Description:BACKGROUND
Field of Invention
[001] Embodiments of the present invention generally relate to a computer vision based animal identification and particularly to a system for real-time serpents detection and classification.
Description of Related Art
[002] Accurate identification of snake species has remained a longstanding challenge in both public safety and wildlife research. Various species exhibit subtle differences in physical appearance, which often leads to confusion between venomous and non-venomous types. Individuals such as farmers, forest workers, and hikers often face life-threatening situations due to misidentification. Manual identification by herpetologists or trained experts offers reliable results but proves impractical in many real-world scenarios due to limited accessibility and response time.
[003] Existing digital solutions include mobile applications and computer vision models designed for species identification. These platforms generally rely on user-submitted images or textual inputs and deliver classification results based on predefined datasets or crowdsourced feedback. However, the inconsistency in image quality, lighting conditions, and background interference often reduces their reliability. Additionally, many of these models lack specificity for venom detection and provide limited support for real-time use in field environments. Moreover, these models often prioritize general wildlife identification and fall short in handling the nuanced classification of snake species.
[004] There is thus a need for an improved and advanced system for real-time serpents detection and classification that can administer the aforementioned limitations in a more efficient manner.
SUMMARY
[005] Embodiments in accordance with the present invention provide a system for real-time serpents detection and classification. The system comprising a multimedia acquisition unit adapted to receive digital media related to serpents from an electronic device. The system further comprising a processing unit in communication with the image acquisition unit. The processing unit is configured to receive the digital media from the multimedia acquisition unit; execute a trained DenseNet121 adapted to preprocess the received digital media; isolate segments depicting the serpents from the preprocessed digital media; deploy a Convolutional Neural Network (CNN) model adapted to engage a computer vision algorithm adapted to identify discriminative features of the serpents in the isolated segments; compare the identified discriminative features of the serpents with a training dataset comprising pretrained digital media; and classify the corresponding serpents into one of predefined categories venomous, non-venomous, or a combination thereof—based on the learned discriminative features and classification confidence thresholds derived from the training dataset.
[006] Embodiments in accordance with the present invention further provide a method for real-time serpents detection and classification. The method comprising steps of receiving digital media related to serpents from a multimedia acquisition unit; executing a trained DenseNet121 adapted to preprocess the received digital media; isolating segments depicting the serpents from the preprocessed digital media; deploying a Convolutional Neural Network (CNN) model adapted to engage a computer vision algorithm adapted to identify discriminative features of the serpents in the isolate segments; comparing the identified discriminative features of the serpents with a training dataset comprising pretrained digital media; and classifying the corresponding serpents into one of predefined categories venomous, non-venomous, or a combination thereof—based on the learned discriminative features and classification confidence thresholds derived from the training dataset.
[007] Embodiments of the present invention may provide a number of advantages depending on their particular configuration. First, embodiments of the present application may provide a system for real-time serpents detection and classification.
[008] Next, embodiments of the present application may provide a serpents detection system that enables precise classification of venomous and non-venomous snakes. This reduces the chances of misidentification, ensuring reliable results even under variable conditions such as lighting, background clutter, or unusual snake postures.
[009] Next, embodiments of the present application may provide a serpents detection system that helps in identifying snakes instantly in high-risk areas like agricultural fields, forests, and industrial sites, thus preventing potential snakebite incidents.
[0010] Next, embodiments of the present application may provide a serpents detection system that captures misclassified and newly uploaded images to retrain the model periodically. This leads to improved performance over time and adaptability to new snake species or environmental conditions.
[0011] Next, embodiments of the present application may provide a serpents detection system that allows conservationists, first responders, and the general public to benefit from advanced AI-based classification without specialized training.
[0012] Next, embodiments of the present application may provide a serpents detection system that uploads and dynamic video inputs, offering broader usability. This dual input capability increases its applicability in real-world scenarios, ranging from casual encounters in residential areas to continuous surveillance in wildlife zones.
[0013] These and other advantages will be apparent from the present application of the embodiments described herein.
[0014] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The above and still further features and advantages of embodiments of the present invention will become apparent upon consideration of the following detailed description of embodiments thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
[0016] FIG. 1 illustrates a schematic block diagram of a system for real-time serpents detection and classification, according to an embodiment of the present invention;
[0017] FIG. 2 illustrates a block diagram of a processing unit, according to an embodiment of the present invention; and
[0018] FIG. 3 depicts a flowchart of a method for real-time serpents detection and classification, according to an embodiment of the present invention.
[0019] The headings used herein are for organizational purposes only and are not meant to be used to limit the scope of the description or the claims. As used throughout this application, the word "may" is used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense (i.e., meaning must). Similarly, the words “include”, “including”, and “includes” mean including but not limited to. To facilitate understanding, like reference numerals have been used, where possible, to designate like elements common to the figures. Optional portions of the figures may be illustrated using dashed or dotted lines, unless the context of usage indicates otherwise.
DETAILED DESCRIPTION
[0020] The following description includes the preferred best mode of one embodiment of the present invention. It will be clear from this description of the invention that the invention is not limited to these illustrated embodiments but that the invention also includes a variety of modifications and embodiments thereto. Therefore, the present description should be seen as illustrative and not limiting. While the invention is susceptible to various modifications and alternative constructions, it should be understood, that there is no intention to limit the invention to the specific form disclosed, but, on the contrary, the invention is to cover all modifications, alternative constructions, and equivalents falling within the scope of the invention as defined in the claims.
[0021] In any embodiment described herein, the open-ended terms "comprising", "comprises”, and the like (which are synonymous with "including", "having” and "characterized by") may be replaced by the respective partially closed phrases "consisting essentially of", “consists essentially of", and the like or the respective closed phrases "consisting of", "consists of”, the like.
[0022] As used herein, the singular forms “a”, “an”, and “the” designate both the singular and the plural, unless expressly stated to designate the singular only.
[0023] FIG. 1 illustrates a schematic block diagram of a system 100 for real-time serpents detection and classification, according to an embodiment of the present invention. In an embodiment of the present invention, the system 100 may be adapted to visually identify serpents i.e., Snakes using computational intellect techniques. The system 100 may further be adapted to classify the identified serpents into a venomous and a non-venomous class. Additionally, the system 100 may be adapted to provide additional information relating to the identified serpents.
[0024] The system 100 focuses on classification, with potential integration of techniques such as Grad-CAM to provide visual explanations of predictions by highlighting a presence of the serpents in a region of operation of the system 100. The visual explanations of the predictions enhances an interpretability of the classifications, making it easier for users to understand a decision-making process of the system 100.
[0025] The serpents identified and classified by the system 100 may be, but not limited to, a king cobra, a rattle snake, a black mamba, an Indian cobra, a taipan, and so forth. Embodiments of the present invention are intended to include or otherwise cover any serpents, including known, related art, and/or later developed technologies, that may be identified and classified by the system 100.
[0026] The system 100 may be utilized in domains such as, but not limited to, security, wildlife conservation, public safety, healthcare, and so forth. Embodiments of the present invention are intended to include or otherwise cover any domains, including known, related art, and/or later developed technologies, for utilization of the system 100.
[0027] According to the embodiments of the present invention, the system 100 may incorporate non-limiting hardware components to enhance the processing speed and efficiency such as the system 100 may comprise an electronic device 102, a multimedia acquisition unit 106, a processing unit 108, a trained DenseNet121 110, a Convolutional Neural Network (CNN) model 112, a computer vision algorithm 114, and a training dataset 116. In an embodiment of the present invention, the hardware components of the system 100 may be integrated with computer-executable instructions for overcoming the challenges and the limitations of the existing systems.
[0028] In an embodiment of the present invention, the electronic device 102 may be adapted to upload and/or capture digital media to the system 100. The electronic device 102 may further be adapted to receive AI-generated classification reports along with the additional information relating to the identified serpents, in an embodiment of the present invention. The electronic device 102 may be, but not limited to, a computing unit or an image capturing unit, such as a mobile phone, a smartphone, a tablet, a Close Circuit Television (CCTV) camera, a camcorder, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the electronic device 102, including known, related art, and/or later developed technologies.
[0029] In an embodiment of the present invention, the electronic device 102 may comprise a computer application 104 for displaying the classified serpents into either the "venomous" or "non-venomous" categories. Further, the computer application 104 may be adapted to display the AI-generated classification reports along with the additional information relating to the identified serpents, in an embodiment of the present invention.
[0030] In an embodiment of the present invention, the multimedia acquisition unit 106 may be adapted to receive the digital media related to the serpents from the electronic device 102.
[0031] In an embodiment of the present invention, the processing unit 108 may be in communication with the multimedia acquisition unit 106. The processing unit 108 may further be configured to execute computer-executable instructions to generate an output relating to the system 100. According to embodiments of the present invention, the processing unit 108 may be, but not limited to, a Programmable Logic Control (PLC) unit, a microprocessor, a development board, and so forth. Embodiments of the present invention are intended to include or otherwise cover any type of the processing unit 108 including known, related art, and/or later developed technologies. In an embodiment of the present invention, the processing unit 108 may further be explained in conjunction with FIG. 2.
[0032] FIG. 2 illustrates a block diagram of the processing unit 108 of the system 100, according to an embodiment of the present invention. The processing unit 108 may comprise the computer-executable instructions in form of programming modules such as a data receiving module 200, a data preprocessing module 202, a data identification module 204, a data classification module 206, and an info generation module 208.
[0033] In an embodiment of the present invention, the data receiving module 200 may be adapted to receive the digital media from the multimedia acquisition unit 106. The data receiving module 200 may further be configured to transmit the received digital media to the data preprocessing module 202.
[0034] The data preprocessing module 202 may be activated upon receipt of the digital media from the data receiving module 200. In an embodiment of the present invention, the data preprocessing module 202 may be configured to execute the trained DenseNet121 110. The trained DenseNet121 110 may be adapted to execute a set of syntax on the received digital media. The set of syntax may be, but not limited to, a GlobalAveragePolling2d function, a Rectified Linear Unit (ReLU) activated 1024 units dense function, a Sigmoid activated 1 units Dense function, a cv2.vedioCapture Open Computer Vision (CV) function, a cv2.cvtColor Open Computer Vision (CV) function, and so forth. Embodiments of the present invention are intended to include or otherwise cover syntaxes, including known, related art, and/or later developed technologies, executed by trained DenseNet121 110 on the received digital media.
[0035] The trained DenseNet121 110 may further be adapted to preprocess the received digital media. The preprocessing of the received digital media may be carried out by actions such as, but not limited to, a fixed dimension, normalizing pixel values, applying data augmentation, flipping, rotating, brightness adjustment, and so forth. Embodiments of the present invention are intended to include or otherwise cover any actions, including known, related art, and/or later developed technologies, for preprocessing of the received digital media. The data preprocessing module 202 may further be configured to transmit the preprocessed digital media to the data identification module 204.
[0036] The data identification module 204 may be activated upon receipt of the preprocessed digital media from the data preprocessing module 202. In an embodiment of the present invention, the data identification module 204 may be configured to isolate segments depicting the serpents from the preprocessed digital media. The isolation of the segments may be carried out by activating the computer vision algorithm 114 for identification of a contour of the serpents in the preprocessed digital media. Moreover, upon identification of the contour of the serpents, the data identification module 204 may be configured to slice the identified contour and save the extraction as a Portable Network Graphics (.PNG) file.
[0037] Further, the data identification module 204 may be configured to deploy the Convolutional Neural Network (CNN) model 112 engaging the computer vision algorithm 114 adapted to identify discriminative features of the serpents in the isolated segments. The discriminative features identified by the computer vision algorithm 114 may be, but not limited to, a color, a length, a girth, a location of eyes, a pattern of scale, a visibly of snoot, a location of fangs, a tail design, a presence of hood, and so forth. Embodiments of the present invention are intended to include or otherwise cover any discriminative features, including known, related art, and/or later developed technologies, that may be identified by the computer vision algorithm 114 in the isolated segments.
[0038] Further, the data identification module 204 may be configured to compare the identified discriminative features of the serpents with the training dataset 116 comprising pretrained digital media. The comparison may be carried out by generation of a matrix. The matrix may comprise a list of the identified discriminative features. Additionally, the matrix may comprise a corresponding classification confidence thresholds for every match of the identified discriminative features with the pretrained digital media collected in the training dataset 116. The identified discriminative features having the highest classification confidence thresholds may be considered as learned discriminative features of the serpents. In an embodiment of the present invention, the data identification module 204 may be configured to split the training dataset 116 into training, validation, and testing subsets.
[0039] The data identification module 204 may be configured to transmit the interpolated learned discriminative features of the serpents to the data classification module 206.
[0040] The data classification module 206 may be activated upon receipt of the learned discriminative features of the serpents. In an embodiment of the present invention, the data classification module 206 may be configured to classify the corresponding serpents into one of predefined categories venomous, non-venomous, or a combination thereof, based on the learned discriminative features and the classification confidence thresholds derived from the training dataset 116.
[0041] In an embodiment of the present invention, the info generation module 208 may be configured to generate the additional information relating to the classified serpents. The additional information may be, but not limited to, a confidence score, a relevant digest, a fun fact, a trivia, and so forth. Embodiments of the present invention are intended to include or otherwise cover any additional information, including known, related art, and/or later developed technologies, that may be generated and provided relating to the classified serpents. The info generation module 208 may be configured to display the additional information onto the electronic device 102.
[0042] In an embodiment of the present invention, the info generation module 208 may be configured to generate the AI-generated classification reports. The info generation module 208 may be configured to display the AI-generated classification reports onto the electronic device 102.
[0043] In an embodiment of the present invention, the info generation module 208 may be configured to generate a notification upon sighting of the serpents in a predefined premise such as homes, offices, and so forth. Further, the generated notification may be transmitted to the electronic device 102. The notification received on the electronic device 102 may be in a pre-defined form, in an embodiment of the present invention. According to embodiments of the present invention, the pre-defined form of the notification received on the electronic device 102 may be, but not limited to a pop-up notification, a flash notification, a ringer notification, a silent notification, a push notification, a hidden notification, an electronic mail notification, a Short Message Service (SMS) notification, an always on-screen notification, and so forth. Embodiments of the present invention are intended to include or otherwise cover any pre-defined form of the notification that may be received on the electronic device 102, including known, related art, and/or later developed technologies.
[0044] FIG. 3 depicts a flowchart of a method 300 for real-time serpents detection and classification, according to an embodiment of the present invention.
[0045] At step 302, the system 100 may receive the digital media from the multimedia acquisition unit 106.
[0046] At step 304, the system 100 may execute the trained DenseNet121 110 adapted to preprocess the received digital media.
[0047] At step 306, the system 100 may isolate the segments depicting the serpents from the preprocessed digital media.
[0048] At step 308, the system 100 may deploy the Convolutional Neural Network (CNN) model 112 to engage the computer vision algorithm 114 to identify the discriminative features of the serpents in the isolated segments.
[0049] At step 310, the system 100 may compare the identified discriminative features of the serpents with the training dataset 116 comprising pretrained digital media.
[0050] At step 312, if the identified discriminative features may indicate venomous serpents, then the method 300 may proceed to a step 314. Else, the method 300 may proceed to a step 316.
[0051] At step 314, the system 100 may classify the corresponding serpents into the venomous category.
[0052] At step 316, the system 100 may classify the corresponding serpents into the non-venomous category.
[0053] At step 318, the system 100 may provide the additional information relating to the classified serpents.
[0054] At step 320, the system 100 may generate the AI-generated classification reports and display the AI-generated classification reports on the electronic device 102.
[0055] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it is to be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0056] This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the invention is defined in the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements within substantial differences from the literal languages of the claims. , Claims:CLAIMS
I/We Claim:
1. A system (100) for real-time serpents detection and classification, the system (100) comprising:
a multimedia acquisition unit (106) adapted to receive digital media related to serpents from an electronic device (102); and
a processing unit (108) in communication with the image acquisition unit, characterized in that the processing unit (108) is configured to:
receive the digital media from the multimedia acquisition unit (106);
execute a trained DenseNet121 (110) adapted to preprocess the received digital media;
isolate segments depicting the serpents from the preprocessed digital media;
deploy a Convolutional Neural Network (CNN) model (112) adapted to engage a computer vision algorithm (114) adapted to identify discriminative features of the serpents in the isolated segments;
compare the identified discriminative features of the serpents with a training dataset (116) comprising pretrained digital media; and
classify the corresponding serpents into one of predefined categories selected from venomous, non-venomous, or a combination thereof based on the learned discriminative features and classification confidence thresholds derived from the training dataset (116).
2. The system (100) as claimed in claim 1, wherein the preprocessing of the received digital media is carried out by resizing input digital media to a fixed dimension, normalizing pixel values, applying data augmentation, flipping, rotating, brightness adjustment, or a combination thereof.
3. The system (100) as claimed in claim 1, wherein the electronic device (102) is selected from a computing unit, an image capturing unit, or a combination thereof.
4. The system (100) as claimed in claim 1, wherein the electronic device (102) comprises a computer application (104) for displaying the classified serpents into either the "venomous" or "non-venomous" categories.
5. The system (100) as claimed in claim 1, wherein the processing unit (108) is configured to provide additional information selected from, a confidence score, a relevant digest, a fun fact, a trivia, or a combination thereof relating to the classified serpents.
6. The system (100) as claimed in claim 1, wherein the processing unit (108) is configured to split the training dataset (116) into training, validation, and testing subsets.
7. The system (100) as claimed in claim 1, wherein the processing unit (108) is configured to generate AI-generated classification reports and display the AI-generated classification reports on the electronic device (102).
8. A method (300) for real-time serpents detection and classification, the method (300) is characterized by steps of:
receiving digital media related to serpents from a multimedia acquisition unit (106);
executing a trained DenseNet121 (110) adapted to preprocess the received digital media;
isolating segments depicting the serpents from the preprocessed digital media;
deploying a Convolutional Neural Network (CNN) model (112) adapted to engage a computer vision algorithm (114) adapted to identify discriminative features of the serpents in the isolate segments;
comparing the identified discriminative features of the serpents with a training dataset (116) comprising pretrained digital media; and
classifying the corresponding serpents into one of predefined categories venomous, non-venomous, or a combination thereof based on the learned discriminative features and classification confidence thresholds derived from the training dataset (116).
9. The method (300) as claimed in claim 8, comprising a step of providing additional information selected from, a confidence score, a relevant digest, a fun fact, a trivia, or a combination thereof relating to the classified serpents.
10. The method (300) as claimed in claim 8, comprising a step of generating an AI-generated classification reports and displaying the AI-generated classification reports on the electronic device (102).
Date: April 16, 2025
Place: Noida

Nainsi Rastogi
Patent Agent (IN/PA-2372)
Agent for the Applicant