CN107730501A - A kind of fish body tail frequency detection method and system - Google Patents
A kind of fish body tail frequency detection method and system Download PDFInfo
- Publication number
- CN107730501A CN107730501A CN201711062340.7A CN201711062340A CN107730501A CN 107730501 A CN107730501 A CN 107730501A CN 201711062340 A CN201711062340 A CN 201711062340A CN 107730501 A CN107730501 A CN 107730501A
- Authority
- CN
- China
- Prior art keywords
- fish body
- point
- tail
- target
- fish
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The present invention discloses a kind of fish body tail frequency detection method and system.By obtaining fish body target gray image;Adaptive segmentation threshold is obtained according to fish body target gray image intensity value, binaryzation fish body target image is obtained to fish body target gray image dividing processing by segmentation threshold;The position of fish body moving target center of mass point and the area of fish body target area are obtained according to binaryzation fish body target image;Using the area of the position of target centroid point and target area as tracking feature to object real-time tracking;The coordinate of fish body tail point and head point is obtained according to the fish body target centroid of tracking and profile point coordinates;Fish body tail fin swing angle is obtained according to the coordinate of fish body moving target barycenter point coordinates, fish body tail point and fish body head point;Fish body is calculated according to fish body tail fin swing angle to wag the tail value;Fish body tail beat frequency is calculated according to wag the tail value and video frame rate of fish body.Using the fish body tail frequency detection method and system of the present invention, the error of the fish body tail frequency changing rule of acquisition is small, and reliability is high.
Description
Technical field
The present invention relates to detection field, more particularly to a kind of fish body tail frequency detection method and system.
Background technology
The main stream approach of research fish body tail frequency is to extract fish body skeleton by computer vision technique to obtain fish at present
The changing rule of body tail frequency.And the computing of fish body skeleton pattern obtains center framework firstly the need of using multiple curve matching mode
Line, then skeleton pattern is established based on Medial-Axis Transformation thought, if being finally fitted the translation equation that soma envelope and soma are done, obtain
Proper long theoretical coefficient, and then establish fish body soma motion model;Calculating process is complex, and real-time is poor, can not meet
The demand that video is handled in real time;The method solving result of multiple curve matching mode and fitting soma envelope being capable of approaching to reality
Fish body tail beat frequency, but its error is larger, and reliability is relatively low.
The content of the invention
It is an object of the invention to provide a kind of fish body tail frequency detection method and system so that the fish body tail frequency change rule of acquisition
The error of rule is small, and reliability is high.
To achieve the above object, the invention provides following scheme:
A kind of fish body tail frequency detection method, it is characterised in that obtain fish body target gray image;According to the fish body target
The gray values of gray level image, adaptive segmentation threshold is obtained using maximum between-cluster variance algorithm, passes through the adaptivenon-uniform sampling
Threshold value obtains binaryzation fish body target image to the fish body target gray image dividing processing;According to the binaryzation fish body mesh
Logo image obtains the position of fish body moving target center of mass point and the area of fish body target area;With the fish body moving target barycenter
Point position and the fish body target area area as tracking feature to object real-time tracking;According to the fish body accurately tracked
Target centroid and profile point coordinates obtain the coordinate of fish body tail point and head point;According to the fish body moving target barycenter point coordinates,
The coordinate of the fish body tail point and the fish body head point obtains fish body tail fin swing angle;According to the fish body tail fin swing angle
Fish body is calculated to wag the tail value;Fish body tail beat frequency is calculated according to wag the tail value and video frame rate of the fish body.
Optionally, the acquisition fish body target gray image, is specifically included:
Fish body motion video image progress statistics background modeling is obtained into current background image;Carry out present frame and institute
The difference operation for stating background image obtains fish body target gray image;Moving target is not included in the background image.
Optionally, position and the fish that fish body moving target center of mass point is obtained according to the binaryzation fish body target image
The area of body target area, is specifically included:The binaryzation fish body target image got is corroded and expansive working,
The zonule noise spot of the binaryzation fish body target image is removed, and fraction overlapping region is separated, small holes and edge
Lost part is filled, and fraction noise region still has;
All connected regions less than target area are filtered out, it is complete to retain fish body target area, the fish body target area
For the connected region in the image after filtering process, the connected region center of mass point is fish body moving target center of mass point.
Optionally, it is described using the area of the position of the fish body moving target center of mass point and the fish body target area as
Tracking feature is to object real-time tracking;Fish body tail point and head are obtained according to the fish body target centroid and profile point coordinates accurately tracked
The coordinate of point, is specifically included:
The connected region profile point is obtained according to C={ (x (1), y (1)), (x (2), y (2)) ... (x (n), y (n)) }
Set, wherein, C represents the set of the connected region profile point, (x (1), y (1)), (x (2), y (2)) ... (x (n), y
(n) profile point in the connected region) is represented;
The fish body tail point is the farthest point of fish body moving target center of mass point described in distance in the connected region profile point;
According toThe connected region profile point is calculated to the fish body
The distance of moving target center of mass point position, wherein disCc(t) represent the connected region profile point to the fish body moving target
The distance of center of mass point position, (x (t), y (t)) represent the coordinate of the connected region profile point, (xc,yc) represent the fish body fortune
Moving-target barycenter point coordinates;
According to t=argmax (disCc(t) dis) is calculatedCc(t) correspondence profile point t when taking maximum;
According to (xt,ytCoordinate (the x that the coordinate that)=C (x (t), y (t)) calculates the fish body tail point is correspondence profile point t
(t),y(t))。
Optionally, it is described using the area of the position of the fish body moving target center of mass point and the fish body target area as
Tracking feature, obtain the coordinate of fish body head point;Specifically include:
The fish body moving target center of mass point and the fish body tail point are located on straight line, the fish body head point and fish body
For tail point respectively positioned at the both sides of the vertical line of the straight line, the fish body head point is the vertical line non-tail point side connected region of the straight line
The point farthest apart from barycenter in the profile point of domain;
According toCalculate profile point (x corresponding to the fish body head point
(h), y (h)), wherein, h be the fish body head point to the connected region profile point on ultimate range, (xc,yc) described in expression
Fish body moving target barycenter point coordinates, (x (h), y (h)) represent profile point corresponding to the fish body head point;
According to (xh,yhThe coordinate that)=C (x (h), y (h)) calculates the fish body head point is corresponding profile point h coordinate.
Optionally, it is described according to the fish body moving target barycenter point coordinates, the fish body tail point and the fish body head point
Coordinate obtain fish body tail fin swing angle, specifically include:
According toThe fish body moving target center of mass point is obtained to the fish body head point
Distance disch;
According toThe fish body moving target center of mass point is obtained to the fish body tail point
Distance disct;
According toThe fish body head point is obtained to the distance dis of the fish body tail pointth;
Wherein, the fish body moving target barycenter point coordinates is (xc,yc), the coordinate of the fish body head point position is (xh,yh), it is described
The coordinate of fish body tail point position is (xt,yt);
According toFish body tail fin is obtained to swing
Angle, wherein, β represents fish body tail fin swing angle, disctRepresent the fish body moving target center of mass point to the fish body tail point
Distance, dischRepresent the fish body moving target center of mass point to the distance of the fish body head point, disthRepresent the fish body head
Distance of the point to the fish body tail point.
Optionally, it is described fish body is obtained according to the fish body tail fin swing angle to wag the tail value, specifically include:Define angle of oscillation
Degree threshold value is βT, in different frame, same fish body tail fin swing angle β >=βT, number of oscillations is updated, otherwise, number of oscillations is not
Renewal;
According toFish body tail fin in kth frame video is calculated to wag the tail value, wherein, β expression fish body tails
Fin swing angle, βTRepresent swing angle threshold value.
Optionally, it is described that fish body tail beat frequency is obtained according to wag the tail value and video frame rate of the fish body, specifically include:
According to formulaCalculate n-th frame video and correspond to fish body tail frequency in the time, wherein, fβRepresent fish body
The size of tail frequency, ββ(k) angle that tail fin is swung is represented, r represents video frame rate, and n represents the frame number of video.
To achieve these goals, present invention also offers following scheme:
A kind of fish body tail frequency detecting system, the fish body fish body tail frequency detecting system are used to detect fish body tail frequency, including:
Fish body target gray image collection module, for obtaining fish body target gray image;
Binaryzation fish body target image acquisition module, for the gray values according to the fish body target gray image, is adopted
Adaptive segmentation threshold is obtained with maximum between-cluster variance algorithm, by the adaptivenon-uniform sampling threshold value to the fish body target gray
Image dividing processing obtains binaryzation fish body target image;
The position of fish body moving target center of mass point and the area acquisition module of fish body target area, for according to the two-value
Change fish body target image and obtain the position of fish body moving target center of mass point and the area of fish body target area;
Fish body tail point and fish body head point coordinates acquisition module, for the position of the fish body moving target center of mass point and institute
The area of fish body target area is stated as tracking feature to object real-time tracking;According to the fish body target centroid and wheel accurately tracked
Wide point coordinates obtains the coordinate of fish body tail point and head point;
Fish body tail fin swing angle acquisition module, for according to the fish body moving target barycenter point coordinates, the fish body
The coordinate of tail point and the fish body head point obtains fish body tail fin swing angle;
Fish body is wagged the tail value module, is wagged the tail value for calculating fish body according to the fish body tail fin swing angle;
Fish body tail beat frequency module, for calculating fish body tail beat frequency according to wag the tail value and video frame rate of the fish body.
According to specific embodiment provided by the invention, the invention discloses following technique effect:
Method and system provided by the invention only needs to establish fish by fish body barycenter, tail point, head point position relationship feature
Body is wagged the tail angle solving model, and the analysis can that the analysis of fish body target area is converted into key feature points directly obtains fish
Body tail frequency, without building fish body skeleton, algorithm model of the invention is simple, and complexity is low, and real-time is preferable, the fish body tail of acquisition
Frequency changing rule error is small, and reliability is high.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is fish body tail frequency detection method flow chart of the present invention;
Fig. 2 is fish body tail frequency detecting system structure chart of the present invention;
Fig. 3 is fish body water quality monitoring experimental configuration of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
It is an object of the invention to provide a kind of fish body tail frequency detection method and system so that the fish body tail frequency change rule of acquisition
The error of rule is small, and reliability is high.
In order to facilitate the understanding of the purposes, features and advantages of the present invention, it is below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is further detailed explanation.
Fig. 1 is fish body tail frequency detection method flow chart of the present invention, and methods described includes:
Step 101:Obtain fish body target gray image;
Step 102:According to the gray values of the fish body target gray image, it is obtained from using maximum between-cluster variance algorithm
Segmentation threshold is adapted to, binaryzation fish is obtained to the fish body target gray image dividing processing by the adaptivenon-uniform sampling threshold value
Body target image;
Step 103:Position and the fish body of fish body moving target center of mass point are obtained according to the binaryzation fish body target image
The area of target area;
Step 104:Using the area of the position of the fish body moving target center of mass point and the fish body target area as chasing after
Track feature is to object real-time tracking;Fish body tail point and head point are obtained according to the fish body target centroid and profile point coordinates accurately tracked
Coordinate
Step 105:According to the seat of the fish body moving target barycenter point coordinates, the fish body tail point and the fish body head point
Mark obtains fish body tail fin swing angle;
Step 106:Fish body is calculated according to the fish body tail fin swing angle to wag the tail value;
Step 107:Fish body tail beat frequency is calculated according to wag the tail value and video frame rate of the fish body.
In step 101, the acquisition fish body target gray image, specifically include:
Fish body motion video image progress statistics background modeling is obtained into current background image;Carry out present frame and institute
The difference operation for stating background image obtains fish body target gray image;Moving target is not included in the background image.
In step 102, position and the fish of fish body moving target center of mass point are obtained according to the binaryzation fish body target image
The area of body target area, is specifically included:
The binaryzation fish body target image got is corroded and expansive working, the binaryzation fish body target
The zonule noise spot of image is removed, and fraction overlapping region is separated, and small holes and edge lost part are filled, small portion
Point noise region still has;
All connected regions less than target area are filtered out, it is complete to retain fish body target area, the fish body target area
For the connected region in the image after filtering process, the connected region center of mass point is fish body moving target center of mass point.
After filtered processing, all connected regions in image are fish body target area.With connected region centroid position
Equivalent fish body moving target centroid position.The rank of fish body target area 0 away from 1 rank away from as shown in Equation 1:
Wherein M00Represent 0 rank away from M01And M10Represent 1 rank away from the pixel number that, x and y are respectively image length and width direction, G
(i, j) is the binary image pixel value after filtered processing, then fish body target area center-of-mass coordinate is:
In step 104, using the area of the position of the fish body moving target center of mass point and the fish body target area as
Tracking feature is to object real-time tracking;Fish body tail point and head are obtained according to the fish body target centroid and profile point coordinates accurately tracked
The coordinate of point, is specifically included:
The connected region profile point is obtained according to C={ (x (1), y (1)), (x (2), y (2)) ... (x (n), y (n)) }
Set, wherein, C represents the set of the connected region profile point, (x (1), y (1)), (x (2), y (2)) ... (x (n), y
(n) profile point in the connected region) is represented;
The fish body tail point is the farthest point of fish body moving target center of mass point described in distance in the connected region profile point;
According toThe connected region profile point is calculated to the fish body
The distance of moving target center of mass point position, wherein disCc(t) represent the connected region profile point to the fish body moving target
The distance of center of mass point position, (x (t), y (t)) represent the coordinate of the connected region profile point, (xc,yc) represent the fish body fortune
Moving-target barycenter point coordinates;
According to t=argmax (disCc(t) dis) is calculatedCc(t) correspondence profile point t when taking maximum;
According to (xt,ytCoordinate (the x that the coordinate that)=C (x (t), y (t)) calculates the fish body tail point is correspondence profile point t
(t),y(t))。
It is described special using the area of the position of the fish body moving target center of mass point and the fish body target area as tracking
Sign, obtain the coordinate of fish body head point;Specifically include:
The fish body moving target center of mass point and the fish body tail point are located on straight line, the fish body head point and fish body
For tail point respectively positioned at the both sides of the vertical line of the straight line, the fish body head point is the vertical line non-tail point side connected region of the straight line
The point farthest apart from barycenter in the profile point of domain;
According toCalculate profile point (x corresponding to the fish body head point
(h), y (h)), wherein, h be the fish body head point to the connected region profile point on ultimate range, (xc,yc) described in expression
Fish body moving target barycenter point coordinates, (x (h), y (h)) represent profile point corresponding to the fish body head point;
According to (xh,yhThe coordinate that)=C (x (h), y (h)) calculates the fish body head point is corresponding profile point h coordinate.
The coordinate according to the fish body moving target barycenter point coordinates, the fish body tail point and the fish body head point obtains
Fish body tail fin swing angle is taken, is specifically included:
According toThe fish body moving target center of mass point is obtained to the fish body head point
Distance disch;
According toThe fish body moving target center of mass point is obtained to the fish body tail point
Distance disct;
According toThe fish body head point is obtained to the distance dis of the fish body tail pointth;
Wherein, the fish body moving target barycenter point coordinates is (xc,yc), the coordinate of the fish body head point position is (xh,yh), it is described
The coordinate of fish body tail point position is (xt,yt);
In step 105, according toObtain fish
Body tail fin swing angle, wherein, β represents fish body tail fin swing angle, disctRepresent the fish body moving target center of mass point to institute
State the distance of fish body tail point, dischRepresent the fish body moving target center of mass point to the distance of the fish body head point, disthRepresent
Distance of the fish body head point to the fish body tail point.
It is described fish body is obtained according to the fish body tail fin swing angle to wag the tail value, specifically include:Define swing angle threshold value
For βT, in different frame, same fish body tail fin swing angle β >=βT, number of oscillations is updated, otherwise, number of oscillations does not update;
In step 106, according toFish body tail fin in kth frame video is calculated to wag the tail value, wherein, β
Represent fish body tail fin swing angle, βTRepresent swing angle threshold value.
It is described that fish body tail beat frequency is obtained according to wag the tail value and video frame rate of the fish body in step 107, specifically include:
According to formulaCalculate n-th frame video and correspond to fish body tail frequency in the time, wherein, fβRepresent fish body
The size of tail frequency, ββ(k) angle that tail fin is swung is represented, r represents video frame rate, and n represents the frame number of video.
Fig. 2 is fish body tail frequency detecting system structure chart of the present invention, and the fish body fish body tail frequency detecting system is used to detect fish
Body tail frequency, including:
Fish body target gray image collection module 201, for obtaining fish body target gray image;
Binaryzation fish body target image acquisition module 202, for the gray values according to the fish body target gray image,
Adaptive segmentation threshold is obtained using maximum between-cluster variance algorithm, by the adaptivenon-uniform sampling threshold value to fish body target ash
Degree image dividing processing obtains binaryzation fish body target image;
The position of fish body moving target center of mass point and the area acquisition module 203 of fish body target area, for according to
Binaryzation fish body target image obtains the position of fish body moving target center of mass point and the area of fish body target area;
Fish body tail point and fish body head point coordinates acquisition module 204, for the position of the fish body moving target center of mass point
With the area of the fish body target area as tracking feature to object real-time tracking;According to the fish body target centroid accurately tracked
The coordinate of fish body tail point and head point is obtained with profile point coordinates;
Fish body tail fin swing angle acquisition module 205, for according to the fish body moving target barycenter point coordinates, the fish
The coordinate of body tail point and the fish body head point obtains fish body tail fin swing angle;
Fish body is wagged the tail value module 206, is wagged the tail value for calculating fish body according to the fish body tail fin swing angle;
Fish body tail beat frequency module 207, for calculating fish body tail beat frequency according to wag the tail value and video frame rate of the fish body.
The research method of Fish behavior has field measurement method, fishery harvesting experimental method, flume experiment method and mathematical simulation method]
Deng, wherein, fish body motor behavior monitoring water quality on line system mainly uses flume experiment method.For test system performance, this hair
It is bright to devise laboratory biological water quality monitoring system.Gather fish body sport video in real time by camera, be transferred to computer end
LabVIEW software platforms are handled, and by obtaining fish body motion state parameterses tail frequency, fish body tail frequency is shown by software platform
Analysis result.Fig. 3 is fish body water quality monitoring experimental configuration of the present invention;
Corresponding major experimental equipment has:
(1) fish jar is tested:Fish jar size is 35cm*20cm*30cm, and wherein top view size is 35cm*20cm, is being gathered
Equal proportion zoom image during image;
(2) water:Experiment fish jar is added after running water standing is dechlorinated for 2-3 days;
(3) fish:From the red crucian of health, after culture 2-3 angels fish body adaptation water environment+tested;
(4) handstone:Colored handstone is added in fish jar is tested, simulates fish body real life environments;
(5) pH monitorings meter:For test experience water pH value;
(6) pump is supplied oxygen:For supplying oxygen, ensure there is the dissolved oxygen of abundance in water, fish body is full of activity;
(7) camera support:For supporting camera, camera heights are adjusted;
(8) industrial camera:Video image is tested for gathering;
(9)PC:By LabVIEW software monitoring systems, and analyze and process experimental data;
(10) gigabit network cable:Camera, by gigabit network interface connection, ensures video data transmission rate with PC ends.
Each embodiment is described by the way of progressive in this specification, what each embodiment stressed be and other
The difference of embodiment, between each embodiment identical similar portion mutually referring to.
Specific case used herein is set forth to the principle and embodiment of the present invention, and above example is said
It is bright to be only intended to help the method and its core concept for understanding the present invention;Meanwhile for those of ordinary skill in the art, foundation
The thought of the present invention, in specific embodiments and applications there will be changes.In summary, this specification content is not
It is interpreted as limitation of the present invention.
Claims (9)
- A kind of 1. fish body tail frequency detection method, it is characterised in thatObtain fish body target gray image;According to the gray values of the fish body target gray image, adaptivenon-uniform sampling threshold is obtained using maximum between-cluster variance algorithm Value, binaryzation fish body target figure is obtained by the adaptivenon-uniform sampling threshold value to the fish body target gray image dividing processing Picture;The position of fish body moving target center of mass point and the face of fish body target area are obtained according to the binaryzation fish body target image Product;Using the area of the position of the fish body moving target center of mass point and the fish body target area as tracking feature to target Real-time tracking;The coordinate of fish body tail point and head point is obtained according to the fish body target centroid and profile point coordinates accurately tracked;Fish body tail is obtained according to the coordinate of the fish body moving target barycenter point coordinates, the fish body tail point and the fish body head point Fin swing angle;Fish body is calculated according to the fish body tail fin swing angle to wag the tail value;Fish body tail beat frequency is calculated according to wag the tail value and video frame rate of the fish body.
- 2. according to the method for claim 1, it is characterised in that the acquisition fish body target gray image, specifically include:Fish body motion video image progress statistics background modeling is obtained into current background image;The difference operation for carrying out present frame and the background image obtains fish body target gray image;Do not include in the background image Moving target.
- 3. according to the method for claim 1, it is characterised in that described that fish is obtained according to the binaryzation fish body target image The position of body moving target center of mass point and the area of fish body target area, are specifically included:The binaryzation fish body target image got is corroded and expansive working, the binaryzation fish body target image Zonule noise spot be removed, fraction overlapping region is separated, and small holes and edge lost part are filled, and fraction is made an uproar Sound area domain still has;All connected regions less than target area are filtered out, complete to retain fish body target area, the fish body target area is filter The connected region in image after ripple processing, the connected region center of mass point is fish body moving target center of mass point.
- 4. according to the method for claim 1, it is characterised in that the position with the fish body moving target center of mass point and The area of the fish body target area is as tracking feature to object real-time tracking;According to the fish body target centroid that accurately tracks and Profile point coordinates obtains the coordinate of fish body tail point and head point, specifically includes:The collection of the connected region profile point is obtained according to C={ (x (1), y (1)), (x (2), y (2)) ... (x (n), y (n)) } Close, wherein, C represents the set of the connected region profile point, (x (1), y (1)), (x (2), y (2)) ... (x (n), y (n)) table Show the profile point in the connected region;The fish body tail point is that fish body described in distance moves mesh in the connected region profile point Mark the farthest point of center of mass point;According toThe connected region profile point is calculated to move to the fish body The distance of target centroid point position, wherein disCc(t) represent the connected region profile point to the fish body moving target barycenter The distance of point position, (x (t), y (t)) represent the coordinate of the connected region profile point, (xc,yc) represent the fish body motion mesh Mark barycenter point coordinates;According to t=argmax (disCc(t) dis) is calculatedCc(t) correspondence profile point t when taking maximum;According to (xt,ytCoordinate (x (t), the y that the coordinate that)=C (x (t), y (t)) calculates the fish body tail point is correspondence profile point t (t))。
- 5. according to the method for claim 1, it is characterised in that the fish body target centroid and profile that the basis accurately tracks Point coordinates obtains the coordinate of fish body tail point and head point, obtains the coordinate of fish body head point;Specifically include:The fish body moving target matter Heart point and the fish body tail point are located on straight line, and the fish body head point and fish body tail point are located at the vertical line of the straight line respectively Both sides, the fish body head point is farthest apart from barycenter in the non-tail point side connected region profile point of vertical line of the straight line Point;According toCalculate profile point (x (h), y corresponding to the fish body head point (h)), wherein, h be the fish body head point to the connected region profile point on ultimate range, (xc,yc) represent the fish body Moving target barycenter point coordinates, (x (h), y (h)) represent profile point corresponding to the fish body head point;According to (xh,yhThe coordinate that)=C (x (h), y (h)) calculates the fish body head point is corresponding profile point h coordinate.
- 6. according to the method for claim 1, it is characterised in that it is described according to the fish body moving target barycenter point coordinates, The coordinate of the fish body tail point and the fish body head point obtains fish body tail fin swing angle, specifically includes:According toObtain the fish body moving target center of mass point to the fish body head point away from From disch;According toThe fish body moving target center of mass point is obtained to the distance of the fish body tail point disct;According toThe fish body head point is obtained to the distance dis of the fish body tail pointth;Its In, the fish body moving target barycenter point coordinates is (xc,yc), the coordinate of the fish body head point position is (xh,yh), the fish The coordinate of body tail point position is (xt,yt);According toObtain fish body tail fin angle of oscillation Degree, wherein, β represents fish body tail fin swing angle, disctRepresent the fish body moving target center of mass point to the fish body tail point Distance, dischRepresent the fish body moving target center of mass point to the distance of the fish body head point, disthRepresent the fish body head point To the distance of the fish body tail point.
- 7. according to the method for claim 1, it is characterised in that described that fish body is obtained according to the fish body tail fin swing angle Wag the tail value, specifically include:It is β to define swing angle threshold valueT, in different frame, same fish body tail fin swing angle β >=βT, to pendulum Dynamic number renewal, otherwise, number of oscillations does not update;According toFish body tail fin in kth frame video is calculated to wag the tail value, wherein, β represents that fish body tail fin is put Dynamic angle, βTRepresent swing angle threshold value.
- 8. according to the method for claim 1, it is characterised in that it is described according to the fish body wag the tail value and video frame rate acquisition Fish body tail beat frequency, is specifically included:According to formulaCalculate n-th frame video and correspond to fish body tail frequency in the time, wherein, fβRepresent fish body tail frequency Size, ββ(k) angle that tail fin is swung is represented, r represents video frame rate, and n represents the frame number of video.
- 9. a kind of fish body tail frequency detecting system, the fish body tail frequency detecting system is applied to detection fish body tail frequency, it is characterised in that Including:Fish body target gray image collection module, for obtaining fish body target gray image;Binaryzation fish body target image acquisition module, for the gray values according to the fish body target gray image, using most Variance algorithm obtains adaptive segmentation threshold between major class, by the adaptivenon-uniform sampling threshold value to the fish body target gray image Dividing processing obtains binaryzation fish body target image;The position of fish body moving target center of mass point and the area acquisition module of fish body target area, for according to the binaryzation fish Body target image obtains the position of fish body moving target center of mass point and the area of fish body target area;Fish body tail point and fish body head point coordinates acquisition module, for the position of the fish body moving target center of mass point and the fish The area of body target area is as tracking feature to object real-time tracking;According to the fish body target centroid and profile point accurately tracked Coordinate obtains the coordinate of fish body tail point and head point;Fish body tail fin swing angle acquisition module, for according to the fish body moving target barycenter point coordinates, the fish body tail point Fish body tail fin swing angle is obtained with the coordinate of the fish body head point;Fish body is wagged the tail value module, is wagged the tail value for calculating fish body according to the fish body tail fin swing angle;Fish body tail beat frequency module, for calculating fish body tail beat frequency according to wag the tail value and video frame rate of the fish body.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711062340.7A CN107730501A (en) | 2017-11-02 | 2017-11-02 | A kind of fish body tail frequency detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711062340.7A CN107730501A (en) | 2017-11-02 | 2017-11-02 | A kind of fish body tail frequency detection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107730501A true CN107730501A (en) | 2018-02-23 |
Family
ID=61222184
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711062340.7A Pending CN107730501A (en) | 2017-11-02 | 2017-11-02 | A kind of fish body tail frequency detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107730501A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109145808A (en) * | 2018-08-17 | 2019-01-04 | 郑州轻工业学院 | A kind of tuna recognition methods based on adaptive fish body bending die |
CN110702869A (en) * | 2019-11-01 | 2020-01-17 | 无锡中科水质环境技术有限公司 | Fish stress avoidance behavior water quality monitoring method based on video image analysis |
CN111199551A (en) * | 2020-01-06 | 2020-05-26 | 北京农业信息技术研究中心 | Target segmentation method and system for fish overlapped image |
CN113379800A (en) * | 2021-06-11 | 2021-09-10 | 山东大学 | Single fish three-dimensional track and orientation tracking method and system based on biorthogonal view |
CN113516635A (en) * | 2021-06-15 | 2021-10-19 | 中国农业大学 | Fish-vegetable symbiotic system and vegetable nitrogen element demand estimation method based on fish behaviors |
CN115063885A (en) * | 2022-06-14 | 2022-09-16 | 中国科学院水生生物研究所 | Method and system for analyzing fish motion characteristics |
CN116245361A (en) * | 2023-02-21 | 2023-06-09 | 中国农业大学 | Method, device and system for early warning of nitrogen concentration in industrial fish-vegetable symbiotic circulating water |
-
2017
- 2017-11-02 CN CN201711062340.7A patent/CN107730501A/en active Pending
Non-Patent Citations (1)
Title |
---|
彭红梅: ""基于生物水质监测的鱼体运动状态检测系统研究"", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109145808A (en) * | 2018-08-17 | 2019-01-04 | 郑州轻工业学院 | A kind of tuna recognition methods based on adaptive fish body bending die |
CN110702869A (en) * | 2019-11-01 | 2020-01-17 | 无锡中科水质环境技术有限公司 | Fish stress avoidance behavior water quality monitoring method based on video image analysis |
CN111199551A (en) * | 2020-01-06 | 2020-05-26 | 北京农业信息技术研究中心 | Target segmentation method and system for fish overlapped image |
CN113379800A (en) * | 2021-06-11 | 2021-09-10 | 山东大学 | Single fish three-dimensional track and orientation tracking method and system based on biorthogonal view |
CN113379800B (en) * | 2021-06-11 | 2022-07-29 | 山东大学 | Single fish three-dimensional track and orientation tracking method and system based on biorthogonal view |
CN113516635A (en) * | 2021-06-15 | 2021-10-19 | 中国农业大学 | Fish-vegetable symbiotic system and vegetable nitrogen element demand estimation method based on fish behaviors |
CN113516635B (en) * | 2021-06-15 | 2024-02-27 | 中国农业大学 | Fish and vegetable symbiotic system and vegetable nitrogen element demand estimation method based on fish behaviors |
CN115063885A (en) * | 2022-06-14 | 2022-09-16 | 中国科学院水生生物研究所 | Method and system for analyzing fish motion characteristics |
CN115063885B (en) * | 2022-06-14 | 2023-06-23 | 中国科学院水生生物研究所 | Analysis method and system for fish motion characteristics |
CN116245361A (en) * | 2023-02-21 | 2023-06-09 | 中国农业大学 | Method, device and system for early warning of nitrogen concentration in industrial fish-vegetable symbiotic circulating water |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107730501A (en) | A kind of fish body tail frequency detection method and system | |
CN105069746B (en) | Video real-time face replacement method and its system based on local affine invariant and color transfer technology | |
CN104715493B (en) | A kind of method of movement human Attitude estimation | |
CN101604447B (en) | No-mark human body motion capture method | |
CN109285179A (en) | A kind of motion target tracking method based on multi-feature fusion | |
CN106251399A (en) | A kind of outdoor scene three-dimensional rebuilding method based on lsd slam | |
CN104484868B (en) | The moving target of a kind of combination template matches and image outline is taken photo by plane tracking | |
Elfiky et al. | Automation of dormant pruning in specialty crop production: An adaptive framework for automatic reconstruction and modeling of apple trees | |
CN107808123A (en) | The feasible area detecting method of image, electronic equipment, storage medium, detecting system | |
Bender et al. | Computer-assisted 3D kinematic analysis of all leg joints in walking insects | |
CN102184541A (en) | Multi-objective optimized human body motion tracking method | |
CN107993250A (en) | A kind of fast multi-target pedestrian tracking and analysis method and its intelligent apparatus | |
CN109508741A (en) | Method based on deep learning screening training set | |
CN108280852A (en) | A kind of door and window point cloud shape detecting method and system based on laser point cloud data | |
CN110223317A (en) | A kind of Moving target detection based on image procossing and trajectory predictions method | |
CN105243375A (en) | Motion characteristics extraction method and device | |
CN108182416A (en) | A kind of Human bodys' response method, system and device under monitoring unmanned scene | |
CN109766873A (en) | A kind of pedestrian mixing deformable convolution recognition methods again | |
CN106127161A (en) | Fast target detection method based on cascade multilayer detector | |
CN109087337A (en) | Long-time method for tracking target and system based on layering convolution feature | |
CN102156994B (en) | Joint positioning method for single-view unmarked human motion tracking | |
CN103390193A (en) | Automatic training device for navigation-oriented rat robot, and rat behavior identification method and training method | |
CN114240866B (en) | Tissue culture seedling grading method and device based on two-dimensional image and three-dimensional growth information | |
CN102592135A (en) | Visual tracking method of subspace fusing target space distribution and time sequence distribution characteristics | |
CN115131712A (en) | Intelligent counting method of drill rods driven by computer vision |
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: 20180223 |
|
RJ01 | Rejection of invention patent application after publication |