Sign In to Follow Application
View All Documents & Correspondence

Image Sensing Animal Repellent Cum Security System For Crop Protection

Abstract: An automated system employs a deep learning (CNN) model trained on diverse datasets and transferred to a Nano Jetson for field deployment for future proofing. Cameras to monitor agriculture lands for monkey intrusion, processing images via API for object detection. Detected monkeys trigger a large hooter to deter them while automated SMS alerts notify stakeholders over the users. This integrated approach offers real-time monitoring and swift response, mitigating human-monkey conflicts and safeguarding agricultural interests. The system fosters harmonious coexistence by proactively addressing threats and promoting timely intervention, enhancing community safety and property protection. The system as claimed in claim 1, wherein, provide an automated system employs a deep learning (CNN) model trained on diverse datasets and transferred to a Nano Jetson for field deployment for future proofing. Cameras to monitor agriculture lands for monkey intrusion, processing images via API for object detection. Detected monkeys trigger a large hooter to deter them while automated SMS alerts notify stakeholders over the users.

Get Free WhatsApp Updates!
Notices, Deadlines & Correspondence

Patent Information

Application #
Filing Date
17 June 2024
Publication Number
27/2024
Publication Type
INA
Invention Field
COMPUTER SCIENCE
Status
Email
Parent Application

Applicants

UTTARANCHAL UNIVERSITY
ARCADIA GRANT, P.O. CHANDANWARI, PREMNAGAR, DEHRADUN - 248007, UTTARAKHAND, INDIA

Inventors

1. RAJESH SINGH
DIVISION OF RESEARCH AND INNOVATION, ARCADIA GRANT, P.O. CHANDANWARI, PREMNAGAR, DEHRADUN - 248007, UTTARAKHAND, INDIA
2. ANITA GEHLOT
DIVISION OF RESEARCH AND INNOVATION, ARCADIA GRANT, P.O. CHANDANWARI, PREMNAGAR, DEHRADUN - 248007, UTTARAKHAND, INDIA
3. SIDDHARTH SWAMI
DIVISION OF RESEARCH AND INNOVATION, ARCADIA GRANT, P.O. CHANDANWARI, PREMNAGAR, DEHRADUN - 248007, UTTARAKHAND, INDIA
4. MANISH NEGI
DIVISION OF RESEARCH AND INNOVATION, ARCADIA GRANT, P.O. CHANDANWARI, PREMNAGAR, DEHRADUN - 248007, UTTARAKHAND, INDIA
5. NIKHIL BISHT
DIVISION OF RESEARCH AND INNOVATION, ARCADIA GRANT, P.O. CHANDANWARI, PREMNAGAR, DEHRADUN - 248007, UTTARAKHAND, INDIA

Specification

Description:Field of the Invention
This invention relates to Image sensing Animal Repellent cum Security System for Crop Protection
Background of the Invention
Agriculture engages 50% of the population and contributes to GDP about 18-19%. However, wildlife intrusion into agricultural fields can pose a serious threat to crops and also to their lives In regions such as Uttarakhand, which has different geographical features and close association with forests, this problem becomes more pronounce. Among wildlife, monkeys alone are responsible for approximately 20-30% of crop damage in the regions of Uttarakhand and also some incident where monkeys were poisoned to prevent crop damage, shows the need for effective, humane solutions to this problem. The "Image Sensing Animal Repellent cum Security System with Alarm and Alert" works on such issues and deliver an effective, automated monitoring and animal repellent system. By the usage of advanced and emerging technologies such as deep learning and wireless sensor networks, this system can detect animals, activate the appropriate repellent system such as the hooter, and thus prevent crop damage and minimize human-wildlife animal conflict. The impact of this project lies in its potential to safeguard agricultural crops and animal lives, ensuring a prosperous and peaceful coexistence.
KR100882890B1
The present invention relates to a monitoring system and a monitoring method for detecting an intruder. To this end, in the present invention, the image capturing apparatus captures an image of a predetermined region, detects information about a person reflected on the image based on the image captured by the human detecting apparatus, and the wireless terminal apparatus is held and transported by a person. The wireless receiving apparatus receives a signal transmitted by radio from a wireless terminal apparatus existing in a predetermined area, the terminal detecting apparatus detects information on the wireless terminal apparatus based on the received signal, and the intruder determination apparatus detects the signal. The information on the intruder is detected based on the information about the person and the information detected about the wireless terminal device.
RESEARCH GAP:
• The system’s continuous monitoring capabilities allow for the collection of valuable data on monkey activity patterns. This data can be used to improve future iterations of the system and inform broader wildlife management strategies.
• Automated detection and repellent activation relieve farmers from constant vigilance, reducing stress and allowing them to focus on other agricultural tasks.
CN115131855A The application discloses a face recognition method for an electronic fence, which is characterized in that a moving target is confirmed through a multi-target motion detection technology, the moving target is subjected to face recognition scanning, the moving target with face features is screened out to generate a face feature record table, and a person who repeatedly comes and goes or stays for too long time is analyzed and judged to be a suspected object with invasion intention according to the face feature record table. The application discloses a face identification system for fence completes the shooting to the scene through the surveillance camera head, accomplishes the demonstration to the shooting image through display module, accomplishes the analysis confirmation to many times round personnel and long-term detention personnel through the analysis processing module to this confirms the suspect who has the invasion intention, has avoided the artificial consumption of manual monitoring, and avoided the omission problem among the manual monitoring process, has promoted the security that fence used.
RESEARCH GAP:
• By providing a systematic approach to monitoring and repelling monkeys, the invention contributes to better overall wildlife management. It helps balance the needs of human populations with the conservation of wildlife.
• The system can be scaled to cover large agricultural areas by installing additional external cameras and adding them into a single integrated monitoring network system thus enabling it for extensive surveillance without compromising performance.
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to Image sensing Animal Repellent cum Security System for Crop Protection.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
To minimize human-wildlife conflict such as damage to crops and threats to both humans and wildlife, an advanced security invention has been developed to help stakeholders such as farmers, security personnel etc to detect the presence of animals without causing them physical harm.
The process of training this invention how to tell the difference between monkeys and non-monkeys began by defining two classes: “monkey” and “not_Monkey.” . 7558 diverse images in the dataset were annotated manually with bounding boxes and polygon tools for accuracy. This then annotated dataset was distributed into training, validation, and test sets with strict quality control to ensure uniformity and precision. 5575 images constituted the training set, while that of validation included 1407 images, and testing one had 576 images
A comprehensive health check was done to ascertain data quality as well as balance where heat maps were generated in order to visualize density and distribution of annotation. Preprocessing steps were resizing images to a dimension of 240x240 pixels, normalization of pixel values, as well as auto orientation. Data augmentation using horizontal flips and rotations enhanced the size of the dataset up to 15,850 which increases the invention’s resilience.
The invention was trained using an automated machine learning solution with transfer learning from a public checkpoint, which initialized it with pre-trained weights. The training process, which took 5 hours, involved real-time tracking of evaluation metrics such as mean Average Precision (mAP), precision, and recall.
Deployment of the invention on an NVIDIA Jetson Nano allowed for efficient localized processing. The integration utilized an API key, project ID, and model version, enabling real-time detection and activation of repellent systems when monkeys were identified. This approach ensured the invention's practical application in real-world scenarios.
Initially, cameras are usually placed at the monitoring space such as agriculture land where monkey are creating damage to the fields. The camera being eye of the project send the visuals which are processed further. Camera captures high quality of the images after every 5 sec technically speaking the camera provides the input to the system.
The captured images are then processed using the Roboflow API for object detection. The Roboflow API enables to make use of the trained model. The model identifies targeted objects within the images, particularly focusing on detecting the presence of monkey. This stage is important for accurate identification and localization of potential threats.
Subsequently, the detection results, includes any identified monkeys and their position, are displayed in real-time on a connected screen. This visual feedback enables continuous monitoring and validation of the detection process by users, facilitating prompt response to detected threats.
Activate Repellent System (Large Hooter) if Monkey Detected:
Upon detecting a monkey within the monitored area, the system triggers the activation of the repellent system. Specifically, a large hooter plays a loud sound of different animals like dog, lion aimed at scaring, startling and deterring the detected monkeys. This immediate response serves as a deterrent, discouraging monkeys from further intrusion or causing harm.
Report Threats via SMS:
In parallel with activating the repellent system, the system sends automated SMS notifications i.e. “Alert: Monkey detected! Generating Sound......" to stakeholders such as farmers and security personnel via Twilio Rest API. Such notifications alerts individuals or authorities about the detected monkey or monkeys in the agricultural land and thus allowing an immediate action to deal with the situations and prevent potential conflicts or damage of the agriculture land and also lives of the animal.
To conclude, the automated detection and repellent system for monkeys is efficient in curbing conflicts between human beings and monkeys. By combining image capturing, object recognizing via Roboflow API alongside rapid response mechanism, this system takes a proactive approach to managing monkey activity within human inhabited areas. Therefore, more research should be conducted on such systems in order to ensure that they not only help humans but also conserve the welfare of monkeys. Moreover, Twilio communication service sends short message alerts (SMS) to farmers or security personnel who may be programmed into the device before hand.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: PROCESS FLOW
FIGURE 2: COMPLETE FLOW OF THE PROCESS
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
To minimize human-wildlife conflict such as damage to crops and threats to both humans and wildlife, an advanced security invention has been developed to help stakeholders such as farmers, security personnel etc. to detect the presence of animals without causing them physical harm.
The process of training this invention how to tell the difference between monkeys and non-monkeys began by defining two classes: “monkey” and “not_Monkey.” . 7558 diverse images in the dataset were annotated manually with bounding boxes and polygon tools for accuracy. This then annotated dataset was distributed into training, validation, and test sets with strict quality control to ensure uniformity and precision. 5575 images constituted the training set, while that of validation included 1407 images, and testing one had 576 images
A comprehensive health check was done to ascertain data quality as well as balance where heat maps were generated in order to visualize density and distribution of annotation. Preprocessing steps were resizing images to a dimension of 240x240 pixels, normalization of pixel values, as well as auto orientation. Data augmentation using horizontal flips and rotations enhanced the size of the dataset up to 15,850 which increases the invention’s resilience.
The invention was trained using an automated machine learning solution with transfer learning from a public checkpoint, which initialized it with pre-trained weights. The training process, which took 5 hours, involved real-time tracking of evaluation metrics such as mean Average Precision (mAP), precision, and recall.
Deployment of the invention on an NVIDIA Jetson Nano allowed for efficient localized processing. The integration utilized an API key, project ID, and model version, enabling real-time detection and activation of repellent systems when monkeys were identified. This approach ensured the invention's practical application in real-world scenarios.
Initially, cameras are usually placed at the monitoring space such as agriculture land where monkey are creating damage to the fields. The camera being eye of the project send the visuals which are processed further. Camera captures high quality of the images after every 5 sec technically speaking the camera provides the input to the system.
The captured images are then processed using the Roboflow API for object detection. The Roboflow API enables to make use of the trained model. The model identifies targeted objects within the images, particularly focusing on detecting the presence of monkey. This stage is important for accurate identification and localization of potential threats.
Subsequently, the detection results, includes any identified monkeys and their position, are displayed in real-time on a connected screen. This visual feedback enables continuous monitoring and validation of the detection process by users, facilitating prompt response to detected threats.
Activate Repellent System (Large Hooter) if Monkey Detected:
Upon detecting a monkey within the monitored area, the system triggers the activation of the repellent system. Specifically, a large hooter plays a loud sound of different animals like dog, lion aimed at scaring, startling and deterring the detected monkeys. This immediate response serves as a deterrent, discouraging monkeys from further intrusion or causing harm.
Report Threats via SMS:
In parallel with activating the repellent system, the system sends automated SMS notifications i.e. “Alert: Monkey detected! Generating Sound......" to stakeholders such as farmers and security personnel via Twilio Rest API. Such notifications alerts individuals or authorities about the detected monkey or monkeys in the agricultural land and thus allowing an immediate action to deal with the situations and prevent potential conflicts or damage of the agriculture land and also lives of the animal.
To conclude, the automated detection and repellent system for monkeys is efficient in curbing conflicts between human beings and monkeys. By combining image capturing, object recognizing via Roboflow API alongside rapid response mechanism, this system takes a proactive approach to managing monkey activity within human inhabited areas. Therefore, more research should be conducted on such systems in order to ensure that they not only help humans but also conserve the welfare of monkeys. Moreover, Twilio communication service sends short message alerts (SMS) to farmers or security personnel who may be programmed into the device before hand.
ADVANTAGES OF THE INVENTION:
Preventing Crop Damage: The invention is able to detect monkeys in real-time and activate repellent systems which prevent damage to crops, thus saves lives of both humans and monkeys and also reduces the financial losses the farmers may suffer.
Enhanced Human Safety: Minimizing direct conflicts between farmers and wildlife especially in agricultural areas where man and animal are likely to come into contact.
Non-Lethal Deterrence: Detering away the monkeys using loud hooter helps to ensure that the monkeys are not killed – a method of promoting ethical treatment of wildlife. By doing so it helps maintain biodiversity and shows respect for animals’ welfare.
Real-Time Monitoring and Response: Continuous monitoring along with instant responsive system helps stakeholders to quickly take action against potential threats. With automated alerts and real-time visual feedback, there is no delay in getting rid of any monkey found as that would reduce any delay that may cause potential damage or conflict.
Automated Alerts: Integration of SMS notifications through Twilio Rest API makes sure that farmers or even security personnel receive prompt information on monkey detections. As a result, responses are made fast while ensuring coordination is achieved thus further reducing potential damage.
Reduced Labor Costs: The detection and repellent system minimize the need for constant human surveillance and intervention, reducing labour costs and freeing up personnel for other tasks.
, Claims:1. An Image sensing Animal Repellent cum Security System for Crop Protection comprises an automated system, a deep leaning, a camera, an integrated approach, wherein the automated system employs a deep learning (CNN) model trained on diverse datasets and transferred to a Nano Jetson for field deployment for future proofing.
2. The system as claimed in claim 1, wherein provides Cameras to monitor agriculture lands for monkey intrusion, processing images via API for object detection, detected monkeys trigger a large hooter to deter them while automated SMS alerts notify stakeholders over the users.
3. The system as claimed in claim 1, wherein, provides integrated approach that offers real-time monitoring and swift response, mitigating human-monkey conflicts and safeguarding agricultural interests.
4. The system as claimed in claim 1, wherein, effectively provides system that fosters harmonious coexistence by proactively addressing threats and promoting timely intervention, enhancing community safety and property protection.

Documents

Application Documents

# Name Date
1 202411046465-STATEMENT OF UNDERTAKING (FORM 3) [17-06-2024(online)].pdf 2024-06-17
2 202411046465-REQUEST FOR EARLY PUBLICATION(FORM-9) [17-06-2024(online)].pdf 2024-06-17
3 202411046465-POWER OF AUTHORITY [17-06-2024(online)].pdf 2024-06-17
4 202411046465-FORM-9 [17-06-2024(online)].pdf 2024-06-17
5 202411046465-FORM FOR SMALL ENTITY(FORM-28) [17-06-2024(online)].pdf 2024-06-17
6 202411046465-FORM 1 [17-06-2024(online)].pdf 2024-06-17
7 202411046465-EVIDENCE FOR REGISTRATION UNDER SSI(FORM-28) [17-06-2024(online)].pdf 2024-06-17
8 202411046465-EVIDENCE FOR REGISTRATION UNDER SSI [17-06-2024(online)].pdf 2024-06-17
9 202411046465-EDUCATIONAL INSTITUTION(S) [17-06-2024(online)].pdf 2024-06-17
10 202411046465-DRAWINGS [17-06-2024(online)].pdf 2024-06-17
11 202411046465-DECLARATION OF INVENTORSHIP (FORM 5) [17-06-2024(online)].pdf 2024-06-17
12 202411046465-COMPLETE SPECIFICATION [17-06-2024(online)].pdf 2024-06-17
13 202411046465-FORM 18 [28-01-2025(online)].pdf 2025-01-28