CN109033997A - A kind of lumbering event detecting method and system - Google Patents
A kind of lumbering event detecting method and system Download PDFInfo
- Publication number
- CN109033997A CN109033997A CN201810720058.1A CN201810720058A CN109033997A CN 109033997 A CN109033997 A CN 109033997A CN 201810720058 A CN201810720058 A CN 201810720058A CN 109033997 A CN109033997 A CN 109033997A
- Authority
- CN
- China
- Prior art keywords
- lumbering
- audio
- information
- event
- camera
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Burglar Alarm Systems (AREA)
Abstract
The present invention provides a kind of lumbering event detecting method and systems, and camera and voice collection device, multidate information and acoustic information in real-time acquisition camera preset range are installed in the woods；Data processor, it is previously stored with lumbering audio-video model, by comparing the multidate information, acoustic information and the lumbering audio-video model, carry out lumbering voice recognition judgement, when being identified as lumbering sound, voice collection device determines Sounnd source direction, and the camera monitors angle according to lumbering Sounnd source direction adjust automatically, and notifies relevant departments to take action in time by server.The present invention can identify lumbering phenomenon in first time, improve monitoring effect by combining acoustic information and multidate information.
Description
Technical field
The present invention relates to audio-video detection identification technology field more particularly to a kind of lumbering event detecting method and systems.
Background technique
Currently, relying primarily on the mode of artificial inspection and masses' discovery report to the protection of felling trees unlawfully of forest, but this protection
There is biggish limitation over time and space, and just hair and the means of transport of molecule of felling trees unlawfully are increasingly advanced, also increase
Inspection difficulty.Also it can use Satellite Remote Sensing technology fell trees unlawfully the detection of behavior, but Satellite Remote Sensing is intelligent
Obviously fell trees unlawfully region it was found that area of felling trees unlawfully is biggish, be difficult first time discovery fell trees unlawfully situation and collective and it is personal generally also
It has no ability to undertake the high hardware construction of Satellite Remote Sensing, technical support and running cost.
Summary of the invention
The present invention is in order to solve the above technical problems, provide a kind of lumbering event detecting method, which comprises is setting
Camera and voice collection device, multidate information and acoustic information in real-time acquisition camera preset range are installed in woods；
Data processor is previously stored with lumbering audio-video model, by the multidate information of acquisition and acoustic information combination shape
Input information at audio/video information as model is calculated, and carries out lumbering event recognition judgement.
When the acoustic information and the lumbering audio-video Model Matching, voice collection device determines Sounnd source direction, institute
Camera is stated according to lumbering Sounnd source direction adjust automatically monitoring angle, when the multidate information and the lumbering audio-video model
Timing is judged as lumbering event, notifies relevant departments to take action in time by server.
Preferably, the voice collection device uses sound pick-up or microphone array.
It preferably, is the accuracy for guaranteeing lumbering event recognition, it, will by collecting various lumbering audio, video datas
These data obtain the lumbering audio-video model using deep neural network training, and lumbering audio-video model is implanted to number
According in processor.
Preferably, the installation camera and voice collection device are mating one by one, and at least a set of, are distributed in the woods,
Cover the woods.
Preferably, recording fraud model is prestored in the data processor, for judging and abandoning recorded audio data.
Preferably, the installation camera and voice collection device and the server are connected using wired or wireless network
It connects.
A kind of lumbering audio-video detection system, comprising:
Camera is mounted in the woods, acquires the multidate information in preset range in real time, and certainly according to lumbering Sounnd source direction
Dynamic adjustment monitoring angle；
Voice collection device is installed close to the camera, acquires the acoustic information in preset range in real time, and determination is cut down
The Sounnd source direction of the wooden sound；The multidate information and acoustic information, which combine, forms audio/video information.
Data processor is previously stored with lumbering audio-video model, by comparing the audio/video information and the lumbering
Audio-video model carries out lumbering event recognition judgement；
Server, when data processor judges the audio/video information for the generation of lumbering event, server notice is related
Department takes action in time.
Preferably, the voice collection device uses sound pick-up or microphone array.
Preferably, the lumbering audio-video model is trained and is obtained using deep neural network.
The installation camera and voice collection device are mating one by one, and at least a set of, are distributed in the woods.
Preferably, recording fraud model is prestored in the data processor, for judging and abandoning recorded audio data.
Preferably, the installation camera and voice collection device and the server are connected using wired or wireless network
It connects.
By the above-mentioned description of this invention it is found that compared to the prior art, the present invention has the advantage that
The application proposes a kind of lumbering event detecting method and system, first passes through camera and voice collection device acquisition sound
Video information, then lumbering event is judged whether it is by data processor, when being judged as lumbering event, reported by server
To relevant departments.By combining acoustic information and multidate information, lumbering phenomenon can be identified in first time, improve monitoring effect
Fruit.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.
Wherein:
Fig. 1 is the system composition schematic diagram of the embodiment of the present invention.
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below
Drawings and examples are closed, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used
To explain the present invention, it is not intended to limit the present invention.
A kind of lumbering event detecting method, which comprises camera and voice collection device, institute are installed in the woods
It states installation camera and voice collection device is mating one by one and at least a set of, be distributed in the woods, cover the woods, acquire in real time
Multidate information and acoustic information in camera preset range.Data processor is previously stored with lumbering audio-video model, will adopt
Multidate information and the acoustic information combination of collection form audio/video information and are calculated as the input information of model, and lumber
Event recognition judgement.
When the acoustic information and the lumbering audio-video Model Matching, voice collection device determines Sounnd source direction, institute
Camera is stated according to lumbering Sounnd source direction adjust automatically monitoring angle, when the multidate information and the lumbering audio-video model
Timing is judged as lumbering event, notifies relevant departments to take action in time by server.
These are counted by collecting various lumbering audio, video datas for the accuracy for guaranteeing lumbering event recognition
The lumbering audio-video model is obtained according to using deep neural network training, and lumbering audio-video model is implanted to data processing
In device.
In the present embodiment, the voice collection device uses microphone array device.
Referring to Fig. 1, a kind of lumbering audio-video detection system, comprising:
Camera is mounted in the woods, is equipped with holder, acquires the multidate information in preset range, and root in real time
Angle is monitored according to lumbering Sounnd source direction adjust automatically；
Voice collection device, including microphone array are installed close to the camera, acquire the sound in preset range in real time
Message breath, and determine the Sounnd source direction of lumbering sound；The multidate information and acoustic information, which combine, forms audio/video information.
Data processor is previously stored with through deep neural network and trains and obtain lumbering audio-video model and recording
Model is cheated, by comparing the audio/video information and the lumbering audio-video model, carries out lumbering event recognition judgement.Pass through
The recording that the recording fraud model judgement person of felling trees unlawfully plays, and abandon recorded audio data.In the present embodiment, data processor installation
In the voice collection device.
Server, when data processor judges the audio/video information for the generation of lumbering event, server notice is related
Department takes action in time.
In the present embodiment, the data processor for judging sound and server are separated, the edge calculations method of use makes
Terminal inherently has processing capacity, reduces the pressure of service centre, and service centre only needs to receive result and reported result.
In conclusion compared to the prior art, the application proposed by the present invention propose a kind of lumbering event detecting method and
System first passes through camera and voice collection device acquisition audio/video information, then judges whether it is lumbering by data processor
Event is reported to relevant departments by server when being judged as lumbering event.By combining acoustic information and multidate information,
Lumbering phenomenon can be identified in first time, improve monitoring effect.
The present invention is exemplarily described above in conjunction with attached drawing, it is clear that the present invention implements not by aforesaid way
Limitation, as long as the improvement for the various unsubstantialities that the inventive concept and technical scheme of the present invention carry out is used, or without changing
It is within the scope of the present invention into the conception and technical scheme of the invention are directly applied to other occasions.
Claims (10)
1. a kind of lumbering event detecting method, which is characterized in that the described method includes: installation camera and sound are adopted in the woods
Acquisition means, multidate information and acoustic information in real-time acquisition camera preset range form audio/video information；Data processing
Device is previously stored with lumbering audio-video model, the multidate information of acquisition and acoustic information is combined as to the input information of model
It is calculated, and carries out lumbering event recognition judgement；When the acoustic information and the lumbering audio-video Model Matching, sound
Acquisition device determines that Sounnd source direction, the camera monitor angle according to lumbering Sounnd source direction adjust automatically, when the dynamic is believed
When breath is with the lumbering audio-video Model Matching, it is judged as lumbering event, notifies relevant departments to take row in time by server
It is dynamic.
2. a kind of lumbering event detecting method according to claim 1, which is characterized in that the voice collection device uses
Sound pick-up or microphone array.
3. a kind of lumbering event detecting method according to claim 1, which is characterized in that the lumbering audio-video model is adopted
It is trained and is obtained with deep neural network.
4. a kind of lumbering event detecting method according to claim 1, which is characterized in that the installation camera and sound
Acquisition device is mating one by one, and at least a set of, is distributed in the woods.
5. a kind of lumbering event detecting method according to claim 1, which is characterized in that prestored in the data processor
There is recording fraud model, for judging and abandoning recorded audio data.
6. a kind of lumbering event detection system characterized by comprising
Camera is mounted in the woods, acquires the multidate information in preset range in real time, and adjust automatically according to lumbering Sounnd source direction
Whole monitoring angle；
Voice collection device is installed close to the camera, acquires the acoustic information in preset range in real time, and determine lumbering sound
The Sounnd source direction of sound；The multidate information and acoustic information, which combine, forms audio/video information；
Data processor is previously stored with lumbering audio-video model, is regarded by comparing the audio/video information and the lumbering sound
Frequency model carries out lumbering event recognition judgement；
Server, when data processor judges the audio/video information for the generation of lumbering event, server notifies relevant departments
It takes action in time.
7. a kind of lumbering event detection system according to claim 6, which is characterized in that the voice collection device
Using sound pick-up or microphone array.
8. a kind of lumbering event detection system according to claim 6, which is characterized in that the lumbering audio-video model is adopted
It is trained and is obtained with deep neural network.
9. a kind of lumbering event detection system according to claim 6, which is characterized in that the installation camera and sound
Acquisition device is mating one by one, and at least a set of, is distributed in the woods.
10. a kind of lumbering event detection system according to claim 6, which is characterized in that the installation camera harmony
Sound acquisition device is connect with the server using wired or wireless network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810720058.1A CN109033997A (en) | 2018-07-02 | 2018-07-02 | A kind of lumbering event detecting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810720058.1A CN109033997A (en) | 2018-07-02 | 2018-07-02 | A kind of lumbering event detecting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109033997A true CN109033997A (en) | 2018-12-18 |
Family
ID=65521581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810720058.1A Pending CN109033997A (en) | 2018-07-02 | 2018-07-02 | A kind of lumbering event detecting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109033997A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113711820A (en) * | 2021-08-10 | 2021-11-30 | 秦刚 | Ancient and famous tree management and protection system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008016360A1 (en) * | 2006-08-03 | 2008-02-07 | International Business Machines Corporation | Video surveillance system and method with combined video and audio recognition |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| CN102393986A (en) * | 2011-08-11 | 2012-03-28 | 重庆市科学技术研究院 | Illegal lumbering detection method, device and system based on audio frequency distinguishing |
| CN106846803A (en) * | 2017-02-08 | 2017-06-13 | 广西交通科学研究院有限公司 | Traffic incidents detection device and method based on audio |
| CN106898346A (en) * | 2017-04-19 | 2017-06-27 | 杭州派尼澳电子科技有限公司 | A kind of freeway tunnel safety monitoring system |
| CN107086036A (en) * | 2017-04-19 | 2017-08-22 | 杭州派尼澳电子科技有限公司 | A kind of freeway tunnel method for safety monitoring |
-
2018
- 2018-07-02 CN CN201810720058.1A patent/CN109033997A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008016360A1 (en) * | 2006-08-03 | 2008-02-07 | International Business Machines Corporation | Video surveillance system and method with combined video and audio recognition |
| CN101751782A (en) * | 2009-12-30 | 2010-06-23 | 北京大学深圳研究生院 | Crossroad traffic event automatic detection system based on multi-source information fusion |
| CN102393986A (en) * | 2011-08-11 | 2012-03-28 | 重庆市科学技术研究院 | Illegal lumbering detection method, device and system based on audio frequency distinguishing |
| CN106846803A (en) * | 2017-02-08 | 2017-06-13 | 广西交通科学研究院有限公司 | Traffic incidents detection device and method based on audio |
| CN106898346A (en) * | 2017-04-19 | 2017-06-27 | 杭州派尼澳电子科技有限公司 | A kind of freeway tunnel safety monitoring system |
| CN107086036A (en) * | 2017-04-19 | 2017-08-22 | 杭州派尼澳电子科技有限公司 | A kind of freeway tunnel method for safety monitoring |
Non-Patent Citations (1)
| Title |
|---|
| 王再欢等: "一种利用声音识别的森林盗伐检测方法", 《计算机工程与应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113711820A (en) * | 2021-08-10 | 2021-11-30 | 秦刚 | Ancient and famous tree management and protection system and method |
| CN113711820B (en) * | 2021-08-10 | 2023-12-15 | 厦门源森园林景观股份有限公司 | Ancient tree name wood management protection system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Klump | Bird communication in the noisy world | |
| CN104644189B (en) | Analysis method for psychological activities | |
| CN101150788B (en) | Self modulation radio broadcast terminal system and its monitoring processor | |
| US8164484B2 (en) | Detection and classification of running vehicles based on acoustic signatures | |
| Doddington et al. | SHEEP, GOATS, LAMBS and WOLVES: a statistical analysis of speaker performance in the NIST 1998 speaker recognition evaluation. | |
| Murray et al. | Characterizing the graded structure of false killer whale (Pseudorca crassidens) vocalizations | |
| JP5704598B2 (en) | Animal-machine voice interaction system | |
| Schibler et al. | The irrelevance of individual discrimination in meerkat alarm calls | |
| CN101655907B (en) | Trainman driving state monitoring intelligent alarm system | |
| CN104305964B (en) | Wear-type fatigue detection device and method | |
| CN109616140A (en) | A kind of abnormal sound analysis system | |
| Leong et al. | Quantifying acoustic and temporal characteristics of vocalizations for a group of captive African elephants Loxodonta africana | |
| CA2656268A1 (en) | Video surveillance system and method with combined video and audio recognition | |
| US20080040110A1 (en) | Apparatus and Methods for the Detection of Emotions in Audio Interactions | |
| CN108351968A (en) | It is a kind of for the alarm method of criminal activity, device, storage medium and server | |
| CN108986430A (en) | Net based on speech recognition about vehicle safe early warning method and system | |
| CN108583592A (en) | A kind of subway service on buses or trains job information acquisition intelligent detecting method | |
| CN109033997A (en) | A kind of lumbering event detecting method and system | |
| CN109949540A (en) | A kind of artificial intelligence early warning system | |
| CN107430791A (en) | System for originating and stopping elapsed time clock in the environment medium-long range with multiple different activation signals | |
| AU2017203766B2 (en) | Method and apparatus for detecting seizures including audio characterization | |
| Holt et al. | Call directionality and its behavioural significance in male northern elephant seals, Mirounga angustirostris | |
| CN110120000A (en) | Multimedia remote interlocking quality of education intelligent monitor system and control method | |
| CN110324742A (en) | Control method, earphone and storage medium | |
| CN213877002U (en) | Elevator smoke control device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |