CN104933402A - Fugu rubripe attacking behavior monitoring and early warning method based on computer vision - Google Patents
Fugu rubripe attacking behavior monitoring and early warning method based on computer vision Download PDFInfo
- Publication number
- CN104933402A CN104933402A CN201510252761.0A CN201510252761A CN104933402A CN 104933402 A CN104933402 A CN 104933402A CN 201510252761 A CN201510252761 A CN 201510252761A CN 104933402 A CN104933402 A CN 104933402A
- Authority
- CN
- China
- Prior art keywords
- fugu rubripes
- image
- fugu
- rubripes
- coordinate
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a fugu rubripe attacking behavior monitoring and early warning method based on computer vision. The method comprises the following steps: pre-processing multiple frames of images for acquiring video information of fugu rubripe; determining a geometrical center coordinate and a body axis coordinate of the fugu rubripe in an image of the fugu rubripe in the multiple frames of images; determining the fugu rubripe of an attacker with the attacking behavior in the first fugu rubripe and the second fugu rubripe, obtaining the frequency of the attacking behavior of the fugu rubripe of the attacker within a preset time period, and sending warning information to a farmer when the frequency exceeds the preset frequency. By virtue of the method, the attacking behavior of the fugu rubripe can be effectively monitored and early warned, and cultivation enterprises are reminded of treating teeth of the fugu rubripe with the attacking behavior in time, so that the production decreasing caused by the attacking behaviors of the fugu rubripes is avoided.
Description
Technical field
The present invention relates to field of computer technology, be specifically related to a kind of Fugu rubripes attack monitoring and early warning method and system based on computer vision.
Background technology
Fugu rubripes belongs to ominivore-fish, moral character is violent and have sharp tooth in mouth, in industrial aquaculture process, because cultivation density is high, the manor of Fugu rubripes is realized, is fought for the reasons such as bait, can there is attack in Fugu rubripes, and cause Fugu rubripes injured even dead each other, and then cause the Fugu rubripes underproduction and cause economic loss; The breeding enterprise generally regular tooth to Fugu rubripes processes, generally give in industrial aquaculture process, within 1 year, regularly to carry out twice process to the tooth of Fugu rubripes, but because Fugu rubripes is after dental treatments, can constantly grow out again, therefore attack still happens occasionally, need regularly to process the tooth of indivedual Fugu rubripes; Fugu rubripes is the food fish of high economic worth, and meat is careful, propagates artificially in large quantities on Laizhou, Yantai and other places.
Existing more methodical attack main study subjects are Lu Sheng mammal, use terrestrial animal behavioural characteristic and behaviour classification, are not suitable for the analysis of Fugu rubripes behavior.
Summary of the invention
For defect of the prior art, the invention provides a kind of Fugu rubripes attack monitoring and early warning method and system based on computer vision, effectively monitoring and early warning is carried out to the attack of Fugu rubripes.
First aspect, the invention provides a kind of Fugu rubripes attack monitoring and early warning method based on computer vision, comprising:
Gather the video information of Fugu rubripes, pre-service is carried out to the image of multiple frames of described video information;
Obtain the image of the Fugu rubripes in the image of pretreated multiple frame, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, the image of described Fugu rubripes comprises the image of the first Fugu rubripes and the image of the second Fugu rubripes;
Determine body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes, the distance comprising body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes at the image of described multiple frame is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, the angle of the body axes of the first Fugu rubripes and the second Fugu rubripes is that 75 degree of angles are to an angle of 90 degrees, and the body surface of described first Fugu rubripes or the second Fugu rubripes is when having corresponding biting, determine that described first Fugu rubripes and the second Fugu rubripes have attack,
Determine the Fugu rubripes having the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, send warning message to poultry feeders;
Wherein, the Geometric center coordinates of described Fugu rubripes is the coordinate of the mid point of the health of Fugu rubripes, the body axes coordinate of described Fugu rubripes is the coordinate of the head of Fugu rubripes and the line of centre of body weight, and body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is the head of the first Fugu rubripes and the second Fugu rubripes and the line coordinate of body centre.
Optionally, the video information of described collection Fugu rubripes, pre-service is carried out to the image of multiple frames of described video information, comprising:
Wavelet threshold denoising method is adopted to remove the noise of the image of described video information.
Optionally, the image of the Fugu rubripes in the image of the pretreated multiple frame of described acquisition, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, comprising:
The image of the Fugu rubripes in the image of described pretreated multiple frame is detected by background subtraction;
By the Image Segmentation Using of Pulse Coupled Neural Network algorithm to described Fugu rubripes;
The image of example filtering algorithm to described Fugu rubripes is utilized to follow the tracks of, and the Geometric center coordinates of the first Fugu rubripes and the second Fugu rubripes and body axes coordinate in the image of the described Fugu rubripes of real-time calculating.
Optionally, describedly determine the Fugu rubripes having the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, comprising:
The Geometric center coordinates of Fugu rubripes in the image of the first Fugu rubripes in the image of described multiple frame and the image of the second Fugu rubripes and body axes coordinate are contrasted, in the image of present frame and former frame, the body axes coordinate of the first Fugu rubripes changes, and the body axes coordinate of the second Fugu rubripes changes in the image of present frame and next frame, then determine that the first Fugu rubripes is the Fugu rubripes of attacker, the second Fugu rubripes is by the Fugu rubripes of attacker.
Optionally, described method also comprises: by SIFT feature extraction algorithm, extract described by the surface characteristics of the Fugu rubripes of attacker, and judge describedly whether had corresponding biting by the body surface of the Fugu rubripes of attacker according to described surface characteristics, if have, then record the label of the Fugu rubripes of described attacker;
Accordingly, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, sends warning message, comprising to poultry feeders:
When the number of times of described labelled notation exceedes preset times, send warning message to poultry feeders.
Optionally, the distance of body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, comprising:
Body centre's coordinate according to described first Fugu rubripes and the second Fugu rubripes determines that the body of described first Fugu rubripes and the second Fugu rubripes is long;
Accordingly, the distance of body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes be less than the body of described first Fugu rubripes and the second Fugu rubripes long in body long the shortest by 1/2.
Second aspect, present invention also offers a kind of Fugu rubripes attack monitoring early-warning system based on computer vision, comprising:
Image processing module, the image for multiple frames of the video information to collection Fugu rubripes carries out pre-service;
Coordinate determination module, for obtaining the image of the Fugu rubripes in the image of pretreated multiple frame, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, the image of described Fugu rubripes comprises the image of the first Fugu rubripes and the image of the second Fugu rubripes;
Attack determination module, for determining body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes, the distance comprising body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes at the image of described multiple frame is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, the angle of the body axes of the first Fugu rubripes and the second Fugu rubripes is that 75 degree of angles are to an angle of 90 degrees, and the body surface of described first Fugu rubripes or the second Fugu rubripes is when having corresponding biting, determine that described first Fugu rubripes and the second Fugu rubripes have attack,
Warning message sending module, for when determining there is the Fugu rubripes of the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, send warning message to poultry feeders;
Wherein, the Geometric center coordinates of described Fugu rubripes is the coordinate of the mid point of the health of Fugu rubripes, the body axes coordinate of described Fugu rubripes is the coordinate of the head of Fugu rubripes and the line of centre of body weight, and body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is the head of the first Fugu rubripes and the second Fugu rubripes and the line coordinate of body centre.
Optionally, described coordinate determination module, for:
The image of the Fugu rubripes in the image of described pretreated multiple frame is detected by background subtraction;
By the Image Segmentation Using of Pulse Coupled Neural Network algorithm to described Fugu rubripes;
The image of example filtering algorithm to described Fugu rubripes is utilized to follow the tracks of, and the Geometric center coordinates of the first Fugu rubripes and the second Fugu rubripes and body axes coordinate in the image of the described Fugu rubripes of real-time calculating.
Optionally, described attack determination module, for:
The Geometric center coordinates of Fugu rubripes in the image of the first Fugu rubripes in the image of described multiple frame and the image of the second Fugu rubripes and body axes coordinate are contrasted, in the image of present frame and former frame, the body axes coordinate of the first Fugu rubripes changes, and the body axes coordinate of the second Fugu rubripes changes in the image of present frame and next frame, then determine that the first Fugu rubripes is the Fugu rubripes of attacker, the second Fugu rubripes is by the Fugu rubripes of attacker.
Optionally, described system also comprises:
Attack number of times mark module, for passing through SIFT feature extraction algorithm, extract described by the surface characteristics of the Fugu rubripes of attacker, and judge describedly whether had corresponding biting by the body surface of the Fugu rubripes of attacker according to described surface characteristics, when there being the biting of new trip, record the label of the Fugu rubripes of described attacker;
Accordingly, described warning message sending module, for:
When the number of times of described labelled notation exceedes preset times, send warning message to poultry feeders.
As shown from the above technical solution, a kind of Fugu rubripes attack monitoring and early warning method and system based on computer vision provided by the invention, effectively monitoring and early warning is carried out to the attack of Fugu rubripes, remind breeding enterprise to process the tooth of Fugu rubripes that attack occurs in time, and then avoid the underproduction that causes because Fugu rubripes each other attack occurs.
In instructions of the present invention, describe a large amount of detail.But can understand, embodiments of the invention can be put into practice when not having these details.In some instances, be not shown specifically known method, structure and technology, so that not fuzzy understanding of this description.
Last it is noted that above each embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to foregoing embodiments to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein some or all of technical characteristic; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of various embodiments of the present invention technical scheme, it all should be encompassed in the middle of the scope of claim of the present invention and instructions.
Accompanying drawing explanation
The schematic flow sheet of a kind of Fugu rubripes attack monitoring and early warning method based on computer vision that Fig. 1 provides for one embodiment of the invention;
The structural representation of a kind of Fugu rubripes attack monitoring early-warning system based on computer vision that Fig. 2 provides for one embodiment of the invention.
Embodiment
Below in conjunction with accompanying drawing, the embodiment of invention is further described.Following examples only for technical scheme of the present invention is clearly described, and can not limit the scope of the invention with this.
Before the embodiment of the present invention is described in detail, first, some terms are described in detail:
The Fugu rubripes of attacker: refer to use tabular tooth to attack the Fugu rubripes of other Fugu rubripes;
The under fire Fugu rubripes of side: attacked by other Fugu rubripes, occur the Fugu rubripes of biting with it;
The body axes of Fugu rubripes: the line of Fugu rubripes head and centre of body weight;
Fugu rubripes Geometric center coordinates: the coordinate of Fugu rubripes fish body central point;
Body centre's coordinate of Fugu rubripes: the line of Fugu rubripes head and body centre.
Fig. 1 shows the schematic flow sheet of a kind of Fugu rubripes attack monitoring and early warning method based on computer vision that the embodiment of the present invention provides, and as shown in Figure 1, the method comprises the steps:
101, gather the video information of Fugu rubripes, pre-service is carried out to the image of multiple frames of described video information;
102, the image of the Fugu rubripes in the image of pretreated multiple frame is obtained, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, the image of described Fugu rubripes comprises the image of the first Fugu rubripes and the image of the second Fugu rubripes;
103, determine body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes, the distance comprising body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes at the image of described multiple frame is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, the angle of the body axes of the first Fugu rubripes and the second Fugu rubripes is that 75 degree of angles are to an angle of 90 degrees, and the body surface of described first Fugu rubripes or the second Fugu rubripes is when having corresponding biting, determine that described first Fugu rubripes and the second Fugu rubripes have attack,
104, the Fugu rubripes having the attacker of attack in described first Fugu rubripes and the second Fugu rubripes is determined, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, send warning message to poultry feeders;
Wherein, the Geometric center coordinates of described Fugu rubripes is the coordinate of the mid point of the health of Fugu rubripes, the body axes coordinate of described Fugu rubripes is the coordinate of the head of Fugu rubripes and the line of centre of body weight, and body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is the head of the first Fugu rubripes and the second Fugu rubripes and the line coordinate of body centre.
Said method carries out monitoring and early warning to the attack of Fugu rubripes effectively, remind breeding enterprise to process the tooth of Fugu rubripes that attack occurs in time, and then avoid the underproduction that causes because Fugu rubripes each other attack occurs.
In above-mentioned steps 101, gather the video information of Fugu rubripes, pre-service carried out to the image of multiple frames of described video information, comprising:
Wavelet threshold denoising method is adopted to remove the noise of the image of described video information.Wherein, the threshold value selection rule of use is the fixed threshold estimation technique.
In above-mentioned steps 102, obtain the image of the Fugu rubripes in the image of pretreated multiple frame, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, comprising:
The image of the Fugu rubripes in the image of described pretreated multiple frame is detected by background subtraction;
By the Image Segmentation Using of Pulse Coupled Neural Network algorithm to described Fugu rubripes;
The image of example filtering algorithm to described Fugu rubripes is utilized to follow the tracks of, and the Geometric center coordinates of the first Fugu rubripes and the second Fugu rubripes and body axes coordinate in the image of the described Fugu rubripes of real-time calculating.
In above-mentioned steps 103, the distance of body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, comprising:
Body centre's coordinate according to described first Fugu rubripes and the second Fugu rubripes determines that the body of described first Fugu rubripes and the second Fugu rubripes is long;
Accordingly, the distance of body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes be less than the body of described first Fugu rubripes and the second Fugu rubripes long in body long the shortest by 1/2.
In above-mentioned steps 104, describedly determine the Fugu rubripes having the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, comprising:
The Geometric center coordinates of Fugu rubripes in the image of the first Fugu rubripes in the image of described multiple frame and the image of the second Fugu rubripes and body axes coordinate are contrasted, in the image of present frame and former frame, the body axes coordinate of the first Fugu rubripes changes, and the body axes coordinate of the second Fugu rubripes changes in the image of present frame and next frame, then determine that the first Fugu rubripes is the Fugu rubripes of attacker, the second Fugu rubripes is by the Fugu rubripes of attacker.
Will be understood that, if meet following two conditions, wherein a Fugu rubripes has suddenly speed to promote or health deformation, simultaneously two Fugu rubripes Geometric center coordinates distances are less than the long and angle of the body axes of two Fugu rubripes of 1/2 Fugu rubripes body between 75 ° ~ 90 °, then suppose that it there occurs attack.
The Fugu rubripes judging attacker with by the Fugu rubripes of attacker, first there is speed to promote in video information or the Fugu rubripes of health deformation is judged as the Fugu rubripes of attacker, and delayedly in video information have unexpected speed to promote or the Fugu rubripes of health deformation is the Fugu rubripes of under fire side;
Extract the Fugu rubripes image that supposition is under attack, by SIFT feature extraction algorithm, extract described by the surface characteristics of the Fugu rubripes of attacker, and judge describedly whether had corresponding biting by the body surface of the Fugu rubripes of attacker according to described surface characteristics, if have, then record the label of the Fugu rubripes of described attacker;
Above-mentioned correspondence bite as corresponding position the biting of having newline to become when attacking, this place can judge according to the feature of biting, its time of biting, when the time of biting and Jiading, the time consistency of attack occurred, then determine that the attack supposed is exactly real attack.
Accordingly, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, sends warning message, comprising to poultry feeders:
When the number of times of described labelled notation exceedes preset times, send warning message to poultry feeders.
Will be understood that, the Fugu rubripes image that supposition is under attack is extracted in above-mentioned steps, use SIFT feature extraction algorithm, extract Fugu rubripes surface characteristics, according to the difference of front and back Feature point recognition, judge that under fire whether Fugu rubripes body surface has corresponding attack to bite, if there is situation of significantly biting, then records the Fugu rubripes that attack occurs and mark is attacked on computers.
Add up the attack of record, suppose the situation that more than 3 times attacks occurred in a day, early warning interaction platform gives the alarm, and the Fugu rubripes of poultry feeders to attacker cuts tooth process.
Fig. 2 shows the structural representation of a kind of Fugu rubripes attack monitoring early-warning system based on computer vision that the embodiment of the present invention provides, and as shown in Figure 2, this system comprises:
Image processing module 21, the image for multiple frames of the video information to collection Fugu rubripes carries out pre-service;
Coordinate determination module 22, for obtaining the image of the Fugu rubripes in the image of pretreated multiple frame, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, the image of described Fugu rubripes comprises the image of the first Fugu rubripes and the image of the second Fugu rubripes;
Attack determination module 23, for the body centre's coordinate for determining the first Fugu rubripes and the second Fugu rubripes, the distance comprising body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes at the image of described multiple frame is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, the angle of the body axes of the first Fugu rubripes and the second Fugu rubripes is that 75 degree of angles are to an angle of 90 degrees, and the body surface of described first Fugu rubripes or the second Fugu rubripes is when having corresponding biting, determine that described first Fugu rubripes and the second Fugu rubripes have attack,
Warning message sending module 24, for when determining there is the Fugu rubripes of the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, send warning message to poultry feeders;
Wherein, the Geometric center coordinates of described Fugu rubripes is the coordinate of the mid point of the health of Fugu rubripes, and the body axes coordinate of described Fugu rubripes is the coordinate of the head of Fugu rubripes and the line of centre of body weight.
Described image processing module, for:
Wavelet threshold denoising method is adopted to remove the noise of the image of described video information.
Described coordinate determination module, for:
The image of the Fugu rubripes in the image of described pretreated multiple frame is detected by background subtraction;
By the Image Segmentation Using of Pulse Coupled Neural Network algorithm to described Fugu rubripes;
The image of example filtering algorithm to described Fugu rubripes is utilized to follow the tracks of, and the Geometric center coordinates of the first Fugu rubripes and the second Fugu rubripes and body axes coordinate in the image of the described Fugu rubripes of real-time calculating.
Described attack determination module, for:
The Geometric center coordinates of Fugu rubripes in the image of the first Fugu rubripes in the image of described multiple frame and the image of the second Fugu rubripes and body axes coordinate are contrasted, in the image of present frame and former frame, the body axes coordinate of the first Fugu rubripes changes, and the body axes coordinate of the second Fugu rubripes changes in the image of present frame and next frame, then determine that the first Fugu rubripes is the Fugu rubripes of attacker, the second Fugu rubripes is by the Fugu rubripes of attacker.
Described system also comprises:
Attack number of times mark module, for passing through SIFT feature extraction algorithm, extract described by the surface characteristics of the Fugu rubripes of attacker, and judge describedly whether had corresponding biting by the body surface of the Fugu rubripes of attacker according to described surface characteristics, when there being corresponding biting, record the label of the Fugu rubripes of described attacker;
Accordingly, described warning message sending module, for:
When the number of times of described labelled notation exceedes preset times, send warning message to poultry feeders.
Said system and said method are relations one to one, and the present embodiment is no longer described in detail to the implementation detail of said system.
Claims (10)
1., based on a Fugu rubripes attack monitoring and early warning method for computer vision, it is characterized in that, comprising:
Gather the video information of Fugu rubripes, pre-service is carried out to the image of multiple frames of described video information;
Obtain the image of the Fugu rubripes in the image of pretreated multiple frame, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, the image of described Fugu rubripes comprises the image of the first Fugu rubripes and the image of the second Fugu rubripes;
Determine body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes, the distance comprising body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes at the image of described multiple frame is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, the angle of the body axes of the first Fugu rubripes and the second Fugu rubripes is that 75 degree of angles are to an angle of 90 degrees, and the body surface of described first Fugu rubripes or the second Fugu rubripes is when having corresponding biting, determine that described first Fugu rubripes and the second Fugu rubripes have attack,
Determine the Fugu rubripes having the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, send warning message to poultry feeders;
Wherein, the Geometric center coordinates of described Fugu rubripes is the coordinate of the mid point of the health of Fugu rubripes, the body axes coordinate of described Fugu rubripes is the coordinate of the head of Fugu rubripes and the line of centre of body weight, and body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is the head of the first Fugu rubripes and the second Fugu rubripes and the line coordinate of body centre.
2. method according to claim 1, is characterized in that, the video information of described collection Fugu rubripes, carries out pre-service, comprising the image of multiple frames of described video information:
Wavelet threshold denoising method is adopted to remove the noise of the image of described video information.
3. method according to claim 1, it is characterized in that, the image of the Fugu rubripes in the image of the pretreated multiple frame of described acquisition, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, comprising:
The image of the Fugu rubripes in the image of described pretreated multiple frame is detected by background subtraction;
By the Image Segmentation Using of Pulse Coupled Neural Network algorithm to described Fugu rubripes;
The image of example filtering algorithm to described Fugu rubripes is utilized to follow the tracks of, and the Geometric center coordinates of the first Fugu rubripes and the second Fugu rubripes and body axes coordinate in the image of the described Fugu rubripes of real-time calculating.
4. method according to claim 1, is characterized in that, describedly determines the Fugu rubripes having the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, comprising:
The Geometric center coordinates of Fugu rubripes in the image of the first Fugu rubripes in the image of described multiple frame and the image of the second Fugu rubripes and body axes coordinate are contrasted, in the image of present frame and former frame, the body axes coordinate of the first Fugu rubripes changes, and the body axes coordinate of the second Fugu rubripes changes in the image of present frame and next frame, then determine that the first Fugu rubripes is the Fugu rubripes of attacker, the second Fugu rubripes is by the Fugu rubripes of attacker.
5. method according to claim 4, it is characterized in that, described method also comprises: by SIFT feature extraction algorithm, extract described by the surface characteristics of the Fugu rubripes of attacker, and judge describedly whether had corresponding biting by the body surface of the Fugu rubripes of attacker according to described surface characteristics, if have, then record the label of the Fugu rubripes of described attacker;
Accordingly, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, sends warning message, comprising to poultry feeders:
When the number of times of described labelled notation exceedes preset times, send warning message to poultry feeders.
6. method according to claim 1, is characterized in that, the distance of body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, comprising:
Body centre's coordinate according to described first Fugu rubripes and the second Fugu rubripes determines that the body of described first Fugu rubripes and the second Fugu rubripes is long;
Accordingly, the distance of body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes be less than the body of described first Fugu rubripes and the second Fugu rubripes long in body long the shortest by 1/2.
7., based on a Fugu rubripes attack monitoring early-warning system for computer vision, it is characterized in that, comprising:
Image processing module, the image for multiple frames of the video information to collection Fugu rubripes carries out pre-service;
Coordinate determination module, for obtaining the image of the Fugu rubripes in the image of pretreated multiple frame, determine Geometric center coordinates and the body axes coordinate of Fugu rubripes in the image of the Fugu rubripes in the image of multiple frame, the image of described Fugu rubripes comprises the image of the first Fugu rubripes and the image of the second Fugu rubripes;
Attack determination module, for determining body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes, the distance comprising body centre's coordinate of the first Fugu rubripes and the second Fugu rubripes at the image of described multiple frame is less than 1/2 of the body length of described first Fugu rubripes or the second Fugu rubripes, the angle of the body axes of the first Fugu rubripes and the second Fugu rubripes is that 75 degree of angles are to an angle of 90 degrees, and the body surface of described first Fugu rubripes or the second Fugu rubripes is when having corresponding biting, determine that described first Fugu rubripes and the second Fugu rubripes have attack,
Warning message sending module, for when determining there is the Fugu rubripes of the attacker of attack in described first Fugu rubripes and the second Fugu rubripes, the Fugu rubripes obtaining described attacker has the number of times of attack in preset time period, and when described number of times exceeds preset times, send warning message to poultry feeders;
Wherein, the Geometric center coordinates of described Fugu rubripes is the coordinate of the mid point of the health of Fugu rubripes, the body axes coordinate of described Fugu rubripes is the coordinate of the head of Fugu rubripes and the line of centre of body weight, and body centre's coordinate of described first Fugu rubripes and the second Fugu rubripes is the head of the first Fugu rubripes and the second Fugu rubripes and the line coordinate of body centre.
8. system according to claim 7, is characterized in that, described coordinate determination module, for:
The image of the Fugu rubripes in the image of described pretreated multiple frame is detected by background subtraction;
By the Image Segmentation Using of Pulse Coupled Neural Network algorithm to described Fugu rubripes;
The image of example filtering algorithm to described Fugu rubripes is utilized to follow the tracks of, and the Geometric center coordinates of the first Fugu rubripes and the second Fugu rubripes and body axes coordinate in the image of the described Fugu rubripes of real-time calculating.
9. system according to claim 7, is characterized in that, described attack determination module, for:
The Geometric center coordinates of Fugu rubripes in the image of the first Fugu rubripes in the image of described multiple frame and the image of the second Fugu rubripes and body axes coordinate are contrasted, in the image of present frame and former frame, the body axes coordinate of the first Fugu rubripes changes, and the body axes coordinate of the second Fugu rubripes changes in the image of present frame and next frame, then determine that the first Fugu rubripes is the Fugu rubripes of attacker, the second Fugu rubripes is by the Fugu rubripes of attacker.
10. system according to claim 9, is characterized in that, described system also comprises:
Attack number of times mark module, for passing through SIFT feature extraction algorithm, extract described by the surface characteristics of the Fugu rubripes of attacker, and judge describedly whether had corresponding biting by the body surface of the Fugu rubripes of attacker according to described surface characteristics, when there being corresponding biting, record the label of the Fugu rubripes of described attacker;
Accordingly, described warning message sending module, for:
When the number of times of described labelled notation exceedes preset times, send warning message to poultry feeders.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510252761.0A CN104933402B (en) | 2015-05-18 | 2015-05-18 | A kind of Fugu rubripes attack monitoring and early warning method based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510252761.0A CN104933402B (en) | 2015-05-18 | 2015-05-18 | A kind of Fugu rubripes attack monitoring and early warning method based on computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104933402A true CN104933402A (en) | 2015-09-23 |
| CN104933402B CN104933402B (en) | 2018-07-06 |
Family
ID=54120562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510252761.0A Active CN104933402B (en) | 2015-05-18 | 2015-05-18 | A kind of Fugu rubripes attack monitoring and early warning method based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104933402B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469165A (en) * | 2015-12-16 | 2016-04-06 | 中国农业大学 | Early warning method, device and system of river crab agonistic behavior |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090110289A1 (en) * | 2007-10-31 | 2009-04-30 | The Boeing Company | Image processing of apparatus condition |
| CN101719216B (en) * | 2009-12-21 | 2012-01-04 | 西安电子科技大学 | Movement human abnormal behavior identification method based on template matching |
| CN104008367A (en) * | 2014-05-08 | 2014-08-27 | 中国农业大学 | Automatic fattening pig behavior analyzing system and method based on computer vision |
-
2015
- 2015-05-18 CN CN201510252761.0A patent/CN104933402B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090110289A1 (en) * | 2007-10-31 | 2009-04-30 | The Boeing Company | Image processing of apparatus condition |
| CN101719216B (en) * | 2009-12-21 | 2012-01-04 | 西安电子科技大学 | Movement human abnormal behavior identification method based on template matching |
| CN104008367A (en) * | 2014-05-08 | 2014-08-27 | 中国农业大学 | Automatic fattening pig behavior analyzing system and method based on computer vision |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105469165A (en) * | 2015-12-16 | 2016-04-06 | 中国农业大学 | Early warning method, device and system of river crab agonistic behavior |
| CN105469165B (en) * | 2015-12-16 | 2021-09-28 | 中国农业大学 | River crab fighting behavior early warning method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104933402B (en) | 2018-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fang et al. | Comparative study on poultry target tracking algorithms based on a deep regression network | |
| Pinkiewicz et al. | A computer vision system to analyse the swimming behaviour of farmed fish in commercial aquaculture facilities: a case study using cage-held Atlantic salmon | |
| CN106259095A (en) | The behavior of a kind of pond cultured freshwater fish is to the determination methods in terms of aquaculture | |
| CN112000051A (en) | Livestock breeding management system based on Internet of things | |
| CN112734731B (en) | Livestock temperature detection method, device, equipment and storage medium | |
| CN107248252B (en) | Efficient forest fire detection system | |
| CN104008367A (en) | Automatic fattening pig behavior analyzing system and method based on computer vision | |
| CN106447672B (en) | It is a kind of intersection block fish body identification method of counting | |
| CN104969875A (en) | Pet behavior detection system based on image change | |
| CN113662530B (en) | Pig physiological growth state monitoring and early warning method | |
| CN110287902B (en) | Livestock and poultry survival detection method, device, equipment and computer program product | |
| WO2022247500A1 (en) | Piglet anti-crushing early warning method and apparatus, device, and storage medium | |
| CN112386765B (en) | Intelligent infusion monitoring system based on 5G | |
| CN111680587B (en) | Multi-target tracking-based chicken flock activity real-time estimation method and system | |
| CN113076818A (en) | Pet excrement identification method and device and computer readable storage medium | |
| CN104933402A (en) | Fugu rubripe attacking behavior monitoring and early warning method based on computer vision | |
| CN112265881B (en) | Elevator monitoring system, monitoring method, monitoring device and storage medium for livestock | |
| CN113507490A (en) | Multi-source information fusion live pig full-chain intelligent monitoring method and device | |
| Goehner et al. | A comparison of background subtraction algorithms for detecting avian nesting events in uncontrolled outdoor video | |
| CN111860326B (en) | Building site article movement detection method, device, equipment and storage medium | |
| CN113393628A (en) | Intelligent monitoring alarm method, system, intelligent terminal and storage medium | |
| CN110008881B (en) | Method and device for identifying cow behaviors of multiple moving targets | |
| Zador et al. | Determining spatial and temporal overlap of an endangered seabird with a large commercial trawl fishery | |
| CN115342937B (en) | Temperature anomaly detection method and device | |
| CN111414811A (en) | Pig drinking water monitoring system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |