AU2020103211A4 - Machine learning based rodent detection and control device - Google Patents

Abstract

"MACHINE LEARNING BASED RODENT DETECTION AND CONTROL DEVICE " Exemplary aspects of the present disclosure are directed towards the Machine Learning Based Rodent Detection and Control Device, consisting of a LASER MAPPING DEVICE (LMD) 101 capable of mapping planner surface in three dimension (3-D), RODENT MONITORING DEVICE (RMD) 102 capable of detecting rodents based on thermal signatures and Seismic Signals, and Plurality of RODENT CONTROL DEVICE (RCD) 103 capable of driving away the rodent by playing higher order prey's Bio- Acoustic sound and Seismic signal. Microcontroller 101a integrated with LMD 101, RMD 102 and RCD 103 executes relevant machine learning algorithms (MLA) for detecting rodents in a farm field based on rodent's seismic activities, thermal and video images and generates Acoustic and Seismic signal to thrive away the rodents. The higher order pray acoustic and seismic signals are mimicked and played so as to scare the rodent. 1/5 101 103 102 FIG I 100 MACHINE LEARNING BASED RODENT DETECTION AND CONTROL DEVISE

Description

1/5

101

103 102

FIG I 100 MACHINE LEARNING BASED RODENT DETECTION AND CONTROL DEVISE

I TITLE

Machine Leaming-Based Rodent Detection And Control Device

PREAMBLE TO THE DESCRIPTION

The following specification particularly describes the invention and the manner in which it is to be performed.

DESCRIPTION TECHNICAL FIELD

[0001] The present disclosure generally relates to the rodent/pest detection in a farm field by employing LiDAR technology in conjunction with Seismic's Sensor and Thermal Imaging. Further, Rodent/pest classification and selection of appropriate prey for scaring away the rodent/pest is carried out by executing relevant machine learning algorithms. Performing Seismic vibration and Bio-Acoustic sounds of higher-order prey to scare the pest.

BACKGROUND

[0002] In the Process of Atomation of agriculture rodent or animal detection and restraing them plays a major role in increasing yield of the crop. Farmers square-off the rodents and animals by adopting seveal lethal and non lethal measures which might be an alarm system or by using chemicals. Most of the time these methods prove inneftive as the identification of rodents are done at last stage of crop distruction.

[0003] Though sevral alarm systems and mechanism are in place, avaerting rodents and animals is a big challenge. The alarming system might give some sounds either to alert the farmer or to restrain the rodent or aniamls. But this system on long usage makes the rodent or animal to adapt the sounds of alarm and wont show further results on it.

[0004] Numerous prior arts have made attempts to automate the farm fence with numerus proto typing but haven't achived more desirable feature in a single unit for the farmers.

Z

[0005] Similarly, several prior art disclosures have ascertained best devices and practices for rotent detection using several means such as electric fence, laser fence, vibration sensor fence, IR fence, Combinational light fence, camera based fence and so on.

[0006] Articles in the prior art by Bridget A. Matikainen-Ankney et al in their article Rodent Activity Detector (RAD), an Open Source Device for Measuring Activity in Rodent Home Cages discussed PIR sensors and how it detects when warm moving objects (such as an animal) cross its sensing zone. By mapping the area of activation using an infrared LED, they determined that in Allentown NextGen wire rack home cages with RAD placed above the wire rack, RAD tracks activity in -30% of the cage surface area.

[0007] In the prior art CN108399696A, with title Intrusion behavior recognition methods and device, described about the invention which alleviates conventional machines study identification intrusion behavior technical problem of high cost and poor for applicability. Invention includes : Obtain time series signal, wherein time series signal is sequence signal made of the tested amplitude for enclosing boundary's vibration arranges at any time ; Characteristic quantity is extracted from time series signal, wherein characteristic quantity includes : The maximum value of the tested peak swing for enclosing boundary's vibration, energy, spectrum energy breadth coefficient, energy gradient and energy gradient gradient ; Intrusion behavior identification is carried out using characteristic quantity as the input quantity of machine learning algorithm, to determine the tested intrusion behavior type for enclosing boundary by the output quantity of machine learning algorithm.

[0008] Another Prior art RU2013125902/08A- explained invention relates to means of detecting an intruder of extended security boundaries. The technical result is faster and more accurate determination of the area of intrusion. The system consists of a central security post and a plurality of electronic units, each connected to a group of signal processors. Each signal processor is connected to a segmented vibration-sensitive element mounted on a physical enclosure. The electronic units are connected to the central security post by a first RS-485 interface line. The signal processors are connected to corresponding electronic units by other CAN interface lines.

[0009] Similar prior art US5969608A - invention discloses an intrusion detector which has buried sensor modules arranged along a perimetero sense seismic vibrations caused by intrusions within the area defined by the perimeter. The sensor modules transmit data representative of the intrusions via magneto-inductive signals in the ELF to VLF range through ground, air, and/or water to at least one buried relay module within the area. The relay modules transmit RF signals representative of the intrusion data via a camouflaged RF antenna to mobil or fixed stations for appropriate action. Transmission of magneto-inductive signals in the ELF to VLF range is clandestine and reliable, and locations of buried sensor modules and relay modules are not revealed to intruders to reduce the possibility of evasion or tampering. The sensor modules may have sensor elements sensitive to humans, vehicles, and low flying aircraft to give enforcement officers the opportunity to better utilize their resources where the intrusions are occurring.

[0010] In Prior art W02018085949A1 with title Vibration-analysis system and method therefor emphasized on vibration/seismic survey, vibration monitoring, and the like. Invention contains vibration-detection unit may have a vibration-detection sensor and a positioning module for automatically determining the position thereof. The vibration-detection units may be geophones and the system may have a signal process module for compensating for the distortion introduced by the geophones.

[0011] US8705017B2 discloses a system for tracking airborne organisms includes an imager, a backlight source (such as a retroreflective surface) in view of the imager, and a processor configured to analyze one or more images captured by the processor to identify a biological property of an organism.

[0012] An prior art document EP2318804B1 discloses system for detecting intrusion, said system comprising: an illumination source projecting an array of illuminating beams distinguished by beam identifying features, along different optical paths; a detector array comprising elements detecting reflected illumination received in an array of fields of view, said reflected illumination originating from said array of illuminating beams, and said elements using said beam identifying features to determine from which of said illuminating beams said reflected illumination originates; and a signal processing system adapted to detect changes in the reflected illumination levels detected by said elements of said detector array, wherein an increase greater than a first predefined level in said reflected illumination from the field of view associated with an element, provides an indication of an intrusion at the crossing point of that field of view associated with said element, with that optical path whose illuminating beam generates said increase in reflected illumination detected by said element, said optical path being defined by said beam identifying feature of said reflected illumination detected

[0013] Another prior art document WO 2004/008403 describes a laser based range finder for use with cameras of an intrusion detecting system.

[0014] Another prior art document US 4065778 shows a focussing apparatus for a camera where the distance to an object is measured via the intersection of a light beam with the camera's field of view.

[0015] Referring to another document, US 20080222942A1 discloses A method of detecting and exterminating rodents can include collecting geographical data of underground rodent tunnels and nests within a defined geographical region. Additionally, the method can include processing the geographical data, and presenting the data in a form Sufficient to allow an operator to identify a location of the underground rodent tunnels and nests. A method of detecting and exterminating rodents also can include exterminating rodents dwelling in the under round tunnels and nests. A system of detecting and exterminating rodents includes a Substantially above-ground Surveyor which can generate data of underground rodent tunnels and nests, and a data processor which can receive, store, interpret and present the data generated by the Surveyor.

[0016] US20150369591A1 document titled Optical detection systems and methods of using the same where the invention invention relates generally to the field of optical detection systems and, more particularly, to improved systems and methods for accurately detecting presence in, and/or interference with, an area to be monitored using fiber optics.

[0017] JP5263692B2, presented an invention relates to a laser scan sensor that detects, for example, an intruder into a building site, and in particular, after a warning area is set, a new harmless obstacle is installed in the warning area or a car or the like enters. The present invention relates to a laser scan sensor capable of accurately detecting an intruder that should be detected regardless of the presence of the intruder even when the vehicle is parked.

[0018] In an eraly document by Caitlin E O'Connell-Rodwell Et al in thieir publication titled Vibrational Communication in Elephants: A Case for Bone Conduction presented physiological data on bone conduction hearing from cadaveric temporal bone ears of an elephant. They discuss the results in the context of the elephant's ability to detect and interpret ground-bome vibrations as signals and compare with similar measurements in a human cadaveric temporal bone ear. Since elephant ossicles are at least seven times the mass of human ossicles, they compared the sensitivity of both species to vibrations in the frequency range of 8 ,000 Hz and report that elephants have up to an order of magnitude greater sensitivity below 200 Hz, indicating a heightened sensitivity to bone conduction hearing in comparison to humans.

[0019] In a prior document by Peggy S. M. Hill discussed about How do animals use substrate-bome vibrations as an information source?. Stated that, alongside visual signals, songs, or pheromones exists another major communication channel that has been rather neglected until recent decades: substrate-borne vibration. Vibrations carried in the substrate are considered to provide a very old and apparently ubiquitous communication channel that is used alone or in combination with other information channels in multimodal signaling. The substrate could be 'the ground', or a plant leaf or stem, or the surface of water, or a spider's web, or a honeybee's honeycomb. Animals moving on these substrates typically create incidental vibrations that can alert others to their presence. They also may use behaviors to create vibrational waves that are employed in the contexts of mate location and identification, courtship and mating, maternal care and sibling interactions, predation, predator avoidance, foraging, and general recruitment of family members to work. In fact, animals use substrate-bome vibrations to signal in the same contexts that they use vision, hearing, touch, taste, or smell.

[0020] In an invention stated in document CN107527009A, the invention discloses a kind of remnant object detection method based on YOLO target detections, is related to intelligent monitoring, computer vision, deep learning field. The present invention is detected in real-time by YOLO targets, obtains the target classification in every frame image data, and specific coordinate corresponding to it. The non-object target, such as row humans and animals, has accurately been filtered by target classification, has greatly reduced the interference judged follow-up legacy.

[0021] The present invention provides an effective rodent and animal detection and restaining system based on a mixture of Light, Image processing Vibration, and bioacoustics.

[0022] The present invention addresses the shortcomings mentioned above of the prior art.

[0023] All publications herein are incorporated by reference to the same extent as if each publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies, and the definition of that term in the reference does not apply.

SUMMARY

[0024] The following presents a simplified summary of the disclosure in order to provide a basic understanding of the reader. This summary is not an extensive overview of the disclosure, and it does not identify key/critical elements of the invention or delineate the scope of the invention. Its sole purpose is to present some concepts disclosed herein in a simplified form as a prelude to the more detailed description that is presented later.

[0025] Exemplary embodiments of the present disclosure are directed towards the Machine Leaming-Based Rodent Detection And Control Device.

[0026] An exemplary object of the present disclosure is directed towards a system that monitors and restrain the intruding rodents and animals.

[0027] Another exemplary object of the present disclosure is directed towards the integration of microcontroller 102a with geophone 102d to make RODENT MONITORING DEVICE (RMD) 102. Whose primary function is to monitor intruding rodents and animals by identifying their seismic vibrations.

[0028] Another exemplary object of the present disclosure is directed towards the integration of microcontroller 102a with thermal camera 102b and camera 102c for detecting an intruding object by using an image detection algorithm and thermal imaging algorithm.

[0029] An exemplary aspect of the present subject matter is directed towards the integration of microcontroller 102a with camera 103b for transmitting video between Microcontroller 102a and Advanced Microcontroller 101a for detecting intruding animal or rodent.

[0030] An exemplary aspect of the present subject matter is directed towards the use of Microcontroller 102a for detecting intruding animals or rodents using a Machine Learning based Image recognition algorithm and execute an appropriate averting command.

[0031] An exemplary aspect of the present subject matter is directed towards the implementation of mechanical vibrator 103c, which exerts seismic vibrations of specific predator determined by microcontroller 102a.

[0032] Another exemplary aspect of the present disclosure is directed towards playback the bio-acoustic sounds of the corresponding predator through Audio-speaker 103b by Advanced microcontroller 101a.

[0033] Another exemplary aspect of the present disclosure is directed towards the activation of the strobe light and hooter by microcontroller 102a for averting intrusion.

[0034] Another exemplary aspect of the present disclosure directed towards the integration of LiDAR 3600 with microcontroller 101a for 3-Dimensional mapping of the surface and detect the unidentified objects.

[0035] Another exemplary aspect of the present disclosure directed towards intimation of the intruder by microcontroller 101a to the user about the intrusion.

BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In the following, numerous specific details are set forth to provide a thorough description of various embodiments. Certain embodiments may be practised without these specific details or with some variations in detail. In some instances, certain features are described in less detail so as not to obscure other aspects. The level of detail associated with each of the elements or features should not be construed to qualify the novelty or importance of one feature over the others.

[0037] FIG.1 is a diagram depicting 100 Machine Learning-Based Rodent Detection And Control Device, according to an exemplary embodiment of the present disclosure.

[0038] FIG. 2 is a representation 101 Laser Mapping Device (LMD), according to an exemplary embodiment of the present disclosure.

[0039] FIG. 3 is a representation 102 Component Architecture Of Rodent Monitoring Device (RMD), according to an exemplary embodiment of the present disclosure.

[0040] FIG. 4 is a representation 103 Component Architecture Of Rodent Control Device (RCD), according to an exemplary embodiment of the present disclosure.

[0041] FIG. 5 is a diagram 500 Process Executed In Rodent Detection And Control Device, according to an exemplary embodiment of the present disclosure.

DETAILED DESCRIPTION OF EXAMPLE EMBODIMENTS

[0042] It is to be understood that the present disclosure is not limited in its application to the details of construction and the arrangement of components outlined in the following description or illustrated in the drawings. The present disclosure is capable of other embodiments and of being practised or of being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting.

[0043] The use of "including," "comprising," or "having" and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. The terms "a" and "an" herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced item. Further, the use of terms "first," "second," and "third," and the like, herein do not denote any order, quantity, or importance, but rather are used to distinguish one element from another.

[0044] Referring to FIG. 1 is a diagram depicting the 100 Machine Leaming-Based Rodent Detection And Control Device consisting of LASER MAPPING DEVICE (LMD) 101 capable of mapping planner surface in three-dimension (3-D), RODENT MONITORING DEVICE (RMD) 102 capable of detecting rodents based on thermal signatures and Seismic Signals, and Plurality of RODENT CONTROL DEVICE (RCD) 103 capable of driving away from the rodent by playing higher-order prey's BioAcoustic sound and Seismic signal. LASER

MAPPING DEVICE (LMD) 101 is mounted on a centre post in its singular position. Whereas RODENT MONITORING DEVICE (RMD) 102 and RODENT CONTROL DEVICE (RCD) 103 combined and placed in a single unit controlled by a microcontroller 102a. The plurality of RMD 102 and RCD 103 is placed in the area to be protected.

[0045] Further to it, all these devices communicate with each other in WiFi Mesh network. Wherein WiFi mesh network once established between all the devices then the necessity of router or special signalling devices is eliminated. LMD 101 traces the surface anomaly and alerts the concerned Rodent Monitoring Device (RMD) 102 through a WiFi mesh network. Which in turn senses the seismic vibrations and activates the cameras 101b and 101c to get visual and thermal confirmation of the rodent. This information is sent back to LMD101 so that it would communicate the intrusion information to the user.

[0046] In accordance with a non-limiting exemplary embodiment of the present subject matter, FIG. 2 is a depiction of LASER MAPPING DEVICE (LMD) 101 capable of mapping planner surface in three-dimension (3-D). It consists of a state of art microcontroller 101a integrated with advanced 3600 Light Detection and Ranging (LiDAR) device 101b. Microcontroller 101a capable of executing relevant machine learning algorithm to determine the changes in the planner surface. The planner surface may be a farm field or an area where the intrusion is to be averted.

[0047] Further to it, microcontroller 101a is integrated with General Packet Radio Service (GPRS) module 101c to enable it to communicate with the user interface. Whenever a rodent is identified or an intrusion is detected, microcontroller 10la through GPRS module 101c intimates the user about the intrusion and type of intruder and status of averting it. Microcontroller 101a is integrated with WiFi dongle to enable it to create a WiFi mesh network and communicate with other devices. When an anomaly in planner surface mapping is found, using a WiFi mesh network, microcontroller 101a alerts the relevant RMD 102 which is near to the anomaly. It receives the information from RMD 102 about the rodent classification, averting measures taken and status of averting the rodent. All the information thus received is sent to the user through the GPRS module 101c.

[0048] Referring to FIG 3 is a diagram depicting Component Architecture Of Rodent Monitoring Device (RMD) 102. Microcontroller 102a integrates RMD 102 and RCD 103. The RMD 102 is an integration of Microcontroller 102a with thermal camera 102b, video camera

1U

102c and a geophone 102d. Once the Microcontroller 102a receives a signal from LMD 101, it activates geophones to sense the seismic activities. If any activity is present, then it triggers the camera modules 102b and 102c to retrieve pictorial and thermal imagiging. Microcontroller 102a is capable of executing machine learning algorithm (MLA) to predict the intruder based on the seismic index, heat signature and image processing. Once an intruder is identified, the information is fed back to LMD 101 through WiFi Mesh network.

[0049] In accordance with a non-limiting exemplary embodiment of the present subject matter, FIG. 4 depicting the Component Architecture Of Rodent Control Device (RCD) 103. The microcontroller 102a is integrated with flash/ strobe light 103a, Audio speaker 103b and a mechanical vibrator. Primarily this part of the invention is intended to hustle the intruding rodent or animal from the farmland. The first part of intrusion averment is by activating hutter sound through audio speaker 103b and flashing strobe light 103a. In general most of the intruding rodents/ animals get scared off the hooter sound and strobe light, but some rodents such as wild boras are adaptive in nature and thereby this technique won't work well in a long duration.

[0050] Further to it, if RMD 102 identifies that the rodent intrusion hasn't averted, then the microcontroller 102a activates micro vibrators and plays bioacoustic sounds relevant to a pray which is in higher-order to that specific rodent or animal. It is worthwhile to note that, seismic vibrations are generated by rodent or animal which are unique to their kind. With this seismic activity, they communicate and also predict the type of threat around them. Bioacoustic sounds are the sounds liberated from the vocal cords of the animals for communication. These two aspects of the pray hustle away the rodent or animal intruding the farm field.

[0051] Following is a non-limiting exemplary embodiment of the present subject matter, as shown in FIG. 5, which is a 500 Process Executed In Rodent Detection And Control Device. The process starts at step 501, microcontroller 101a acquire geospatial 3-D mapping of the field through LiDAR 101b. When a change in 3-D planner surface mapping is observed by the microcontroller 101a, it sends the alert to RMD 102. In step 502, microcontroller 102a acquire Seismic Vibrations from Geophone 102d of RODENT MONITORING DEVICE (RMD) 102. Step 503, microcontroller 102a execute Machine Learning Algorithm-i (MLA-1) to Compare the geospatial 3-D Images and Seismic values with stored values and if there is a discrepancy then signal RODENT MONITORING DEVICE (RMD) 102 to wake the Thermal camera 102b and camera-module 102c.

[0052] Further in step 504, microcontroller 102a of RODENT MONITORING DEVICE (RMD) 102 Acquire the video feeds and Execute Machine Learning Algorithm-2 (MLA-2) to detect rodent based on the thermal signature and normal image. In subsequent step 505, microcontroller 102a Execute Machine Learning Algorithm-3 (MLA-3) to classify rodent based on the seismic, thermal signature and normal image. Also, select pray for the pest/rodent/animal and its seismic and bioacoustic values. In step 506, microcontroller 102a initiate to play flash/strobe light 103a and Hooter sound through audio speaker 103b in RODENT CONTROL DEVICE (RCD). Step 507, microcontroller 102a check for seismic activity and thermal signature after playing flash and hooter and confirm the presence of rodent/pest. If any seismic or thermal signatures persist then in step 508, microcontroller 102a signal the mechanical vibrator to generate seismic tremors/vibrators 103c and simultaneously play bioacoustic sound mimicking higher-order pray through 103b. If assumed mice entered the farm field then a cat profile is selected and accordingly its seismic vibration is generated and as well its bioacoustics sounds are played.

[0053] Subsequently in step 509, microcontroller 102a check for seismic activity, thermal signatures and geospatial data and confirm the presence of intruding rodent/pest. If rodent presence is persisting, in step 510, microcontroller 102a Repeat the process till the rodent/ animal is restrained from entering the protected zone and inform the user through GPRS 101c connected to microcontroller 101a.

Claims (5)

EDITORIAL NOTE 2020103211 There is one page of claims only STATEMENT OF CLAIMS We Claim,

1. The Machine Learning-Based Rodent Detection and Control Device, consisting of a LASER MAPPING DEVICE (LMD) 101 capable of mapping planner surface in three dimension (3-D); and a RODENT MONITORING DEVICE (RMD) 102 capable of detecting rodents based on thermal signatures and Seismic Signals; and A plurality of RODENT CONTROL DEVICE (RCD) 103 capable of hurling away the rodent by playing hooter sounds and flashing strobe light; and A plurality of RODENT CONTROL DEVICE (RCD) 103 capable of hurling away the rodent by playing higher order prey's Bio- Acoustic sound and Seismic signal.

2. The device as claimed in claim 1, Wherein LASER MAPPING DEVICE (LMD) 101 is an integration of Microcontroller 101a with LiDAR 101b which effectively maps the geospatial data to time domine. The microcontroller 101a executes relevant machine learning algorithm on geospatial data and ascertains an intrusion.

3. The device as claimed in claim 1, Wherein RODENT MONITORING DEVICE (RMD) 102 is an integration of Microcontroller 102a with thermal camera 102b and geophone 103c. When received an awake signal from microcontroller 101a, Microcontroller 102a acquires data from thermal camera 102b and geophone 103c and executes a relevant machine-learning algorithm to ascertain exactly about the type of rodent/animal.

4. The device as claimed in claim 1, LMD 101, RMD 102 and RCD 103 executes relevant machine learning algorithms (MLA) for detecting rodents in a farm field based on rodent's seismic activities, thermal and video images and select a higer order pray of that intruder to generates Bio-Acoustic sounds and Seismic signal of a pray to thrive away the rodents.

5. The device as claimed in claim 1, RCD 103 plays bio-acoustic sounds and seismic signals which are mimicked as of higher order pray so as to scare the rodent.