded digital signal values, also referred to as "samples" in FIG. 17. Time, temperature, and relative humidity can then be recorded, and an on-board classifier is then used to determine if the recorded digital signal values ​​are indicative of a pest. Humidity, time, and temperature can all be used to improve detection and can be stored with other data, for example to aid machine learning. When pests are found, the information is stored in a pest storage device, and when noise is found, the information is stored in a noise storage device. Both the pest storage device and the noise storage device can be stored on any type of computer readable medium, either locally or remotely via a network connection.

[0050] Thus, a particular system and method directed to pest detection has been disclosed. However, it should be apparent to one skilled in the art that many more modifications besides those already described are possible without departing from the inventive concept herein. The subject matter of the present invention is therefore not limited except in the spirit of the present disclosure. Moreover, all terms in interpreting this disclosure should be interpreted as broadly as possible consistent with the context. In particular, the terms "comprise" and "comprising" should be interpreted to refer to elements, components, or steps in a non-exclusive manner, indicating that the referred element, component, or step may be present or utilized 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; a second PCB portion; at least one emitter disposed on the first PCB portion; at least one detector disposed on the second PCB portion; a pulse width modulation controller configured to drive at least one of the at least one emitter and the at least one detector; A system comprising: a space exists between the first PCB portion and the second PCB portion; the at least one emitter is oriented to face the at least one detector; the at least one detector is oriented to face the at least one emitter; the first PCB portion and the second PCB portion are part of a single PCB; The system, wherein the single PCB is V-shaped having a first arm and a second arm, the first arm comprising the first PCB portion and the second arm comprising the second PCB portion.

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

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

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

5. The system of claim 3 , wherein the at least one emitter is configured to project infrared light having a wavelength between 700 nm and 1,400 nm.

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

7. The system of claim 5 , wherein the at least one detector is configured to detect infrared light having a wavelength between 700 nm and 1,400 nm.

8. A pest detection system, comprising: a first printed circuit board (PCB) portion; a second PCB portion; a wide angle emitter disposed on the first PCB portion; a set of detectors disposed on the second PCB portion; a pulse width modulation controller configured to drive the wide angle emitter and the detector; A system comprising: a space exists between the first PCB portion and the second PCB portion; the wide-angle emitter is oriented to face the set of detectors; A system wherein each detector in the set of detectors is oriented to face the wide-angle emitter.

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

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

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

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

13. 13. The system of claim 12, wherein the wide-angle emitter is configured to project infrared light having a wavelength between 700 nm and 1,400 nm.

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

15. The system of claim 13 , wherein each detector in the set of detectors is configured to detect infrared light having a wavelength between 700 nm and 1,400 nm.

16. A pest detection system comprising: a first printed circuit board (PCB) portion; a second PCB portion; at least one emitter disposed on the first PCB portion; at least one detector disposed on the second PCB portion; a pulse width modulation controller configured to drive at least one of the at least one emitter and the at least one detector; A system comprising: a space exists between the first PCB portion and the second PCB portion; the at least one emitter is oriented to face the at least one detector; the at least one detector is oriented to face the at least one emitter; The system, wherein the at least one detector is configured to detect infrared light.

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

18. The system described in claim 17, wherein the single PCB is V-shaped having a first arm and a second arm, the first arm comprising the first PCB portion, and the second arm comprising the second PCB portion.

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

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

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

22. The system described in claim 16, wherein the at least one emitter is configured to project infrared light.

23. The system described in claim 22, wherein the at least one emitter is configured to project infrared light having a wavelength between 700 nm and 1,400 nm.

24. The system described in claim 22, wherein the at least one detector is configured to detect infrared light having a wavelength between 700 nm and 1,400 nm.

25. A pest detection system comprising: a first printed circuit board (PCB) portion; a second PCB portion; at least one emitter disposed on the first PCB portion; at least one detector disposed on the second PCB portion; a pulse width modulation controller configured to drive at least one of the at least one emitter and the at least one detector; A system comprising: a space exists between the first PCB portion and the second PCB portion; the at least one emitter is oriented to face the at least one detector; the at least one detector is oriented to face the at least one emitter; the first PCB portion and the second PCB portion are part of a single PCB; The system, wherein the single PCB is annular having a first side and a second side, the first side comprising the first PCB portion and the second side comprising the second PCB portion.

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

27. The system described in claim 26, wherein the at least one emitter is configured to project infrared light having a wavelength between 700 nm and 1,400 nm.

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

29. The system described in claim 25, wherein the at least one emitter is configured to project infrared light.

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

31. The system described in claim 29, wherein the at least one detector is configured to detect infrared light having a wavelength between 700 nm and 1,400 nm.

Images