WO2022092548A1 - Ecological survey system - Google Patents

Ecological survey system Download PDF

Info

Publication number
WO2022092548A1
WO2022092548A1 PCT/KR2021/012156 KR2021012156W WO2022092548A1 WO 2022092548 A1 WO2022092548 A1 WO 2022092548A1 KR 2021012156 W KR2021012156 W KR 2021012156W WO 2022092548 A1 WO2022092548 A1 WO 2022092548A1
Authority
WO
WIPO (PCT)
Prior art keywords
sound
ecological
animal
species
wild animal
Prior art date
Application number
PCT/KR2021/012156
Other languages
French (fr)
Korean (ko)
Inventor
최병진
Original Assignee
한국자연환경연구소㈜
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 한국자연환경연구소㈜ filed Critical 한국자연환경연구소㈜
Publication of WO2022092548A1 publication Critical patent/WO2022092548A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L17/00—Speaker identification or verification techniques
    • G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
    • G10L19/04—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using predictive techniques
    • G10L19/26—Pre-filtering or post-filtering
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0272—Voice signal separating
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
    • H04R1/32—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only
    • H04R1/40—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/20—Arrangements for obtaining desired frequency or directional characteristics
    • H04R1/32—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only
    • H04R1/40—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers
    • H04R1/406—Arrangements for obtaining desired frequency or directional characteristics for obtaining desired directional characteristic only by combining a number of identical transducers microphones

Definitions

  • the present invention relates to an ecological survey system, and more particularly, by collecting sounds and ultrasonic waves of wild animals (birds, bats, frogs, insects, etc.) It is a system that investigates and analyzes breeding status and changes in the number of individuals. It identifies the species of wild animals that appear in the equipment that records animal sounds, the wireless transmission device, and the wirelessly transmitted sound signal file, and collects the identified species data. It is about an ecological survey system that analyzes the population and habitat based on
  • the investigation method of wild animals confirms the appearance of birds by directly observing and listening to birdsong.
  • Birds are mainly active before and after sunrise and sunset, so even in the same survey area, there is a difference in the species of birds that appear depending on the time the investigator arrives at the site to investigate. As the investigation time varies by point, it may affect the identification of the appearance of the species.
  • the most effective investigation method for nocturnal birds of prey is to identify the appearance of the species with distinctive sounds for each species.
  • bats rest in caves or tree cavities during the daytime, and fly at high speed at night.
  • bats are directly captured by directly exploring the cave or installing a net on the route where bats are supposed to move. After that, the species is identified and the presence or absence of the species is investigated.
  • insects that make sounds such as cicadas and crickets, determine whether the species appears by the presence or absence of a sound.
  • This survey method has no choice but to conduct a survey of a small area, and it is difficult to survey over a long period of time. and monitoring methods are used.
  • a recorder In order to record the sounds of wild animals (bioacustic), a recorder is used that automatically records when a sound abnormality occurs at a specific time or a specific level. will be analyzed
  • the present invention was created to solve the problems of the prior art as described above, and by collecting the sounds and ultrasonic waves of wild animals (birds, bats, frogs, insects, etc.) appearing at the investigation site, the appearance of wild animal species in the investigation area It is a system that investigates and analyzes the existence, long-term breeding status, and changes in the number of individuals. It identifies the species of wild animals that appear in the sound recording equipment, wireless transmission device, and wirelessly transmitted sound signal file, and identifies the identified species. It aims to provide an ecological survey system that analyzes the population and habitat based on the data of
  • the present invention for achieving the above object collects ambient sounds in real time in a distributed and installed state in the irradiation area, but selects only wild animal sound signals excluding noise, and provides a plurality of sound collection units as identification signals together with their own ID signals.
  • Appearance species specific means 210 for specifically classifying wild animal species by comparing the wild animal sound signal among the identification signals provided by the sound collecting unit 100 with the stored wild animal sound book or wild animal sound data in the table;
  • the individual animal recognition means 220 for analyzing the characteristics of each of the wild animal sound signals that are specifically classified by the appearance species specifying means 210, and assigning an individual recognition code to each wild animal sound signal, and collecting the plurality of sounds
  • an ecology analysis unit 200 including an ecology analysis means 230 for extracting the movement lines and main habitats of , and calculating the frequency and number of their appearance;
  • a management unit 300 that receives the analysis data provided by the ecological analysis unit 200 and remotely manages and analyzes it through a management and comprehensive analysis algorithm or program mounted on a computer system; It is characterized in that it includes.
  • the sound collection unit 100 includes a plurality of recording devices or microphones provided with their IDs installed at regular intervals or for each area in the irradiation area, and the sound signal collected by the recording apparatus or microphone, except for ambient noise.
  • a sound filter circuit that filters only animal sound signals, a sound signal processing circuit that converts an identification signal by combining a corresponding time and its own ID signal when a sound signal is applied from the sound filter circuit, and an interface or communication circuit that transmits the identification signal It is characterized in that it includes.
  • the sound collecting unit 100 of the present invention is characterized in that it is installed in a separate prop or a facility including a pre-installed fence or telephone pole, or is installed in a natural feature including a tree.
  • the species specific means 210 of the ecological analysis unit 200 compares the stored wild animal sound book or the wild animal sound data in the table, It is characterized in that it is an acoustic comparison and analysis circuit loaded with an algorithm or program that specifically classifies a species that matches the sound characteristics of a wild animal species including amplitude, frequency, and phase or falls within a set range.
  • the individual animal recognition means 220 of the ecology analysis unit 200 analyzes the sound characteristics of the wild animal and analyzes the individual recognition code when a specific classified wild animal sound signal is provided by the appearance species specifying means 210 . It is characterized in that it is a sound comparison and analysis circuit loaded with an algorithm or program that provides information to recognize a specific animal of a specific species by giving and storing it, and comparing it with a sound signal provided later.
  • the ecological analysis means 230 of the ecological analysis unit 200 includes the sequence of the sound signals provided from the plurality of sound collection units 100 and the appearance animal specifying means 210 and the individual animal recognition means 220. Analyze changes in the level (intensity) of sounds of wild animals provided in At the same time, the main habitat is extracted by analyzing It is characterized in that it is an acoustic comparison and analysis circuit loaded with an algorithm or program.
  • the algorithm or program of the sound comparison and analysis circuit of the present invention automatically analyzes the sounds of wild animals provided as digital files including wav, zc, and mp3. It is a program that learns this pattern after converting it into an image, and it is characterized by analyzing the pulse interval in the spectogram, the highest frequency in the pulse, the lowest frequency, and the frequency at the maximum dB.
  • the management unit 300 receives and stores the analysis data or sound signal provided by the ecological analysis unit 200, and then loads it, including a server installed in a remote control center equipped with an algorithm or program for management and comprehensive analysis. It is characterized in that it is a computer system or a portable terminal of an administrator or researcher.
  • the present invention by means of the above-described problem solving means departs from the method of judging the presence or absence of wild animals through direct field investigations and determines whether wild animals appear for a long period of time through the sound collection unit 100 widely distributed in the investigation area.
  • the number of field investigations is drastically reduced and the investigation is made easier, and the effect of enabling objective comparison between the investigation site and the investigation results is obtained.
  • the present invention collects ambient sounds by distributing and installing the sound collecting unit 100 in a wide irradiation area, but extracting only the sounds of the wild animals excluding the surrounding noise, so that the manager collects and stores the sounds of the wild animals It is possible to immediately check the appearance status of wild animals, the species and specific animals without having to look at them one by one, thereby improving the workability related to survey management.
  • the species specific means 210 of the present invention compares it with the wild animal sound data in the stored wild animal sound book or table, that is, the amplitude and frequency. , matches the sound characteristics of a wildlife species, including topology (e.g., birds singing and behavioral sounds, frog singing and behavioral sounds, bat ultrasonic sounds, whale ultrasonic sounds, and insects such as cicadas and crickets), or By categorizing the species within the set range, the effect is obtained so that the manager can easily classify and confirm the species that have appeared without a separate classification task.
  • topology e.g., birds singing and behavioral sounds, frog singing and behavioral sounds, bat ultrasonic sounds, whale ultrasonic sounds, and insects such as cicadas and crickets
  • the individual animal recognition means 220 of the present invention when a specific classified wild animal sound signal is provided by the appearance species specific means 210, compares and analyzes the sound signal of a specific wild animal that has been collected and stored so far, In the case of an animal sound signal, an individual recognition code is given and stored, and a specific animal of a specific species can be recognized by comparing it with a sound signal provided later, thereby obtaining the effect of easily confirming the number of a specific species.
  • the ecological analysis means 230 of the present invention provides a sequence of sound signals provided by a plurality of sound collection units 100 and wild animals provided by the appearance animal specifying means 210 and individual animal recognition means 220 . Analyze the change in sound level (intensity), but extract the movement line by analyzing the direction in which the species and individual animals moved in the main habitat At the same time, by calculating the frequency of appearance in a specific movement and in a specific area, and by analyzing the specified species and specified animal in the individual animal recognition means 220 to calculate the number of individuals and provide information, video including CCTV It has the effect of allowing the investigation of the movement of wild animals, their frequency of appearance, and the number of individuals through low-volume acoustic data without the need for image collection by a photographing means.
  • the management unit 300 receives, stores and manages the analysis data organized by the ecology analysis unit 200 itself, and uses it as research and analysis data if necessary, as well as transmits from the ecology analysis unit 200 .
  • the management unit 300 receives, stores and manages the analysis data organized by the ecology analysis unit 200 itself, and uses it as research and analysis data if necessary, as well as transmits from the ecology analysis unit 200 .
  • FIG. 1 is a system block diagram schematically showing the configuration of the present invention
  • FIG. 2 is a configuration diagram showing an example to which the present invention is applied and a state of detecting a sound of a wild animal.
  • Figure 3 is a configuration diagram showing an example of the configuration and signal transmission of the ecological analysis unit in the present invention.
  • Figure 4 is a configuration diagram showing another example of the configuration and signal transmission of the ecological analysis unit in the present invention.
  • FIG. 5 is a block diagram showing the overall operating state of the sound collection unit, the ecological analysis unit and the management unit of the present invention.
  • FIG. 6 is a flow chart showing the self-sound signal analysis step of the management unit in the present invention.
  • the ecological survey system 100 of the present invention collects ambient sounds in real time in a distributed and installed state in the survey area, but selects only wild animal sound signals excluding noise, a plurality of sound collecting units 100 provided together as an identification signal;
  • Appearance species specific means 210 for specifically classifying wild animal species by comparing the wild animal sound signal among the identification signals provided by the sound collecting unit 100 with the stored wild animal sound book or wild animal sound data in the table;
  • the individual animal recognition means 220 for analyzing the characteristics of each of the wild animal sound signals that are specifically classified by the appearance species specifying means 210, and assigning an individual recognition code to each wild animal sound signal, and collecting the plurality of sounds
  • an ecology analysis unit 200 including an ecology analysis means 230 for extracting the movement lines and main habitats of , and calculating the
  • the sound collecting unit 100 includes a plurality of recording devices or microphones provided with their IDs installed at regular intervals or by areas in the irradiation area, and ambient noise from the sound signals collected by the recording apparatus or microphone.
  • a sound filter circuit that filters only the sound signals of wild animals except for the sound signal, and when a sound signal is applied from the sound filter circuit, a sound signal processing circuit that combines the corresponding time and its ID signal to convert it into an identification signal, and an interface for transmitting the identification signal; or It may include a communication circuit.
  • the species specific means 210 of the ecological analysis unit 200 of the present invention compares with the wild animal sound data in the stored wild animal sound book or table when the wild animal sound signal is provided from the sound collecting unit 100 . Therefore, it may be an acoustic comparison and analysis circuit loaded with an algorithm or program for specific classification of a species.
  • the individual animal recognition means 220 of the ecological analysis unit 200 analyzes the sound characteristics of the wild animal and analyzes the sound characteristics of the wild animal when a specific classified wild animal sound signal is provided by the appearance species specifying means 210 . It may be a sound comparison and analysis circuit loaded with an algorithm or program that provides information for recognizing a specific animal of a specific species by assigning a recognition code and storing it, and comparing it with a sound signal provided later.
  • the ecological analysis means 230 of the ecological analysis unit 200 includes the sequence of the sound signals provided by the plurality of sound collection units 100 and the appearance animal specific means 210 and the individual animal recognition means ( 220), a sound comparison and analysis circuit equipped with an algorithm or program that analyzes changes in the level (intensity) of the sounds of wild animals, extracts movement routes and main habitats, and calculates the frequency and number of appearances and provides information may be
  • the management unit 300 receives and stores the analysis data or sound signals provided by the ecological analysis unit 200, and then loads and manages and comprehensively analyzes it. It may be a computer system including a server or a portable terminal of an administrator or researcher.
  • the present invention collects ambient sounds in real time in a distributed and installed state in the irradiation area, but selects only wild animal sound signals excluding noise, and provides a plurality of identification signals together with their own ID signals.
  • sound collection unit 100 Appearance species specific means 210 for specifically classifying wild animal species by comparing the wild animal sound signal among the identification signals provided by the sound collecting unit 100 with the stored wild animal sound book or wild animal sound data in the table;
  • the individual animal recognition means 220 for analyzing the characteristics of each of the wild animal sound signals that are specifically classified by the appearance species specifying means 210, and assigning an individual recognition code to each wild animal sound signal, and collecting the plurality of sounds
  • an ecology analysis unit 200 including an ecology analysis means 230 for extracting the movement lines and main habitats of , and calculating
  • the present invention collects the sounds of wild animals that appear for a long period of time through the sound collection unit 100 widely distributed in the investigation area, away from the method of judging whether wild animals appear or not, through direct field investigations.
  • recording and identifying species it is possible to dramatically reduce the number of on-site surveys and make surveys easier, and it is possible to make objective comparisons between survey sites and survey results possible.
  • the sound collecting unit 100 includes a plurality of recording devices or microphones provided with their IDs installed at regular intervals or by areas in the irradiation area, and ambient noise from the sound signals collected by the recording apparatus or microphone.
  • a sound filter circuit that filters only the sound signals of wild animals except for the sound signal, and when a sound signal is applied from the sound filter circuit, a sound signal processing circuit that combines the corresponding time and its ID signal to convert it into an identification signal, and an interface for transmitting the identification signal; or It is a preferred embodiment to include a communication circuit.
  • the sound collecting unit 100 of the present invention has a waterproof and dustproof function to have resistance to rain and snow, and to be automatically saved or programmatically set for an operating time when a sound greater than or equal to a set sound is heard.
  • the sound collection unit 100 of the present invention is installed in a separate pole or a facility including a pre-installed fence or electric pole, or installed in a natural feature including a tree.
  • the sound collection unit 100 of the present invention is distributed and installed in a wide irradiation area to collect ambient sound, and ambient noise, for example, wind noise or the sound of movement of branches or grass.
  • ambient noise for example, wind noise or the sound of movement of branches or grass.
  • a sound that occurs frequently such as a sound of water or water, is regarded as noise, only the sound of an appearing wild animal is extracted, the time at which the sound is generated and its own ID signal are combined, converted into an identification signal, and provided to the ecological analysis unit 200 .
  • the sound collection unit 100 of the present invention is distributed and installed in a wide irradiation area to collect ambient sounds, but by extracting only the sounds of the wild animals excluding the surrounding noise, the manager collects and stores the information of the sounds of the wild animals. It is possible to make it possible to check immediately without having to look at them one by one.
  • the ecology analysis unit 200 is packaged (modularized) with each of a plurality of sound collecting units 100, as shown in FIG. 3 of the accompanying drawings, and provided by the corresponding sound analysis unit 100.
  • a sound signal is provided through an interface and transmitted to the management unit 300 through a communication network. It is also preferable to receive the identification signal including the ID provided by each sound analysis unit 100 and transmit it to the management unit 300 through the communication network.
  • the species specific means 210 of the ecological analysis unit 200 of the present invention compares the stored wild animal sound book or the wild animal sound data of the table. Therefore, it is assumed that an acoustic comparison and analysis circuit equipped with an algorithm or program for specific classification of a species is used as an embodiment.
  • the species specific means 210 of the present invention compares the stored wild animal sound book or wild animal sound data in the table, that is, the amplitude and frequency. , specify a species that matches the sound characteristics of a wildlife species, including topology (e.g. frog calls, rat calls, weasel calls, bird calls, cicadas calls, bat ultrasounds, etc.) or falls within a set range.
  • topology e.g. frog calls, rat calls, weasel calls, bird calls, cicadas calls, bat ultrasounds, etc.
  • the administrator can easily check the classification without a separate classification task.
  • the individual animal recognition means 220 of the ecological analysis unit 200 analyzes the sound characteristics of the wild animal and analyzes the sound characteristics of the wild animal when a specific classified wild animal sound signal is provided by the appearance species specifying means 210 .
  • An embodiment is an acoustic comparison and analysis circuit equipped with an algorithm or program that provides information to recognize a specific animal of a specific species by assigning a recognition code and storing it, and comparing it with a sound signal provided later.
  • the individual animal recognition means 220 of the present invention compares and analyzes sound signals of specific wild animals collected and stored so far when a specific classified wild animal sound signal is provided by the appearing species specific means 210, and other wild animals.
  • a specific classified wild animal sound signal is provided by the appearing species specific means 210, and other wild animals.
  • an animal sound signal it is possible to easily identify the number of a specific species by assigning an individual recognition code to storing it, and then comparing it with a sound signal provided later to recognize a specific animal of a specific species.
  • the ecological analysis means 230 of the ecological analysis unit 200 includes the sequence of the sound signals provided by the plurality of sound collection units 100 and the appearance animal specific means 210 and the individual animal recognition means ( 220), a sound comparison and analysis circuit equipped with an algorithm or program that analyzes changes in the level (intensity) of the sounds of wild animals, extracts movement routes and main habitats, and calculates the frequency and number of appearances and provides information Let it be an example.
  • the ecological analysis means 230 of the present invention is a sequence of sound signals provided by a plurality of sound collection units 100 and wild animals provided by the appearance animal specifying means 210 and the individual animal recognition means 220 . Analyze the change in sound level (intensity), but extract the movement line by analyzing the direction in which the species and individual animals moved in the main habitat At the same time, by calculating the frequency of appearance in a specific movement and in a specific area, and by analyzing the specified species and specified animal in the individual animal recognition means 220 to calculate the number of individuals and provide information, video including CCTV It is possible to investigate the movement of wild animals, their frequency of appearance, and the number of individuals through low-volume acoustic data without the need for image collection by a photographing means (refer to FIG. 2 again).
  • the algorithm or program of the sound comparison and analysis circuit of the present invention automatically analyzes the sounds of wild animals provided as digital files including wav, zc, and mp3, and is a program learned by deep learning in advance and is a voice file. After converting into a spectrogram and expressing it as an image, it is an embodiment to analyze the interval of pulses in the spectogram, the highest frequency in the pulse, the lowest frequency, and the frequency at the maximum dB with a program for learning this pattern.
  • the deep learning technique which is an artificial intelligence machine learning method, is applied to the ecological analysis unit 200 of the present invention, but filtering is performed on the collected and provided sound signals through a convolutional neural network (CNN).
  • CNN convolutional neural network
  • extracting various local features by repeatedly applying multiple filters to find image features, extracting feature sequences from the input image of the CNN through CRNN (Convolutional Recurrent Neural Network), and extracting the extracted feature sequences
  • a sequence of images is predicted using the RNN input as an input, and a sound signal is analyzed by giving weight to which input state each output refers to more by referring to all combinations of the output and input states of the RNN layer.
  • the management unit 300 receives and stores the analysis data or sound signals provided by the ecological analysis unit 200, and then loads and manages and comprehensively analyzes it.
  • An embodiment is a computer system including a server or a portable terminal of an administrator or researcher.
  • the mobile terminal of the administrator or researcher of the present invention is a laptop computer, tablet PC, or smart phone used in a remote control station premises or periodic survey area exploration.
  • the analysis data when transmitted from the ecological analysis unit 200, it is stored as a self-report analysis management table, and then loaded when research and research analysis work is necessary so that management and comprehensive analysis are made.
  • the sound Open the signal file move to the section where the sound signal appears, and determine whether a wild animal appears in the sound signal file, but if the wild animal does not appear at this time, move to the next sound signal section to determine whether a wild animal appears , if a wild animal appears, compare it with the wild animal sound in the sound signal file and the wild animal sound data in the pre-stored wild animal sound book or table, that is, the sound characteristics of wild animal species including amplitude, frequency, and phase
  • the species specific means 210 compares the stored wild animal sound book or wild animal sound data in the table, that is, the amplitude, frequency, and phase.
  • Matches or falls within a set range of sound characteristics e.g., birds singing and behavioral sounds, frog singing and behavioral sounds, bat ultrasonic sounds, whale ultrasonic sounds, insect sounds such as cicadas and crickets, etc.
  • sound characteristics e.g., birds singing and behavioral sounds, frog singing and behavioral sounds, bat ultrasonic sounds, whale ultrasonic sounds, insect sounds such as cicadas and crickets, etc.
  • the management unit 300 receives, stores and manages the analysis data organized by the ecology analysis unit 200 itself, and uses it as research and analysis data if necessary, as well as the data transmitted from the ecology analysis unit 200.
  • the sound signal By allowing the sound signal to be directly analyzed and managed, it is possible to manage multiple survey analysis and improve the reliability of the survey analysis data.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Acoustics & Sound (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Signal Processing (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Otolaryngology (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Agronomy & Crop Science (AREA)
  • Animal Husbandry (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Catching Or Destruction (AREA)

Abstract

The present invention relates to an ecological survey system. More particularly, as a system that investigates and analyzes the presence or absence of wild animal species in a survey area, long-term breeding, and changes in population, by collecting the sounds and ultrasonic waves of wild animals (birds, bats, frogs, insects, etc.) appearing at a survey site, the present invention relates to an ecological survey system that identifies the species of wild animals appearing in animal sound recording equipment, wireless transmission devices, and wirelessly transmitted sound signal files, and analyzes the number and habitat on the basis of the identified species data.

Description

생태 조사 시스템Ecological survey system
본 발명은 생태조사 시스템에 관한 것으로, 더욱 상세하게는 조사 현장에 출현하는 야생동물(조류, 박쥐, 개구리, 곤충 등)의 소리와 초음파를 수집하여, 조사지역의 야생동물 종의 출현 유무와 장기적인 번식 여부 및 개체수의 변화 등을 조사하고 분석하는 시스템으로서, 동물의 소리를 녹음하는 장비와 무선전송장치, 무선전송된 소리신호 파일에서 출현하는 야생동물의 종을 동정하고, 동정된 종의 자료를 기반으로 개체수와 서식을 분석하는 생태조사 시스템에 관한 것이다.The present invention relates to an ecological survey system, and more particularly, by collecting sounds and ultrasonic waves of wild animals (birds, bats, frogs, insects, etc.) It is a system that investigates and analyzes breeding status and changes in the number of individuals. It identifies the species of wild animals that appear in the equipment that records animal sounds, the wireless transmission device, and the wirelessly transmitted sound signal file, and collects the identified species data. It is about an ecological survey system that analyzes the population and habitat based on
일반적으로, 야생 동물 특히 조류의 조사방법은 직접 관찰하는 방법과 새소리를 듣고서 새의 출현을 확인한다. 새들은 주로 일출, 일몰 전후에 주로 활동하는 특성을 가지고 있어 동일한 조사지역이라 할지라도 조사자가 현장에 도착해서 조사하는 시간에 따라서 출현하는 조류 종의 차이가 존재하며, 여러 조사지점을 조사할 경우 조사 지점별 조사 시간이 달라지므로 출현 종의 양상 파악에 영향을 미칠 수가 있다.In general, the investigation method of wild animals, especially birds, confirms the appearance of birds by directly observing and listening to birdsong. Birds are mainly active before and after sunrise and sunset, so even in the same survey area, there is a difference in the species of birds that appear depending on the time the investigator arrives at the site to investigate. As the investigation time varies by point, it may affect the identification of the appearance of the species.
또한, 야행성 맹금류는 종별로 특색있는 소리를 가지고 종의 출현을 파악하는 방법이 가장 효과적인 조사방법이지만 현실적으로 야간에 넓은 조사지역을 돌아다니면 조사하기에는 어려움이 따른다.In addition, the most effective investigation method for nocturnal birds of prey is to identify the appearance of the species with distinctive sounds for each species.
주로 산새들인 명금류(songbirds)는 나뭇가지 등을 이용하여 이동하고 먹이를 찾기 때문에 육안이나 망원경으로 관찰이 어려워, 주로 새가 내는 소리로 종의 서식 유무를 판별하는데, 조사자의 소리 구별능력에 따라 조사 결과의 편차가 크게 발생한다.Songbirds, which are mainly mountain birds, are difficult to observe with the naked eye or telescope because they move and search for food using tree branches. There is a large variation in the survey results.
특히, 박쥐들은 낮시간대에는 동굴이나 나무의 공동 등에서 휴식하고 야간에 빠른속도로 비행해 다니는데, 박쥐의 조사는 동굴을 직접 탐사하여 조사하거나 박쥐가 이동할 것으로 추정되는 경로 상에 그물을 설치하여 직접 포획한 후 종을 동정하고 해당 종의 출현 유무를 조사하게 된다.In particular, bats rest in caves or tree cavities during the daytime, and fly at high speed at night. In the investigation of bats, bats are directly captured by directly exploring the cave or installing a net on the route where bats are supposed to move. After that, the species is identified and the presence or absence of the species is investigated.
또한, 매미나 귀뚜라미류와 같이 소리를 내는 곤충들은 소리의 유무로 해당 종의 출현 여부를 판단하게 된다.In addition, insects that make sounds, such as cicadas and crickets, determine whether the species appears by the presence or absence of a sound.
이러한 조사방법은 좁은 지역에 대한 조사만을 수행할 수밖에 없으며, 조사기간도 장기간에 걸쳐서 조사하는데 어려움이 있어, 다른 대안으로 새, 개구리, 박쥐와 곤충들이 내는 소리(bioacustic)를 이용하여 생물 상을 조사하고 모니터링하는 방법들이 이용된다.This survey method has no choice but to conduct a survey of a small area, and it is difficult to survey over a long period of time. and monitoring methods are used.
상기와 같이, 야생 동물의 소리(bioacustic)를 녹음하기 위해서는 특정시간대나 특정 크기의 소리 이상이 발생할 때 자동으로 녹음하는 녹음기를 사용하는데, 이러한 녹음기로 녹음한 파일을 연구실에 가지고 와서 청음하고 출현 종을 분석하게 된다.As described above, in order to record the sounds of wild animals (bioacustic), a recorder is used that automatically records when a sound abnormality occurs at a specific time or a specific level. will be analyzed
바이오어쿼스틱 장비를 이용한 조사와 모니터링 시에는 많은 지점에 대해서 긴 장시간 내지 기간 녹음 기록된 데이터를 분석하는데, 녹음시간에 버금가는 많은 청취시간이 필요하며, 현재는 녹음 시간만큼 조사자가 녹음자료를 듣고 분석하여 장기간 조사한 대량의 데이터에 대해서 현실적으로 분석 불가능한 문제점이 있다.In the case of investigation and monitoring using bio-acoustic equipment, it is necessary to analyze the recorded data for a long time or for a long period of time for many points. Therefore, there is a problem that it is impossible to realistically analyze a large amount of data that has been investigated for a long period of time.
최근에는 소리 대신 CCTV와 같은 다수의 카메라를 통해 영상을 수집하여 야생 동물의 출현을 감시하는 기술들이 다수 소개되었으나, 이러한 카메라 촬영을 통한 야생 동물 감시의 경우, 야외라는 악조건에서 카메라 렌즈 부분이 쉽게 오염되어 선명한 영상 수집이 난해하고, 이에 따라 출현 야생 동물의 정확한 분석이 어려운 문제점이 있다.Recently, many technologies have been introduced to monitor the appearance of wild animals by collecting images through multiple cameras such as CCTV instead of sound. Therefore, it is difficult to collect clear images, and accordingly, there is a problem in that it is difficult to accurately analyze the wild animals that appear.
또한, 몸집이 작은 야생 돌물의 경우에 풀이나 나무에 가려져 카메라 촬영을 통한 식별이 난해하거나 불가능한 문제점이 있다.In addition, in the case of a small wild stone, there is a problem in that it is difficult or impossible to identify through a camera because it is covered by grass or trees.
상기와 같은 종래 생태 조사 시스템과 관련된 선행 문헌은 다음과 같다.The prior literature related to the conventional ecological survey system as described above is as follows.
문헌1 : 대한민국 등록특허공보 제10-1822037호(명칭 : IoT 기반의 자연생태 조사 시스템 ; 출원일 : 2016년09월05일)Document 1: Republic of Korea Patent Publication No. 10-1822037 (Title: IoT-based natural ecology research system; filing date: September 05, 2016)
문헌2 : 대한민국 등록특허공보 제10-1984983호(명칭 : 야생동물 모니터링 시스템 및 그 방법 ; 출원일 : 2017년09월22일)Document 2: Republic of Korea Patent Publication No. 10-1984983 (Title: Wild animal monitoring system and method; Application date: September 22, 2017)
본 발명은 상기와 같은 종래 기술의 문제점을 해결하고자 창출된 것으로, 조사 현장에 출현하는 야생동물(조류, 박쥐, 개구리, 곤충 등)의 소리와 초음파를 수집하여, 조사지역의 야생동물 종의 출현 유무와 장기적인 번식 여부 및 개체수의 변화 등을 조사하고 분석하는 시스템으로서, 동물의 소리를 녹음하는 장비와 무선전송장치, 무선전송된 소리신호 파일에서 출현하는 야생동물의 종을 동정하고, 동정된 종의 자료를 기반으로 개체수와 서식을 분석하는 생태조사 시스템을 제공하는데 목적을 두고 있다.The present invention was created to solve the problems of the prior art as described above, and by collecting the sounds and ultrasonic waves of wild animals (birds, bats, frogs, insects, etc.) appearing at the investigation site, the appearance of wild animal species in the investigation area It is a system that investigates and analyzes the existence, long-term breeding status, and changes in the number of individuals. It identifies the species of wild animals that appear in the sound recording equipment, wireless transmission device, and wirelessly transmitted sound signal file, and identifies the identified species. It aims to provide an ecological survey system that analyzes the population and habitat based on the data of
상기와 같은 목적 달성을 위한 본 발명은 조사지역에 분포 설치된 상태에서 주변 음향을 실시간 수집하되, 잡음을 제외한 야생동물 소리신호만 선별하여, 자체 ID신호와 함께 식별신호로 제공하는 다수의 음향수집부(100); 상기 음향수집부(100)에서 제공되는 식별신호 중 야생동물 소리신호를 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 비교하여, 야생동물 종을 특정 분류하는 출현종특정수단(210)과, 상기 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호에서 각각 특징을 분석하고, 각각의 야생동물 소리신호에 개별인식코드를 부여하는 동물개별인식수단(220)과, 상기 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하여, 해당 출현 종 및 개별동물의 이동동선 및 주 서식지를 추출함과 동시에, 이들의 출현 빈도와 개체수를 산출하는 생태분석수단(230)을 포함하는 생태분석부(200); 상기 생태분석부(200)에서 제공하는 분석데이터를 전송받아 컴퓨터 시스템에 탑재된 관리 및 종합 분석 알고리즘 내지 프로그램을 통해 원격적으로 관리 분석하는 관리부(300); 를 포함하는 것을 특징으로 한다.The present invention for achieving the above object collects ambient sounds in real time in a distributed and installed state in the irradiation area, but selects only wild animal sound signals excluding noise, and provides a plurality of sound collection units as identification signals together with their own ID signals. (100); Appearance species specific means 210 for specifically classifying wild animal species by comparing the wild animal sound signal among the identification signals provided by the sound collecting unit 100 with the stored wild animal sound book or wild animal sound data in the table; The individual animal recognition means 220 for analyzing the characteristics of each of the wild animal sound signals that are specifically classified by the appearance species specifying means 210, and assigning an individual recognition code to each wild animal sound signal, and collecting the plurality of sounds By analyzing the sequence of sound signals provided by the unit 100 and changes in the level (intensity) of wild animal sounds provided by the appearing animal specifying means 210 and the individual animal recognition means 220, the corresponding appearing species and individual animals an ecology analysis unit 200 including an ecology analysis means 230 for extracting the movement lines and main habitats of , and calculating the frequency and number of their appearance; a management unit 300 that receives the analysis data provided by the ecological analysis unit 200 and remotely manages and analyzes it through a management and comprehensive analysis algorithm or program mounted on a computer system; It is characterized in that it includes.
본 발명 중 상기 음향수집부(100)는 조사지역에 일정 간격 내지 영역별로 설치되는 자체 ID가 부여된 다수의 녹음장치 또는 마이크와, 상기 녹음장치 또는 마이크에서 수집된 음향신호에서 주변 잡음을 제외한 야생동물 소리신호만 여과하는 음향필터회로와, 상기 음향필터회로에서 소리신호가 인가되면 해당 시간과 자체 ID신호를 결합하여 식별신호로 변환하는 음향신호처리회로 및 상기 식별신호를 전송하는 인터페이스 또는 통신회로를 포함하는 것을 특징으로 한다.In the present invention, the sound collection unit 100 includes a plurality of recording devices or microphones provided with their IDs installed at regular intervals or for each area in the irradiation area, and the sound signal collected by the recording apparatus or microphone, except for ambient noise. A sound filter circuit that filters only animal sound signals, a sound signal processing circuit that converts an identification signal by combining a corresponding time and its own ID signal when a sound signal is applied from the sound filter circuit, and an interface or communication circuit that transmits the identification signal It is characterized in that it includes.
본 발명의 상기 음향수집부(100)는 별도의 지주 또는 기설치된 울타리 또는 전신주를 포함한 시설물에 설치되거나, 나무를 포함한 자연 지형물에 설치되는 것을 특징으로 한다.The sound collecting unit 100 of the present invention is characterized in that it is installed in a separate prop or a facility including a pre-installed fence or telephone pole, or is installed in a natural feature including a tree.
본 발명 중 상기 생태분석부(200)의 출현종특정수단(210)은 음향수집부(100)에서 야생동물 소리신호가 제공되면, 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 진폭, 주파수, 위상을 포함한 야생동물 종의 소리 특성과 일치되거나 설정 범위에 속하는 종을 특정 분류하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것을 특징으로 한다.In the present invention, when a wild animal sound signal is provided from the sound collecting unit 100, the species specific means 210 of the ecological analysis unit 200 compares the stored wild animal sound book or the wild animal sound data in the table, It is characterized in that it is an acoustic comparison and analysis circuit loaded with an algorithm or program that specifically classifies a species that matches the sound characteristics of a wild animal species including amplitude, frequency, and phase or falls within a set range.
본 발명 중 상기 생태분석부(200)의 동물개별인식수단(220)은 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호가 제공되면, 해당 야생동물의 소리 특성을 분석하고 개별인식코드를 부여하여 저장 후, 차후 제공되는 소리신호와 비교하여 특정 종의 특정 동물을 인식하도록 하는 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것을 특징으로 한다.In the present invention, the individual animal recognition means 220 of the ecology analysis unit 200 analyzes the sound characteristics of the wild animal and analyzes the individual recognition code when a specific classified wild animal sound signal is provided by the appearance species specifying means 210 . It is characterized in that it is a sound comparison and analysis circuit loaded with an algorithm or program that provides information to recognize a specific animal of a specific species by giving and storing it, and comparing it with a sound signal provided later.
본 발명 중 상기 생태분석부(200)의 생태분석수단(230)은 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하되, 해당 출현 종 및 개별동물이 어느 방향에서 어느 방향으로 이동하였는지를 분석하여 이동동선을 추출하고, 주로 어느 영역에서 집중적으로 소리신호가 수집되는지를 분석하여 주 서식지를 추출함과 동시에, 특정 이동동선과 특정 영역에서 출현 빈도를 산출하고, 동물개별인식수단(220)에서 특정된 종과 특정된 동물을 분석하여 개체수를 산출하여 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것을 특징으로 한다.In the present invention, the ecological analysis means 230 of the ecological analysis unit 200 includes the sequence of the sound signals provided from the plurality of sound collection units 100 and the appearance animal specifying means 210 and the individual animal recognition means 220. Analyze changes in the level (intensity) of sounds of wild animals provided in At the same time, the main habitat is extracted by analyzing It is characterized in that it is an acoustic comparison and analysis circuit loaded with an algorithm or program.
본 발명의 상기 음향비교분석회로의 알고리즘 내지 프로그램은 wav, zc, mp3를 포함한 디지털 파일로 제공되는 야생동물의 소리를 자동으로 분석해주는 것으로서, 사전에 Deep learning 기법으로 학습시킨 프로그램으로 음성파일을 spectrogram으로 변환하여 영상으로 표출한 후, 이 패턴을 학습시키는 프로그램으로 spectogram 내 펄스의 간격, 펄스 내 최고주파수, 최저주파수, 최대 dB 시 주파수를 분석하는 것을 특징으로 한다.The algorithm or program of the sound comparison and analysis circuit of the present invention automatically analyzes the sounds of wild animals provided as digital files including wav, zc, and mp3. It is a program that learns this pattern after converting it into an image, and it is characterized by analyzing the pulse interval in the spectogram, the highest frequency in the pulse, the lowest frequency, and the frequency at the maximum dB.
본 발명 중 상기 관리부(300)는 생태분석부(200)에서 제공하는 분석데이터 또는 소리신호를 전송받아 저장한 후, 로딩하여 관리 및 종합 분석하는 알고리즘 내지 프로그램이 탑재된 원격관제소에 설치된 서버를 포함한 컴퓨터 시스템 또는 관리자 또는 연구자의 휴대단말기인 것을 특징으로 한다.In the present invention, the management unit 300 receives and stores the analysis data or sound signal provided by the ecological analysis unit 200, and then loads it, including a server installed in a remote control center equipped with an algorithm or program for management and comprehensive analysis. It is characterized in that it is a computer system or a portable terminal of an administrator or researcher.
상기와 같은 과제해결수단에 의한 본 발명은 직접 현장조사를 통해서 야생동물의 출현 유무, 번식 유무를 판단하던 조사방법에서 벗어나, 조사지역에 폭넓게 분포된 음향수집부(100)를 통해 장기간 출현하는 야생동물의 소리를 수집 녹음하여 종을 특정 즉 동정함으로써, 현장조사횟수를 획기적으로 줄이면서도 용이하게 조사가 이루어지도록 하며, 조사지점과 조사결과의 객관적 비교가 가능하도록 하는 효과를 얻는다.The present invention by means of the above-described problem solving means departs from the method of judging the presence or absence of wild animals through direct field investigations and determines whether wild animals appear for a long period of time through the sound collection unit 100 widely distributed in the investigation area. By collecting and recording animal sounds and identifying the species, the number of field investigations is drastically reduced and the investigation is made easier, and the effect of enabling objective comparison between the investigation site and the investigation results is obtained.
또한, 본 발명은 상기 음향수집부(100)을 광범위한 조사지역에 분포 설치하여 주변 음향을 수집하되, 주변의 잡음을 제외한 출현 야생동물의 소리만 추출함으로써, 관리자가 야생동물의 소리가 수집 저장된 정보를 일일이 살피지 않고 즉각적으로 야생동물의 출현 상황과 출현 종 및 특정 동물을 확인할 수 있도록 하여 조사 관리와 관련된 작업성을 향상시키는 효과를 얻는다.In addition, the present invention collects ambient sounds by distributing and installing the sound collecting unit 100 in a wide irradiation area, but extracting only the sounds of the wild animals excluding the surrounding noise, so that the manager collects and stores the sounds of the wild animals It is possible to immediately check the appearance status of wild animals, the species and specific animals without having to look at them one by one, thereby improving the workability related to survey management.
또한, 본 발명의 상기 출현종특정수단(210)은 음향수집부(100)에서 야생동물 소리신호가 제공되면, 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 즉, 진폭, 주파수, 위상을 포함한 야생동물 종의 소리 특성(예 : 새 노랫소리와 행동 소리, 개구리의 노랫소리와 행동소리, 박쥐의 초음파 소리, 고래의 초음파 소리, 매미와 귀뚜라미 같은 곤충의 소리 등)과 일치되거나 설정 범위에 속하는 종을 특정 분류함으로써, 관리자가 별도 분류 작업 없이 손쉽게 출현한 생물종을 분류 확인 가능하도록 하는 효과를 얻는다.In addition, when a wild animal sound signal is provided by the sound collection unit 100, the species specific means 210 of the present invention compares it with the wild animal sound data in the stored wild animal sound book or table, that is, the amplitude and frequency. , matches the sound characteristics of a wildlife species, including topology (e.g., birds singing and behavioral sounds, frog singing and behavioral sounds, bat ultrasonic sounds, whale ultrasonic sounds, and insects such as cicadas and crickets), or By categorizing the species within the set range, the effect is obtained so that the manager can easily classify and confirm the species that have appeared without a separate classification task.
또한, 본 발명의 상기 동물개별인식수단(220)은 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호가 제공되면, 현재까지 수집 저장된 특정 야생동물의 소리신호와 비교 분석하여, 다른 야생동물의 소리신호인 경우, 개별인식코드를 부여하여 저장 후, 차후 제공되는 소리신호와 비교하여 특정 종의 특정 동물을 인식 가능하도록 함으로써, 특정 종의 개체수 확인이 용이하게 이루어지도록 하는 효과를 얻는다.In addition, the individual animal recognition means 220 of the present invention, when a specific classified wild animal sound signal is provided by the appearance species specific means 210, compares and analyzes the sound signal of a specific wild animal that has been collected and stored so far, In the case of an animal sound signal, an individual recognition code is given and stored, and a specific animal of a specific species can be recognized by comparing it with a sound signal provided later, thereby obtaining the effect of easily confirming the number of a specific species.
또한, 본 발명의 상기 생태분석수단(230)은 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하되, 해당 출현 종 및 개별동물이 어느 방향에서 어느 방향으로 이동하였는지를 분석하여 이동동선을 추출하고, 주로 어느 영역에서 집중적으로 소리신호가 수집되는지를 분석하여 주 서식지를 추출함과 동시에, 특정 이동동선과 특정 영역에서 출현 빈도를 산출하고, 동물개별인식수단(220)에서 특정된 종과 특정된 동물을 분석하여 개체수를 산출하여 정보를 제공함으로써, CCTV를 포함한 영상 촬영수단에 의한 영상 수집 없이도 저용량 음향 데이터를 통해 야생동물의 이동동선과 출현빈도 및 개체수의 조사가 이루어지도록 하는 효과를 얻는다.In addition, the ecological analysis means 230 of the present invention provides a sequence of sound signals provided by a plurality of sound collection units 100 and wild animals provided by the appearance animal specifying means 210 and individual animal recognition means 220 . Analyze the change in sound level (intensity), but extract the movement line by analyzing the direction in which the species and individual animals moved in the main habitat At the same time, by calculating the frequency of appearance in a specific movement and in a specific area, and by analyzing the specified species and specified animal in the individual animal recognition means 220 to calculate the number of individuals and provide information, video including CCTV It has the effect of allowing the investigation of the movement of wild animals, their frequency of appearance, and the number of individuals through low-volume acoustic data without the need for image collection by a photographing means.
또한, 본 발명은 상기 관리부(300)가 생태분석부(200) 자체에서 정리된 분석데이터를 전송받아 저장 관리하면서 필요한 경우 조사 분석 자료로 활용함은 물론, 상기 생태분석부(200)에서 전송되는 소리신호를 직접 분석하여 관리할 수 있도록 함으로써, 다중적 조사 분석 관리가 이루어지도록 하며 조사 분석 데이터의 신뢰도를 향상시키는 효과를 얻는다.In addition, in the present invention, the management unit 300 receives, stores and manages the analysis data organized by the ecology analysis unit 200 itself, and uses it as research and analysis data if necessary, as well as transmits from the ecology analysis unit 200 . By allowing the sound signal to be directly analyzed and managed, multiple survey analysis management is made and the reliability of the survey analysis data is improved.
도 1은 본 발명의 구성을 간략히 도시한 시스템 블록도.1 is a system block diagram schematically showing the configuration of the present invention;
도 2는 본 발명이 적용되는 예와 야생동물 소리 감지 상태를 도시한 구성도.2 is a configuration diagram showing an example to which the present invention is applied and a state of detecting a sound of a wild animal.
도 3은 본 발명 중 생태분석부의 구성 및 신호 전송에 대한 일례를 도시한 구성도.Figure 3 is a configuration diagram showing an example of the configuration and signal transmission of the ecological analysis unit in the present invention.
도 4는 본 발명 중 생태분석부의 구성 및 신호 전송에 대한 다른 예를 도시한 구성도.Figure 4 is a configuration diagram showing another example of the configuration and signal transmission of the ecological analysis unit in the present invention.
도 5는 본 발명의 음향수집부와 생태분석부 및 관리부의 전반적인 동작상태를 도시한 구성도.5 is a block diagram showing the overall operating state of the sound collection unit, the ecological analysis unit and the management unit of the present invention.
도 6은 본 발명 중 관리부의 자체 소리신호 분석 단계를 도시한 순서도.6 is a flow chart showing the self-sound signal analysis step of the management unit in the present invention.
이와 같이 제시한 첨부 도면을 참고로 하여 본 발명을 설명하면 다음과 같다. Hereinafter, the present invention will be described with reference to the accompanying drawings presented as described above.
먼저, 본 발명인 생태 조사 시스템(100)은 첨부 도면 도 1에 도시된 바와 같이, 조사지역에 분포 설치된 상태에서 주변 음향을 실시간 수집하되, 잡음을 제외한 야생동물 소리신호만 선별하여, 자체 ID신호와 함께 식별신호로 제공하는 다수의 음향수집부(100); 상기 음향수집부(100)에서 제공되는 식별신호 중 야생동물 소리신호를 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 비교하여, 야생동물 종을 특정 분류하는 출현종특정수단(210)과, 상기 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호에서 각각 특징을 분석하고, 각각의 야생동물 소리신호에 개별인식코드를 부여하는 동물개별인식수단(220)과, 상기 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하여, 해당 출현 종 및 개별동물의 이동동선 및 주 서식지를 추출함과 동시에, 이들의 출현 빈도와 개체수를 산출하는 생태분석수단(230)을 포함하는 생태분석부(200); 상기 생태분석부(200)에서 제공하는 분석데이터를 전송받아 컴퓨터 시스템에 탑재된 관리 및 종합 분석 알고리즘 내지 프로그램을 통해 원격적으로 관리 분석하는 관리부(300); 를 포함하는 것일 수 있다.First, as shown in the accompanying drawings, the ecological survey system 100 of the present invention collects ambient sounds in real time in a distributed and installed state in the survey area, but selects only wild animal sound signals excluding noise, a plurality of sound collecting units 100 provided together as an identification signal; Appearance species specific means 210 for specifically classifying wild animal species by comparing the wild animal sound signal among the identification signals provided by the sound collecting unit 100 with the stored wild animal sound book or wild animal sound data in the table; The individual animal recognition means 220 for analyzing the characteristics of each of the wild animal sound signals that are specifically classified by the appearance species specifying means 210, and assigning an individual recognition code to each wild animal sound signal, and collecting the plurality of sounds By analyzing the sequence of sound signals provided by the unit 100 and changes in the level (intensity) of wild animal sounds provided by the appearing animal specifying means 210 and the individual animal recognition means 220, the corresponding appearing species and individual animals an ecology analysis unit 200 including an ecology analysis means 230 for extracting the movement lines and main habitats of , and calculating the frequency and number of their appearance; a management unit 300 that receives the analysis data provided by the ecological analysis unit 200 and remotely manages and analyzes it through a management and comprehensive analysis algorithm or program mounted on a computer system; may include.
여기서, 본 발명 중 상기 음향수집부(100)는 조사지역에 일정 간격 내지 영역별로 설치되는 자체 ID가 부여된 다수의 녹음장치 또는 마이크와, 상기 녹음장치 또는 마이크에서 수집된 음향신호에서 주변 잡음을 제외한 야생동물 소리신호만 여과하는 음향필터회로와, 상기 음향필터회로에서 소리신호가 인가되면 해당 시간과 자체 ID신호를 결합하여 식별신호로 변환하는 음향신호처리회로 및 상기 식별신호를 전송하는 인터페이스 또는 통신회로를 포함하는 것일 수 있다.Here, in the present invention, the sound collecting unit 100 includes a plurality of recording devices or microphones provided with their IDs installed at regular intervals or by areas in the irradiation area, and ambient noise from the sound signals collected by the recording apparatus or microphone. A sound filter circuit that filters only the sound signals of wild animals except for the sound signal, and when a sound signal is applied from the sound filter circuit, a sound signal processing circuit that combines the corresponding time and its ID signal to convert it into an identification signal, and an interface for transmitting the identification signal; or It may include a communication circuit.
한편, 본 발명 중 상기 생태분석부(200)의 출현종특정수단(210)은 음향수집부(100)에서 야생동물 소리신호가 제공되면, 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 종을 특정 분류하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것일 수 있다.On the other hand, in the present invention, the species specific means 210 of the ecological analysis unit 200 of the present invention compares with the wild animal sound data in the stored wild animal sound book or table when the wild animal sound signal is provided from the sound collecting unit 100 . Therefore, it may be an acoustic comparison and analysis circuit loaded with an algorithm or program for specific classification of a species.
또한, 본 발명 중 상기 생태분석부(200)의 동물개별인식수단(220)은 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호가 제공되면, 해당 야생동물의 소리 특성을 분석하고 개별인식코드를 부여하여 저장 후, 차후 제공되는 소리신호와 비교하여 특정 종의 특정 동물을 인식하도록 하는 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것일 수 있다.In addition, in the present invention, the individual animal recognition means 220 of the ecological analysis unit 200 analyzes the sound characteristics of the wild animal and analyzes the sound characteristics of the wild animal when a specific classified wild animal sound signal is provided by the appearance species specifying means 210 . It may be a sound comparison and analysis circuit loaded with an algorithm or program that provides information for recognizing a specific animal of a specific species by assigning a recognition code and storing it, and comparing it with a sound signal provided later.
또한, 본 발명 중 상기 생태분석부(200)의 생태분석수단(230)은 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하여, 이동동선 및 주 서식지를 추출함과 동시에, 출현 빈도 및 개체수를 산출하여 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것일 수 있다.In addition, in the present invention, the ecological analysis means 230 of the ecological analysis unit 200 includes the sequence of the sound signals provided by the plurality of sound collection units 100 and the appearance animal specific means 210 and the individual animal recognition means ( 220), a sound comparison and analysis circuit equipped with an algorithm or program that analyzes changes in the level (intensity) of the sounds of wild animals, extracts movement routes and main habitats, and calculates the frequency and number of appearances and provides information may be
또 한편, 본 발명 중 상기 관리부(300)는 생태분석부(200)에서 제공하는 분석데이터 또는 소리신호를 전송받아 저장한 후, 로딩하여 관리 및 종합 분석하는 알고리즘 내지 프로그램이 탑재된 원격관제소에 설치된 서버를 포함한 컴퓨터 시스템 또는 관리자 또는 연구자의 휴대단말기인 것일 수 있다.On the other hand, in the present invention, the management unit 300 receives and stores the analysis data or sound signals provided by the ecological analysis unit 200, and then loads and manages and comprehensively analyzes it. It may be a computer system including a server or a portable terminal of an administrator or researcher.
이와 같은 본 발명의 작용을 설명하면 다음과 같다.The operation of the present invention will be described as follows.
본 발명은 첨부 도면 도 1에 도시된 바와 같이, 조사지역에 분포 설치된 상태에서 주변 음향을 실시간 수집하되, 잡음을 제외한 야생동물 소리신호만 선별하여, 자체 ID신호와 함께 식별신호로 제공하는 다수의 음향수집부(100); 상기 음향수집부(100)에서 제공되는 식별신호 중 야생동물 소리신호를 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 비교하여, 야생동물 종을 특정 분류하는 출현종특정수단(210)과, 상기 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호에서 각각 특징을 분석하고, 각각의 야생동물 소리신호에 개별인식코드를 부여하는 동물개별인식수단(220)과, 상기 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하여, 해당 출현 종 및 개별동물의 이동동선 및 주 서식지를 추출함과 동시에, 이들의 출현 빈도와 개체수를 산출하는 생태분석수단(230)을 포함하는 생태분석부(200); 상기 생태분석부(200)에서 제공하는 분석데이터를 전송받아 컴퓨터 시스템에 탑재된 관리 및 종합 분석 알고리즘 내지 프로그램을 통해 원격적으로 관리 분석하는 관리부(300); 를 포함하는 생태 조사 시스템(100)이다.As shown in the accompanying drawings, the present invention collects ambient sounds in real time in a distributed and installed state in the irradiation area, but selects only wild animal sound signals excluding noise, and provides a plurality of identification signals together with their own ID signals. sound collection unit 100; Appearance species specific means 210 for specifically classifying wild animal species by comparing the wild animal sound signal among the identification signals provided by the sound collecting unit 100 with the stored wild animal sound book or wild animal sound data in the table; The individual animal recognition means 220 for analyzing the characteristics of each of the wild animal sound signals that are specifically classified by the appearance species specifying means 210, and assigning an individual recognition code to each wild animal sound signal, and collecting the plurality of sounds By analyzing the sequence of sound signals provided by the unit 100 and changes in the level (intensity) of wild animal sounds provided by the appearing animal specifying means 210 and the individual animal recognition means 220, the corresponding appearing species and individual animals an ecology analysis unit 200 including an ecology analysis means 230 for extracting the movement lines and main habitats of , and calculating the frequency and number of their appearance; a management unit 300 that receives the analysis data provided by the ecological analysis unit 200 and remotely manages and analyzes it through a management and comprehensive analysis algorithm or program mounted on a computer system; It is an ecological survey system 100 comprising a.
이와 같이 된 본 발명은 직접 현장조사를 통해서 야생동물의 출현 유무, 번식 유무를 판단하던 조사방법에서 벗어나, 조사지역에 폭넓게 분포된 음향수집부(100)를 통해 장기간 출현하는 야생동물의 소리를 수집 녹음하여 종을 특정 즉 동정함으로써, 현장조사횟수를 획기적으로 줄이면서도 용이하게 조사가 이루어지도록 하며, 조사지점과 조사결과의 객관적 비교가 가능하도록 하는 것이 가능하다.In this way, the present invention collects the sounds of wild animals that appear for a long period of time through the sound collection unit 100 widely distributed in the investigation area, away from the method of judging whether wild animals appear or not, through direct field investigations. By recording and identifying species, it is possible to dramatically reduce the number of on-site surveys and make surveys easier, and it is possible to make objective comparisons between survey sites and survey results possible.
여기서, 본 발명 중 상기 음향수집부(100)는 조사지역에 일정 간격 내지 영역별로 설치되는 자체 ID가 부여된 다수의 녹음장치 또는 마이크와, 상기 녹음장치 또는 마이크에서 수집된 음향신호에서 주변 잡음을 제외한 야생동물 소리신호만 여과하는 음향필터회로와, 상기 음향필터회로에서 소리신호가 인가되면 해당 시간과 자체 ID신호를 결합하여 식별신호로 변환하는 음향신호처리회로 및 상기 식별신호를 전송하는 인터페이스 또는 통신회로를 포함하는 것을 바람직한 실시예로 한다.Here, in the present invention, the sound collecting unit 100 includes a plurality of recording devices or microphones provided with their IDs installed at regular intervals or by areas in the irradiation area, and ambient noise from the sound signals collected by the recording apparatus or microphone. A sound filter circuit that filters only the sound signals of wild animals except for the sound signal, and when a sound signal is applied from the sound filter circuit, a sound signal processing circuit that combines the corresponding time and its ID signal to convert it into an identification signal, and an interface for transmitting the identification signal; or It is a preferred embodiment to include a communication circuit.
이때, 본 발명의 상기 음향수집부(100)는 방수, 방진기능을 가져 눈비에 대한 저항성을 갖고, 설정된 소리 이상의 소리가 들리면 자동으로 저장되거나 작동시간을 프로그램적으로 설정할 수 있는 것이 바람직하다.At this time, it is preferable that the sound collecting unit 100 of the present invention has a waterproof and dustproof function to have resistance to rain and snow, and to be automatically saved or programmatically set for an operating time when a sound greater than or equal to a set sound is heard.
또한, 본 발명의 상기 음향수집부(100)는 별도의 지주 또는 기설치된 울타리 또는 전신주를 포함한 시설물에 설치되거나, 나무를 포함한 자연 지형물에 설치되는 것을 바람직한 실시예로 한다.In addition, it is a preferred embodiment that the sound collection unit 100 of the present invention is installed in a separate pole or a facility including a pre-installed fence or electric pole, or installed in a natural feature including a tree.
이와 같이 된 본 발명의 음향수집부(100)는 첨부 도면 도 2에 도시된 바와 같이, 광범위한 조사지역에 분포 설치되어 주변 음향을 수집하되, 주변의 잡음 예컨대, 바람소리나 나뭇가지나 풀들의 움직임 소리나 물소리 등 빈번히 발생되는 소리는 잡음으로 간주하고 출현하는 야생동물의 소리만 추출하여, 소리가 발생된 시간과 자체 ID신호를 결합하여 식별신호로 변환하여 생태분석부(200)로 제공한다.As shown in FIG. 2 of the accompanying drawings, the sound collection unit 100 of the present invention is distributed and installed in a wide irradiation area to collect ambient sound, and ambient noise, for example, wind noise or the sound of movement of branches or grass. A sound that occurs frequently, such as a sound of water or water, is regarded as noise, only the sound of an appearing wild animal is extracted, the time at which the sound is generated and its own ID signal are combined, converted into an identification signal, and provided to the ecological analysis unit 200 .
이와 같은 본 발명의 음향수집부(100)는 광범위한 조사지역에 분포 설치되어 주변 음향을 수집하되, 주변의 잡음을 제외한 출현 야생동물의 소리만 추출함으로써, 관리자가 야생동물의 소리가 수집 저장된 정보를 일일이 살피지 않고 즉각적으로 확인할 수 있도록 하는 것이 가능하다.As described above, the sound collection unit 100 of the present invention is distributed and installed in a wide irradiation area to collect ambient sounds, but by extracting only the sounds of the wild animals excluding the surrounding noise, the manager collects and stores the information of the sounds of the wild animals. It is possible to make it possible to check immediately without having to look at them one by one.
한편, 본 발명 중 상기 생태분석부(200)는 첨부 도면 도 3에 도시된 바와 같이, 다수의 음향수집부(100) 각각과 패키지 결합(모듈화)되어, 해당 음향분석부(100)에서 제공되는 소리신호를 인터페이스를 통해 제공받아, 통신망을 통해 관리부(300)로 전송하는 것을 일실시예로 하나, 첨부 도면 도 4에 도시된 바와 같이, 다수의 음향수집부(100)와 별도로 조사지역 중앙에 설치되어, 각각의 음향분석부(100)에서 제공되는 ID를 포함한 식별신호를 전송받아 통신망을 통해 관리부(300)로 전송하는 것도 바람직하다.On the other hand, in the present invention, the ecology analysis unit 200 is packaged (modularized) with each of a plurality of sound collecting units 100, as shown in FIG. 3 of the accompanying drawings, and provided by the corresponding sound analysis unit 100. In one embodiment, a sound signal is provided through an interface and transmitted to the management unit 300 through a communication network. It is also preferable to receive the identification signal including the ID provided by each sound analysis unit 100 and transmit it to the management unit 300 through the communication network.
이때, 본 발명 중 상기 생태분석부(200)의 출현종특정수단(210)은 음향수집부(100)에서 야생동물 소리신호가 제공되면, 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 종을 특정 분류하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것을 실시예로 한다.At this time, when a wild animal sound signal is provided from the sound collection unit 100, the species specific means 210 of the ecological analysis unit 200 of the present invention compares the stored wild animal sound book or the wild animal sound data of the table. Therefore, it is assumed that an acoustic comparison and analysis circuit equipped with an algorithm or program for specific classification of a species is used as an embodiment.
이와 같은 본 발명의 상기 출현종특정수단(210)은 음향수집부(100)에서 야생동물 소리신호가 제공되면, 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 즉, 진폭, 주파수, 위상을 포함한 야생동물 종의 소리 특성(예 : 개구리 울음소리, 쥐 울음소리, 족제비 울음소리, 새의 울음소리, 매미의 울음소리, 박쥐의 초음파 등)과 일치되거나 설정 범위에 속하는 종을 특정 분류함으로써, 관리자가 별도 분류 작업없이 손쉽게 분류 확인 가능하도록 한다.When a wild animal sound signal is provided from the sound collecting unit 100, the species specific means 210 of the present invention compares the stored wild animal sound book or wild animal sound data in the table, that is, the amplitude and frequency. , specify a species that matches the sound characteristics of a wildlife species, including topology (e.g. frog calls, rat calls, weasel calls, bird calls, cicadas calls, bat ultrasounds, etc.) or falls within a set range. By categorizing, the administrator can easily check the classification without a separate classification task.
또한, 본 발명 중 상기 생태분석부(200)의 동물개별인식수단(220)은 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호가 제공되면, 해당 야생동물의 소리 특성을 분석하고 개별인식코드를 부여하여 저장 후, 차후 제공되는 소리신호와 비교하여 특정 종의 특정 동물을 인식하도록 하는 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것을 실시예로 한다.In addition, in the present invention, the individual animal recognition means 220 of the ecological analysis unit 200 analyzes the sound characteristics of the wild animal and analyzes the sound characteristics of the wild animal when a specific classified wild animal sound signal is provided by the appearance species specifying means 210 . An embodiment is an acoustic comparison and analysis circuit equipped with an algorithm or program that provides information to recognize a specific animal of a specific species by assigning a recognition code and storing it, and comparing it with a sound signal provided later.
이와 같은 본 발명의 상기 동물개별인식수단(220)은 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호가 제공되면, 현재까지 수집 저장된 특정 야생동물의 소리신호와 비교 분석하여, 다른 야생동물의 소리신호인 경우, 개별인식코드를 부여하여 저장 후, 차후 제공되는 소리신호와 비교하여 특정 종의 특정 동물을 인식 가능하도록 함으로써, 특정 종의 개체수 확인이 용이하게 이루어지도록 하는 것이 가능하다.As described above, the individual animal recognition means 220 of the present invention compares and analyzes sound signals of specific wild animals collected and stored so far when a specific classified wild animal sound signal is provided by the appearing species specific means 210, and other wild animals. In the case of an animal sound signal, it is possible to easily identify the number of a specific species by assigning an individual recognition code to storing it, and then comparing it with a sound signal provided later to recognize a specific animal of a specific species.
또한, 본 발명 중 상기 생태분석부(200)의 생태분석수단(230)은 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하여, 이동동선 및 주 서식지를 추출함과 동시에, 출현 빈도 및 개체수를 산출하여 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것을 실시예로 한다.In addition, in the present invention, the ecological analysis means 230 of the ecological analysis unit 200 includes the sequence of the sound signals provided by the plurality of sound collection units 100 and the appearance animal specific means 210 and the individual animal recognition means ( 220), a sound comparison and analysis circuit equipped with an algorithm or program that analyzes changes in the level (intensity) of the sounds of wild animals, extracts movement routes and main habitats, and calculates the frequency and number of appearances and provides information Let it be an example.
이와 같은 본 발명의 상기 생태분석수단(230)은 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨(강도) 변화를 분석하되, 해당 출현 종 및 개별동물이 어느 방향에서 어느 방향으로 이동하였는지를 분석하여 이동동선을 추출하고, 주로 어느 영역에서 집중적으로 소리신호가 수집되는지를 분석하여 주 서식지를 추출함과 동시에, 특정 이동동선과 특정 영역에서 출현 빈도를 산출하고, 동물개별인식수단(220)에서 특정된 종과 특정된 동물을 분석하여 개체수를 산출하여 정보를 제공함으로써, CCTV를 포함한 영상 촬영수단에 의한 영상 수집 없이도 저용량 음향 데이터를 통해 야생동물의 이동동선과 출현빈도 및 개체수의 조사가 이루어지도록 하는 것이 가능하다(도 2 재 참조).As described above, the ecological analysis means 230 of the present invention is a sequence of sound signals provided by a plurality of sound collection units 100 and wild animals provided by the appearance animal specifying means 210 and the individual animal recognition means 220 . Analyze the change in sound level (intensity), but extract the movement line by analyzing the direction in which the species and individual animals moved in the main habitat At the same time, by calculating the frequency of appearance in a specific movement and in a specific area, and by analyzing the specified species and specified animal in the individual animal recognition means 220 to calculate the number of individuals and provide information, video including CCTV It is possible to investigate the movement of wild animals, their frequency of appearance, and the number of individuals through low-volume acoustic data without the need for image collection by a photographing means (refer to FIG. 2 again).
이때, 본 발명의 상기 음향비교분석회로의 알고리즘 내지 프로그램은 wav, zc, mp3를 포함한 디지털 파일로 제공되는 야생동물의 소리를 자동으로 분석해주는 것으로서, 사전에 Deep learning 기법으로 학습시킨 프로그램으로 음성파일을 spectrogram으로 변환하여 영상으로 표출한 후, 이 패턴을 학습시키는 프로그램으로 spectogram 내 펄스의 간격, 펄스 내 최고주파수, 최저주파수, 최대 dB 시 주파수를 분석하는 것을 실시예로 한다.At this time, the algorithm or program of the sound comparison and analysis circuit of the present invention automatically analyzes the sounds of wild animals provided as digital files including wav, zc, and mp3, and is a program learned by deep learning in advance and is a voice file. After converting into a spectrogram and expressing it as an image, it is an embodiment to analyze the interval of pulses in the spectogram, the highest frequency in the pulse, the lowest frequency, and the frequency at the maximum dB with a program for learning this pattern.
참고로, 본 발명의 상기 생태분석부(200)에 인공지능 기계학습 방법인 Deep learning 기법을 적용하되, 합성곱 신경망 CNN(Convolutional Neural Network)을 통해, 수집 제공되는 소리신호에 대해 filtering을 수행하되, 다수의 Filter를 반복적으로 적용하여 다양한 local 특징을 추출하여 이미지 특징(feature)을 찾아내고, CRNN(Convolutional Recurrent Neural Network)을 통해, 상기 CNN의 Input 이미지로부터 feature sequence를 추출하고, 추출한 feature sequence들을 RNN의 input으로 사용하여 이미지의 시퀀스를 예측하고, 상기 RNN 레이어의 출력과 입력 상태의 모든 조합을 참조하여 각 출력이 어떤 입력 상태를 더 많이 참조하는지에 대한 가중치를 부여하여 소리신호를 분석한다.For reference, the deep learning technique, which is an artificial intelligence machine learning method, is applied to the ecological analysis unit 200 of the present invention, but filtering is performed on the collected and provided sound signals through a convolutional neural network (CNN). , extracting various local features by repeatedly applying multiple filters to find image features, extracting feature sequences from the input image of the CNN through CRNN (Convolutional Recurrent Neural Network), and extracting the extracted feature sequences A sequence of images is predicted using the RNN input as an input, and a sound signal is analyzed by giving weight to which input state each output refers to more by referring to all combinations of the output and input states of the RNN layer.
또 한편, 본 발명 중 상기 관리부(300)는 생태분석부(200)에서 제공하는 분석데이터 또는 소리신호를 전송받아 저장한 후, 로딩하여 관리 및 종합 분석하는 알고리즘 내지 프로그램이 탑재된 원격관제소에 설치된 서버를 포함한 컴퓨터 시스템 또는 관리자 또는 연구자의 휴대단말기인 것을 실시예로 한다.On the other hand, in the present invention, the management unit 300 receives and stores the analysis data or sound signals provided by the ecological analysis unit 200, and then loads and manages and comprehensively analyzes it. An embodiment is a computer system including a server or a portable terminal of an administrator or researcher.
본 발명의 상기 관리자 또는 연구자의 휴대단말기는 원격관제소 영내 또는 주기적인 조사영역 탐사시에 사용되는 노트북 또는 테블릿 PC 또는 스마트폰인 것을 바람직한 실시예로 한다.In a preferred embodiment, the mobile terminal of the administrator or researcher of the present invention is a laptop computer, tablet PC, or smart phone used in a remote control station premises or periodic survey area exploration.
이와 같이 된 본 발명은 첨부 도면 도 5에 도시된 바와 같이, 상기 생태분석부(200)에서 소리신호가 직접 전송 제공되면, 소리신호 파일을 시간별 날짜별로 저장한 후, 연구 및 조사 분석 작업이 필요한 경우 로딩하여 관리 및 종합 분석이 이루어지도록 한다.As shown in the accompanying drawings, in the present invention, as shown in FIG. 5, when a sound signal is transmitted directly from the ecological analysis unit 200, the sound signal file is stored by time and date, and then research and investigation analysis work is required. In case of loading, management and comprehensive analysis are performed.
또한, 본 발명은 상기 생태분석부(200)에서 분석데이터가 전송되면, 자체 조사 분석 관리 테이블로 저장한 후, 연구 및 조사 분석 작업이 필요한 경우 로딩하여 관리 및 종합 분석이 이루어지도록 한다.In addition, in the present invention, when the analysis data is transmitted from the ecological analysis unit 200, it is stored as a self-report analysis management table, and then loaded when research and research analysis work is necessary so that management and comprehensive analysis are made.
이때, 본 발명은 상기 생태분석부(200)에서 소리신호가 직접 전송되어 시간별 날짜별로 저장된 상태에서 관리자 또는 연구자가 연구 및 조사 분석 작업을 하고자 할 경우, 첨부 도면 도 6에 도시된 바와 같이, 소리신호 파일을 열고, 소리신호가 출현한 구간으로 이동하여, 소리신호 파일에서 야생동물이 출현하였는지를 판단하되, 이때 야생동물이 출현하지 않은 경우, 다음 소리신호 구간으로 이동하여 야생동물이 출현하였는지를 판단하고, 만약 야생동물이 출현한 경우, 소리신호 파일의 야생동물 소리와 기저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 즉, 진폭, 주파수, 위상을 포함한 야생동물 종의 소리 특성(예 : 상기 출현종특정수단(210)은 음향수집부(100)에서 야생동물 소리신호가 제공되면, 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 즉, 진폭, 주파수, 위상을 포함한 야생동물 종의 소리 특성(예 : 새 노랫소리와 행동 소리, 개구리의 노랫소리와 행동소리, 박쥐의 초음파 소리, 고래의 초음파 소리, 매미와 귀뚜라미 같은 곤충의 소리 등)과 일치되거나 설정 범위에 속하는 종을 특정한 후, 시간별 출현종 리스트를 작성하고 파일재생이 완료되면 종료한다.At this time, in the present invention, when a manager or a researcher wants to conduct research and research analysis in a state in which the sound signal is directly transmitted from the ecological analysis unit 200 and stored by time and date, as shown in FIG. 6 of the accompanying drawings, the sound Open the signal file, move to the section where the sound signal appears, and determine whether a wild animal appears in the sound signal file, but if the wild animal does not appear at this time, move to the next sound signal section to determine whether a wild animal appears , if a wild animal appears, compare it with the wild animal sound in the sound signal file and the wild animal sound data in the pre-stored wild animal sound book or table, that is, the sound characteristics of wild animal species including amplitude, frequency, and phase ( Example: When a wild animal sound signal is provided from the sound collecting unit 100, the species specific means 210 compares the stored wild animal sound book or wild animal sound data in the table, that is, the amplitude, frequency, and phase. Matches or falls within a set range of sound characteristics (e.g., birds singing and behavioral sounds, frog singing and behavioral sounds, bat ultrasonic sounds, whale ultrasonic sounds, insect sounds such as cicadas and crickets, etc.) After specifying the species it belongs to, it creates a list of species appearing by time, and ends when file playback is complete.
이와 같은 본 발명은 상기 관리부(300)가 생태분석부(200) 자체에서 정리된 분석데이터를 전송받아 저장 관리하면서 필요한 경우 조사 분석 자료로 활용함은 물론, 상기 생태분석부(200)에서 전송되는 소리신호를 직접 분석하여 관리할 수 있도록 함으로써, 다중적 조사 분석 관리가 이루어지도록 하며 조사 분석 데이터의 신뢰도를 향상시키는 것이 가능하다.In the present invention, as described above, the management unit 300 receives, stores and manages the analysis data organized by the ecology analysis unit 200 itself, and uses it as research and analysis data if necessary, as well as the data transmitted from the ecology analysis unit 200. By allowing the sound signal to be directly analyzed and managed, it is possible to manage multiple survey analysis and improve the reliability of the survey analysis data.
이상, 본 발명을 본 발명의 원리를 예시하기 위한 바람직한 실시예와 관련하여 설명하고 도시하였지만, 본 발명은 그와 같이 도시되고 설명된 그대로의 구성 및 작용으로 한정되는 것이 아니다. Although the present invention has been described and illustrated in connection with preferred embodiments for illustrating the principles of the present invention, the present invention is not limited to the construction and operation as so shown and described.
그 밖에도, 첨부된 청구범위의 사상 및 범주를 일탈함이 없이 본 발명에 대한 다수의 변경 및 수정이 가능함을 당업자들은 잘 이해할 수 있을 것이다. In addition, it will be apparent to those skilled in the art that many changes and modifications can be made to the present invention without departing from the spirit and scope of the appended claims.
따라서, 그러한 모든 적절한 변경 및 수정과 균등물들도 본 발명의 범위에 속하는 것으로 간주되어야 할 것이다.Accordingly, all such suitable alterations and modifications and equivalents are to be considered as falling within the scope of the present invention.

Claims (10)

  1. 조사지역에 분포 설치된 상태에서 주변 음향을 실시간 수집하되, 잡음을 제외한 야생동물 소리신호만 선별하여, 자체 ID신호와 함께 식별신호로 제공하는 다수의 음향수집부(100); A plurality of sound collecting unit 100 that collects ambient sounds in real time in a distributed and installed state in the irradiation area, selects only wild animal sound signals excluding noise, and provides them as identification signals together with their own ID signals;
    상기 음향수집부(100)에서 제공되는 식별신호 중 야생동물 소리신호를 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 비교하여, 야생동물 종을 특정 분류하는 출현종특정수단(210)과, 상기 출현종특정수단(210)에서 특정 분류된 야생동물 소리신호에서 각각 특징을 분석하고, 각각의 야생동물 소리신호에 개별인식코드를 부여하는 동물개별인식수단(220)과, 상기 다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨 변화를 분석하여, 해당 출현 종 및 개별동물의 이동동선 및 주 서식지를 추출함과 동시에, 이들의 출현 빈도와 개체수를 산출하는 생태분석수단(230)을 포함하는 생태분석부(200); Appearance species specific means 210 for specifically classifying wild animal species by comparing the wild animal sound signal among the identification signals provided by the sound collecting unit 100 with the stored wild animal sound book or wild animal sound data in the table; The individual animal recognition means 220 for analyzing the characteristics of each of the wild animal sound signals that are specifically classified by the appearance species specifying means 210, and assigning an individual recognition code to each wild animal sound signal, and collecting the plurality of sounds By analyzing the sequence of sound signals provided by the unit 100 and the level change of the wild animal sound provided by the appearing animal specifying means 210 and the individual animal recognition means 220, the movement of the corresponding appearing species and individual animals is analyzed. and an ecological analysis unit 200 including an ecological analysis means 230 for extracting the main habitat and calculating their appearance frequency and number at the same time;
    상기 생태분석부(200)에서 제공하는 분석데이터를 전송받아 컴퓨터 시스템에 탑재된 관리 및 종합 분석 알고리즘 내지 프로그램을 통해 원격적으로 관리 분석하는 관리부(300); 를 포함하는 것,a management unit 300 that receives the analysis data provided by the ecological analysis unit 200 and remotely manages and analyzes it through a management and comprehensive analysis algorithm or program mounted on a computer system; comprising;
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  2. 청구항 1에 있어서,The method according to claim 1,
    상기 음향수집부(100)는,The sound collection unit 100,
    조사지역에 일정 간격 내지 영역별로 설치되는 자체 ID가 부여된 다수의 녹음장치 또는 마이크와, A number of recording devices or microphones with their own IDs installed at regular intervals or by area in the survey area;
    상기 녹음장치 또는 마이크에서 수집된 음향신호에서 주변 잡음을 제외한 야생동물 소리신호만 여과하는 음향필터회로와, an acoustic filter circuit that filters only the wild animal sound signal excluding ambient noise from the acoustic signal collected by the recording device or the microphone;
    상기 음향필터회로에서 소리신호가 인가되면 해당 시간과 자체 ID신호를 결합하여 식별신호로 변환하는 음향신호처리회로 및 When a sound signal is applied from the sound filter circuit, a sound signal processing circuit that combines the corresponding time and its ID signal to convert it into an identification signal; and
    상기 식별신호를 전송하는 인터페이스 또는 통신회로를 포함하는 것,including an interface or communication circuit for transmitting the identification signal;
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  3. 청구항 1에 있어서,The method according to claim 1,
    상기 음향수집부(100)는,The sound collection unit 100,
    별도의 지주 또는 기설치된 울타리 또는 전신주를 포함한 시설물에 설치되거나, 나무를 포함한 자연 지형물에 설치되는 것,Installed on a separate pole or a facility including an existing fence or electric pole, or installed on a natural feature including trees;
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  4. 청구항 1에 있어서,The method according to claim 1,
    상기 생태분석부(200)는,The ecological analysis unit 200,
    다수의 음향수집부(100) 각각과 패키지 결합되어, 해당 음향분석부(100)에서 제공되는 소리신호를 인터페이스를 통해 제공받아, 통신망을 통해 관리부(300)로 전송하는 것,Each of the plurality of sound collection units 100 is package-coupled to receive a sound signal provided from the corresponding sound analysis unit 100 through an interface, and transmit it to the management unit 300 through a communication network;
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  5. 청구항 1에 있어서,The method according to claim 1,
    상기 생태분석부(200)는,The ecological analysis unit 200,
    다수의 음향수집부(100)와 별도로 조사지역 중앙에 설치되어, 각각의 음향분석부(100)에서 제공되는 ID를 포함한 식별신호를 전송받아 통신망을 통해 관리부(300)로 전송하는 것,It is installed in the center of the irradiation area separately from the plurality of sound collection units 100, and receives the identification signal including the ID provided by each sound analysis unit 100 and transmits it to the management unit 300 through the communication network;
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  6. 청구항 1에 있어서,The method according to claim 1,
    상기 생태분석부(200)의 출현종특정수단(210)은,The species specific means 210 of the ecological analysis unit 200,
    음향수집부(100)에서 야생동물 소리신호가 제공되면, 저장된 야생동물 소리도감 내지 테이블의 야생동물 소리데이터와 대비하여, 진폭, 주파수, 위상을 포함한 야생동물 종의 소리 특성과 일치되거나 설정 범위에 속하는 종을 특정 분류하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것,When a wild animal sound signal is provided from the sound collection unit 100, in comparison with the stored wild animal sound book or the wild animal sound data in the table, it matches the sound characteristics of the wild animal species, including amplitude, frequency, and phase, or falls within a set range. An acoustic comparison and analysis circuit equipped with an algorithm or program for specific classification of the species to which it belongs;
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  7. 청구항 1에 있어서,The method according to claim 1,
    상기 생태분석부(200)의 동물개별인식수단(220)은,The individual animal recognition means 220 of the ecological analysis unit 200 is,
    출현종특정수단(210)에서 특정 분류된 야생동물 소리신호가 제공되면, 해당 야생동물의 소리 특성을 분석하고 개별인식코드를 부여하여 저장 후, 차후 제공되는 소리신호와 비교하여 특정 종의 특정 동물을 인식하도록 하는 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것,When a specific classified wild animal sound signal is provided by the appearing species specific means 210, the sound characteristics of the corresponding wild animal are analyzed, an individual recognition code is given, stored, and compared with the sound signal provided later, a specific animal of a specific species It is an acoustic comparison and analysis circuit loaded with an algorithm or program that provides information to recognize
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  8. 청구항 1에 있어서,The method according to claim 1,
    상기 생태분석부(200)의 생태분석수단(230)은,The ecological analysis means 230 of the ecological analysis unit 200 is,
    다수의 음향수집부(100)에서 제공되는 소리신호의 순서 및 상기 출현동물특정수단(210)과 동물개별인식수단(220)에서 제공되는 야생동물 소리의 레벨 변화를 분석하되, 해당 출현 종 및 개별동물이 어느 방향에서 어느 방향으로 이동하였는지를 분석하여 이동동선을 추출하고, 주로 어느 영역에서 집중적으로 소리신호가 수집되는지를 분석하여 주 서식지를 추출함과 동시에, 특정 이동동선과 특정 영역에서 출현 빈도를 산출하고, 동물개별인식수단(220)에서 특정된 종과 특정된 동물을 분석하여 개체수를 산출하여 정보를 제공하는 알고리즘 내지 프로그램이 탑재된 음향비교분석회로인 것,Analyze the sequence of sound signals provided by the plurality of sound collection units 100 and changes in the level of wild animal sounds provided by the appearing animal specifying means 210 and individual animal recognition means 220, but the appearance species and individual It extracts movement lines by analyzing from which direction the animal moved in which direction, and extracts main habitats by analyzing which areas are mainly where sound signals are intensively collected, and at the same time determines the frequency of appearance in specific movement lines and specific areas. It is an acoustic comparison and analysis circuit loaded with an algorithm or program that calculates and provides information by calculating the number of individuals by analyzing the specified species and specified animals in the individual animal recognition means 220,
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  9. 청구항 6 또는 청구항 7 또는 청구항 8에 있어서,9. The method according to claim 6 or 7 or 8,
    상기 알고리즘 내지 프로그램은 wav, zc, mp3를 포함한 디지털 파일로 제공되는 야생동물의 소리를 자동으로 분석하는 것으로서, 사전에 Deep learning 기법으로 학습시킨 프로그램으로 음성파일을 spectrogram으로 변환하여 영상으로 표출한 후, 이 패턴을 학습시키는 프로그램으로 spectogram 내 펄스의 간격, 펄스 내 최고주파수, 최저주파수, 최대 dB 시 주파수를 분석하는 것,The algorithm or program is to automatically analyze the sounds of wild animals provided as digital files including wav, zc, and mp3. It is a program trained in advance by deep learning, and after converting the audio file into a spectrogram and expressing it as an image, , a program that learns this pattern, analyzing the interval of pulses in the spectogram, the highest frequency, the lowest frequency, and the frequency at max dB,
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
  10. 청구항 1에 있어서,The method according to claim 1,
    상기 관리부(300)는,The management unit 300,
    생태분석부(200)에서 제공하는 분석데이터 또는 소리신호를 전송받아 저장한 후, 로딩하여 관리 및 종합 분석하는 알고리즘 내지 프로그램이 탑재된 원격관제소에 설치된 서버를 포함한 컴퓨터 시스템 또는 관리자 또는 연구자의 휴대단말기인 것,After receiving and storing the analysis data or sound signal provided by the ecological analysis unit 200, a computer system including a server installed in a remote control center equipped with an algorithm or program for loading, managing, and comprehensively analyzing, or a mobile terminal of an administrator or researcher being,
    을 특징으로 하는 생태 조사 시스템.Ecological survey system, characterized in that.
PCT/KR2021/012156 2020-10-29 2021-09-07 Ecological survey system WO2022092548A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2020-0141984 2020-10-29
KR1020200141984A KR102397880B1 (en) 2020-10-29 2020-10-29 Ecological survey system

Publications (1)

Publication Number Publication Date
WO2022092548A1 true WO2022092548A1 (en) 2022-05-05

Family

ID=81382876

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/012156 WO2022092548A1 (en) 2020-10-29 2021-09-07 Ecological survey system

Country Status (2)

Country Link
KR (1) KR102397880B1 (en)
WO (1) WO2022092548A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116612780A (en) * 2023-07-19 2023-08-18 百鸟数据科技(北京)有限责任公司 Method and device for collecting outdoor sound, computer equipment and storage medium
CN117711411A (en) * 2023-12-15 2024-03-15 百鸟数据科技(北京)有限责任公司 Sound monitoring and identifying equipment, system, computer equipment and storage medium
CN118522295A (en) * 2024-07-25 2024-08-20 百鸟数据科技(北京)有限责任公司 Wild ecological environment biodiversity variation trend assessment method
CN118609338A (en) * 2024-08-08 2024-09-06 安徽诚溱数据股份有限公司 Agricultural management system and method based on big data

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010152149A (en) * 2008-12-25 2010-07-08 Chubu Electric Power Co Inc Animal observing device
KR101864388B1 (en) * 2018-03-29 2018-06-04 주식회사 경림이앤지 Peculiar sound detection system and method to be cancelled out the noise by using array microphone in CCTV camera system
JP2018099114A (en) * 2016-12-19 2018-06-28 いであ株式会社 Determination/distribution system of position and kind of wild animal

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010152149A (en) * 2008-12-25 2010-07-08 Chubu Electric Power Co Inc Animal observing device
JP2018099114A (en) * 2016-12-19 2018-06-28 いであ株式会社 Determination/distribution system of position and kind of wild animal
KR101864388B1 (en) * 2018-03-29 2018-06-04 주식회사 경림이앤지 Peculiar sound detection system and method to be cancelled out the noise by using array microphone in CCTV camera system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
DONGA SCIENCE: "Donga Science. Listen to the Whispers of the Forest and Evaluate Biodiversity", DONGASCIENCE.COM, KOREA, 7 January 2019 (2019-01-07), Korea, XP055926303, Retrieved from the Internet <URL:https://www.dongascience.com/news.php?idx=26136> [retrieved on 20220531] *
JUNG SEUNGWON: "Development of Open Platform for collecting and classifying animal sounds", PROCEEDINGS OF 2018 FALL ACADEMIC PRESENTATION CONFERENCE, KOREA UNIVERSITY DEPARTMENT OF ELECTRICAL AND ELECTRONIC ENGINEERING, vol. 25, no. 2, 1 November 2018 (2018-11-01), pages 839 - 841, XP055926298 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116612780A (en) * 2023-07-19 2023-08-18 百鸟数据科技(北京)有限责任公司 Method and device for collecting outdoor sound, computer equipment and storage medium
CN116612780B (en) * 2023-07-19 2023-10-27 百鸟数据科技(北京)有限责任公司 Method and device for collecting outdoor sound, computer equipment and storage medium
CN117711411A (en) * 2023-12-15 2024-03-15 百鸟数据科技(北京)有限责任公司 Sound monitoring and identifying equipment, system, computer equipment and storage medium
CN118522295A (en) * 2024-07-25 2024-08-20 百鸟数据科技(北京)有限责任公司 Wild ecological environment biodiversity variation trend assessment method
CN118609338A (en) * 2024-08-08 2024-09-06 安徽诚溱数据股份有限公司 Agricultural management system and method based on big data

Also Published As

Publication number Publication date
KR20220057102A (en) 2022-05-09
KR102397880B1 (en) 2022-05-13

Similar Documents

Publication Publication Date Title
WO2022092548A1 (en) Ecological survey system
Darras et al. Comparing the sampling performance of sound recorders versus point counts in bird surveys: A meta‐analysis
Lambert et al. A low‐cost, yet simple and highly repeatable system for acoustically surveying cryptic species
Reif et al. Using time-lapse digital video recording for a nesting study of birds of prey
Evans et al. Monitoring grassland birds in nocturnal migration
JP7197846B2 (en) Bat exhibition viewing system and method
CN108924483A (en) A kind of automatic monitoring system and method for the field animal based on depth learning technology
Zamora‐Gutierrez et al. The Sonozotz project: Assembling an echolocation call library for bats in a megadiverse country
Orben et al. Comparing imaging, acoustics, and radar to monitor Leach’s storm-petrel colonies
Adams Assessing and analyzing bat activity with acoustic monitoring: challenges and interpretations
Branch et al. Distress calls in tufted titmice (Baeolophus bicolor): are conspecifics or predators the target?
CN114067809A (en) Wild animal sound intelligent monitoring and AI recognition system and device
CN113269039A (en) On-duty personnel behavior identification method and system
Jones et al. Sensory ecology of the frog-eating bat, Trachops cirrhosus, from DNA metabarcoding and behavior
CN107135371A (en) Online electronic security service system
Eisenring et al. Quantifying song behavior in a free‐living, light‐weight, mobile bird using accelerometers
Bergmann et al. The soundscape of swarming: Proof of concept for a noninvasive acoustic species identification of swarming Myotis bats
Knight et al. Individual identification in acoustic recordings
WO2022255635A1 (en) Guided fence installation area derivation system through analysis of vulnerability to harmful birds and animals, and guided fence installation area derivation method using same
CN116884416A (en) Wild animal audio acquisition and detection system, method, storage medium and electronic equipment
CN111105603A (en) Venue and stadium integrated security management platform based on big data
Fahmy et al. Singing behaviour of ruby‐crowned kinglets Regulus calendula in relation to time‐of‐day, time‐of‐year and social context
CH719673A2 (en) AI-BASED REAL-TIME ACOUSTIC WILDLIFE MONITORING SYSTEM
Batist et al. An integrated passive acoustic monitoring and deep learning pipeline for black‐and‐white ruffed lemurs (Varecia variegata) in Ranomafana National Park, Madagascar
Wang et al. Internet of Things‐based smart insect monitoring system using a deep neural network

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21886545

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 12/09/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21886545

Country of ref document: EP

Kind code of ref document: A1