CN112686926A - Method and system for detecting motion of color sphere under complex light and shadow condition - Google Patents
Method and system for detecting motion of color sphere under complex light and shadow condition Download PDFInfo
- Publication number
- CN112686926A CN112686926A CN202011497227.3A CN202011497227A CN112686926A CN 112686926 A CN112686926 A CN 112686926A CN 202011497227 A CN202011497227 A CN 202011497227A CN 112686926 A CN112686926 A CN 112686926A
- Authority
- CN
- China
- Prior art keywords
- color
- video
- target
- motion
- light
- 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
Images
Abstract
The invention discloses a method and a system for detecting the motion of a color sphere under a complex light and shadow condition, wherein the method comprises the following steps: the method comprises the steps of obtaining a motion video of a color sphere under a complex light and shadow condition, analyzing the motion video, carrying out color sphere motion path detection on the analyzed motion video by utilizing a preset color superposition filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere, obtaining a detection result, verifying the detection result, and displaying the detection result after the verification is passed. The movement path of the color sphere can be accurately analyzed by utilizing the preset color superposition filtering algorithm and the scattering effects of the color sphere at different angles in the target environment, the coefficient of the influence of the heat radiation light of the color sphere can be taken into account on the basis of the prior art, the movement path of the color sphere can be more accurately obtained, and the accuracy is improved.
Description
Technical Field
The invention relates to the technical field of path detection, in particular to a method and a system for detecting motion of a color sphere under a complex light and shadow condition.
Background
Along with the improvement of living standard of people, more and more people carry out some recreational activities on weekends or holidays at ordinary times, wherein, billiard sports is popular with people, and can relax the body and mind and enable people to experience the pleasure of sports. However, the ambient light of the billiard hall is relatively complex, so that the situation of complex light and shadow often occurs, and the experience of hitting billiards by players is seriously affected, therefore, in the prior art, video shooting is performed on the motion of the colored ball, and then the motion track of the colored ball is drawn according to the video, but the method has the following defects: because the ambient light is complicated, and the colored ball body refracts light, the accuracy of the motion trail of the colored ball body drawn by simply utilizing the video cannot be ensured, so that the finally drawn motion trail is different from the actual motion trail of the colored ball body, and the experience of hitting billiards by players is greatly influenced.
Disclosure of Invention
Aiming at the problems shown above, the invention provides a method and a system for detecting the movement of a colored ball under the condition of complex light and shadow, which are used for solving the problems that the precision cannot be ensured by simply drawing the movement track of the colored ball by using a video because the ambient light is complex and the colored ball refracts light, so that the finally drawn movement track is different from the actual movement track of the colored ball, and the experience of hitting billiards by players is greatly influenced, which are mentioned in the background technology.
A color sphere motion detection method under the condition of complex light and shadow comprises the following steps:
acquiring a motion video of the color sphere under a complex light and shadow condition;
analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color superposition filtering algorithm and scattering effects of light in a target environment on the color sphere at different angles to obtain a detection result;
and verifying the detection result, and displaying the detection result after the verification is passed.
Preferably, before acquiring the motion video of the color sphere under the complex light and shadow condition, the method further comprises:
acquiring target position information of a target billiard table where the colorful ball is located;
detecting target light and shadow distribution information on the target billiard table;
analyzing the environmental characteristic parameters of the target environment of the target billiard table according to the target position information and the target light and shadow distribution information, wherein the environmental characteristic parameters comprise: simulating light and shadow parameters;
determining the complex light and shadow grade on the target billiard table according to the target light and shadow distribution information on the target billiard table;
and determining a target pixel used for shooting the color sphere based on the complex light and shadow grade and the environment characteristic parameters.
Preferably, the method for acquiring the motion video of the colored sphere under the condition of complex light and shadow comprises the following steps:
locking the shooting main body as the target billiard table;
recording a first video of a color ball on the target billiard table in the moving process by using the target pixel;
preprocessing the first video according to the pixel color gray scale variable quantity, the pixel color gray scale offset and the pixel color gray scale difference value in the target environment to obtain a second video;
and determining the second video as the motion video of the color sphere under the complex light shadow.
Preferably, before analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color overlay filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere, and obtaining a detection result, the method further includes:
acquiring a mass of preset videos, and detecting the qualification of the mass of preset videos;
reserving a first number of first preset videos with the eligibility being larger than or equal to a preset threshold value, and removing a second number of second preset videos with the eligibility being smaller than the preset threshold value;
performing data sampling on the first number of first preset videos to obtain a first number of sampling data;
performing test calculation by using the first quantity of sampling data to design a first color superposition filtering algorithm;
verifying the first color superposition filtering algorithm by using a third number of preset spherical motion track videos, and if all the videos pass the verification, determining the first color superposition filtering algorithm as the preset color superposition filtering algorithm;
if any preset sphere motion track video verification fails, perfecting the first color superposition filtering algorithm to obtain a second color superposition filtering algorithm, and verifying the second color superposition filtering algorithm until the second color superposition filtering algorithm passes the verification;
and determining the second color filtering and overlaying algorithm as the preset color overlaying algorithm.
Preferably, the analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color superposition filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere to obtain a detection result, including:
dividing the motion video into N frames of images;
performing multi-dimensional channel decomposition and mathematical transformation on each frame of image in HSV, YUV and YCBCR color spaces by using the preset color superposition filtering algorithm to obtain a first processing result;
determining scattering coefficients of light in a target environment on the colored sphere at different angles, and optimizing the first processing result according to the scattering coefficients of the light in the target environment on the colored sphere at different angles to obtain a second processing result;
fusing the N second processing results to obtain a target color sphere motion path video corresponding to the motion video;
detecting a color sphere motion path in the target color sphere motion path video to obtain a color sphere motion path drawing graph;
and drawing the color sphere motion path as the detection result to be output.
Preferably, the verifying the detection result, and displaying the detection result after the verification is passed includes:
the method comprises the following steps of collecting motion trail parameters corresponding to the motion of color balls on a target billiard table by utilizing a preset sensing unit, wherein the motion trail parameters comprise: a track amplitude parameter;
verifying the detection result by using the motion trail parameters, and confirming whether the detection result accords with the motion trail parameters, if so, confirming that the detection result passes the verification, otherwise, confirming that the detection result cannot pass the verification;
and displaying the detection result through a preset display unit after the detection result passes the verification.
Preferably, the method further comprises: and determining the initial color of each color ball by using a preset color reduction technology under the complex light and shadow condition.
Preferably, the determining a target pixel used for shooting the color sphere based on the complex light and shadow level and the environmental characteristic parameter includes:
fusing the environmental characteristic parameters by using a self-adaptive weighted average algorithm to obtain a plurality of target characteristic vectors of the environmental characteristic parameters;
constructing a target environment characteristic parameter data set related to the environment characteristic parameters according to the plurality of target characteristic vectors;
carrying out normalization processing on the data in the target environment characteristic parameter data set;
calculating an increment sequence of the shadow distribution sequence of the normalized data;
assigning the increment sequence, and grading the assignment result;
calculating an environment feature level matrix in the target environment according to the divided levels, the assignment result and the probability distribution of the increment sequence;
dividing the shooting pixels into a plurality of grades based on the environment characteristic grade matrix and preset complex light and shadow grade parameters;
corresponding the shooting pixels of multiple grades to the environment characteristic grade matrix and the preset complex light and shadow grade parameters to obtain a pixel reference table;
determining a target environment characteristic grade corresponding to the environment characteristic parameter according to the environment characteristic grade matrix;
and obtaining target pixels corresponding to the target environment characteristic grade and the complex light and shadow grade in the pixel reference table based on the target environment characteristic grade and the complex light and shadow grade.
Preferably, the preprocessing the first video according to the pixel color gray scale variation, the pixel color gray scale offset, and the pixel color gray scale difference value in the target environment to obtain a second video includes:
detecting a first brightness of the target environment under a complex light and shadow condition and a second brightness of the target environment under a non-lighting condition; calculating the light brightness in the first video according to the first brightness and the second brightness:
wherein L is represented as a first light brightness within the first video, L1Expressed as said first luminance, k represents the extinction coefficient within the target environment, d1Expressed as the table length, L, of the target billiard table2Expressed as said second luminance, d2Expressed as the table width of the target billiard table, D is expressed as the focal length when the first video is shot, D1Representing an object distance of a shot product from the target billiard table when the first video is shot;
calculating the target light brightness of the preprocessed first video according to the first light intensity in the first video, the pixel color gray scale variable quantity, the pixel color gray scale offset and the pixel color gray scale difference value in the target environment:
wherein L' represents the brightness of the target light of the processed first video, and W represents the gray scale change of the pixel colorAmount, theta1Expressed as the weight value of the pixel color gray scale variable quantity relative to the first video preprocessing, the value is 0.2, E is expressed as the pixel color gray scale offset, theta2The value of the weighted value of the pixel color gray scale offset to the first video preprocessing is 0.3, Q is the pixel color gray scale difference value, and theta3The weighted value of the pixel color gray scale difference value to the first video preprocessing is expressed, and the value is 0.5; beta is expressed as other interference factors in the target environment and takes the value of [0.05, 0.1%]，
Video quality expressed as said first video, with a value of [0.5, 1%]；
After the target light brightness of the processed first video is determined, preprocessing the first video to obtain a second video, and determining whether the second light brightness in the second video is equal to the target light brightness, if so, determining that the second video is qualified in quality, otherwise, preprocessing the first video again until the second light brightness of the preprocessed second video is equal to the target light brightness.
A system for detecting motion of a colored sphere under complex light and shadow conditions, the system comprising:
the acquisition module is used for acquiring a motion video of the color sphere under the complex light and shadow condition;
the detection module is used for analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color superposition filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere to obtain a detection result;
and the verification module is used for verifying the detection result and displaying the detection result after the verification is passed.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a flowchart illustrating a method for detecting a color sphere under complicated lighting conditions according to the present invention;
FIG. 2 is another flowchart of a method for detecting a color sphere under complicated lighting conditions according to the present invention;
FIG. 3 is a flowchart illustrating a method for detecting a color sphere under complicated lighting conditions according to the present invention;
fig. 4 is a schematic structural diagram of a color sphere motion detection system under a complex light and shadow condition according to the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Along with the improvement of living standard of people, more and more people carry out some recreational activities on weekends or holidays at ordinary times, wherein, billiard sports is popular with people, and can relax the body and mind and enable people to experience the pleasure of sports. However, the ambient light of the billiard hall is relatively complex, so that the situation of complex light and shadow often occurs, and the experience of hitting billiards by players is seriously affected, therefore, in the prior art, video shooting is performed on the motion of the colored ball, and then the motion track of the colored ball is drawn according to the video, but the method has the following defects: because the ambient light is complicated, and the colored ball body refracts light, the precision cannot be guaranteed by simply drawing the motion track of the colored ball body by using a video, so that the finally drawn motion track is different from the actual motion track of the colored ball body, and the experience of hitting billiards by players is greatly influenced. In order to solve the above problem, the present embodiment discloses a method for detecting a motion of a color sphere under a complex light and shadow condition.
A method for detecting motion of a color sphere under a complex light and shadow condition, as shown in fig. 1, includes the following steps:
s101, acquiring a motion video of a color sphere under a complex light and shadow condition;
step S102, analyzing the motion video, and carrying out color sphere motion path detection on the analyzed motion video by using a preset color superposition filtering algorithm and scattering effects of light in a target environment on the color spheres at different angles to obtain a detection result;
and S103, verifying the detection result, and displaying the detection result after the verification is passed.
The working principle of the technical scheme is as follows: the method comprises the steps of obtaining a motion video of a color sphere under a complex light and shadow condition, analyzing the motion video, carrying out color sphere motion path detection on the analyzed motion video by utilizing a preset color superposition filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere, obtaining a detection result, verifying the detection result, and displaying the detection result after the verification is passed.
The beneficial effects of the above technical scheme are: the motion path of the color ball can be accurately analyzed by utilizing the preset color superposition filtering algorithm and the scattering effects of the color ball at different angles in the target environment, the coefficient of the influence of the heat radiation light of the color ball is taken into consideration on the basis of the prior art, and the motion path of the color ball can be more accurately obtained.
In one embodiment, as shown in fig. 2, before obtaining the motion video of the color sphere under the complex light and shadow condition, the method further comprises:
step S201, obtaining target position information of a target billiard table where the colorful ball body is located;
step S202, detecting target light and shadow distribution information on the target billiard table;
step S203, analyzing the environmental characteristic parameters of the target environment of the target billiard table according to the target position information and the target light and shadow distribution information, wherein the environmental characteristic parameters comprise: simulating light and shadow parameters;
step S204, determining the complex light and shadow grade on the target billiard table according to the target light and shadow distribution information on the target billiard table;
and S205, determining a target pixel used for shooting the color sphere based on the complex light and shadow grade and the environment characteristic parameter.
The beneficial effects of the above technical scheme are: the target pixel when the colored sphere moves can be accurately determined according to actual conditions, and then the accuracy of follow-up detection on the moving video can be ensured.
In one embodiment, as shown in fig. 3, acquiring a motion video of a color sphere under a complex light and shadow condition includes:
s301, locking a shooting main body into the target billiard table;
step S302, recording a first video of a color ball on the target billiard table in the motion process by using the target pixel;
step S303, preprocessing the first video according to the pixel color gray scale variable quantity, the pixel color gray scale offset and the pixel color gray scale difference value in the target environment to obtain a second video;
and S304, determining the second video as the motion video of the color sphere under the complex light shadow.
The beneficial effects of the above technical scheme are: the second video is obtained by preprocessing the first video by utilizing the pixel color gray scale variable quantity, the pixel color gray scale offset and the pixel color gray scale difference value in the target environment, so that the actual motion video of the color sphere can be obtained by taking all the influence factors on the motion video of the color sphere in the target environment into consideration, and the authenticity of video data is ensured.
In one embodiment, before analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color overlay filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere, and obtaining a detection result, the method further includes:
acquiring a mass of preset videos, and detecting the qualification of the mass of preset videos;
reserving a first number of first preset videos with the eligibility being larger than or equal to a preset threshold value, and removing a second number of second preset videos with the eligibility being smaller than the preset threshold value;
performing data sampling on the first number of first preset videos to obtain a first number of sampling data;
performing test calculation by using the first quantity of sampling data to design a first color superposition filtering algorithm;
verifying the first color superposition filtering algorithm by using a third number of preset spherical motion track videos, and if all the videos pass the verification, determining the first color superposition filtering algorithm as the preset color superposition filtering algorithm;
if any preset sphere motion track video verification fails, perfecting the first color superposition filtering algorithm to obtain a second color superposition filtering algorithm, and verifying the second color superposition filtering algorithm until the second color superposition filtering algorithm passes the verification;
and determining the second color filtering and overlaying algorithm as the preset color overlaying algorithm.
The beneficial effects of the above technical scheme are: the accuracy of the calculation result of the algorithm can be ensured by verifying the first color superposition filtering algorithm, the accuracy of the evaluation of the motion path of the color sphere is also ensured, and further, the accuracy of the first color filtering algorithm can be further ensured by continuously perfecting the first color superposition filtering algorithm.
In one embodiment, the analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color overlay filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere to obtain a detection result includes:
dividing the motion video into N frames of images;
performing multi-dimensional channel decomposition and mathematical transformation on each frame of image in HSV, YUV and YCBCR color spaces by using the preset color superposition filtering algorithm to obtain a first processing result;
determining scattering coefficients of light in a target environment on the colored sphere at different angles, and optimizing the first processing result according to the scattering coefficients of the light in the target environment on the colored sphere at different angles to obtain a second processing result;
fusing the N second processing results to obtain a target color sphere motion path video corresponding to the motion video;
detecting a color sphere motion path in the target color sphere motion path video to obtain a color sphere motion path drawing graph;
and drawing the color sphere motion path as the detection result to be output.
The beneficial effects of the above technical scheme are: the motion video is divided into N pieces of composition pictures for processing through framing the motion video, the efficiency of processing the pictures is higher and the accuracy is higher compared with the processing of the video, furthermore, multidimensional channel decomposition and mathematical transformation are carried out on each frame of image in HSV, YUV and YCBCR color spaces, so that a plurality of color angles added under complex light and shadow can be guaranteed to be analyzed, the motion path of a color sphere can be determined more accurately, further, the first processing result is optimized through optimizing the scattering coefficient of the color sphere to light as an influence factor to optimize the first processing result again by using the scattering coefficients of different angles of the light of the color sphere in a target environment, the more accurate motion path which accords with the reality is obtained, and the accuracy of data is guaranteed.
In one embodiment, verifying the detection result, and displaying the detection result after the verification is passed includes:
the method comprises the following steps of collecting motion trail parameters corresponding to the motion of color balls on a target billiard table by utilizing a preset sensing unit, wherein the motion trail parameters comprise: a track amplitude parameter;
verifying the detection result by using the motion trail parameters, and confirming whether the detection result accords with the motion trail parameters, if so, confirming that the detection result passes the verification, otherwise, confirming that the detection result cannot pass the verification;
and displaying the detection result through a preset display unit after the detection result passes the verification.
The beneficial effects of the above technical scheme are: the detection result is verified by utilizing the motion trail parameters corresponding to the color ball motion on the target billiard table, so that the detection result can be further ensured to be in accordance with the actual motion trail parameters, and the data practicality is further ensured.
In one embodiment, the method further comprises: and determining the initial color of each color ball by using a preset color reduction technology under the complex light and shadow condition.
The beneficial effects of the above technical scheme are: the respective motion path of each color sphere in the detection result can be accurately determined by determining the initial color of each color sphere, the problem that a certain color sphere is not corresponding to the motion path of the color sphere due to the fact that the path is complicated is avoided, the respective motion path of each color sphere can be distinguished more intuitively, and the experience of a player hitting billiards is further provided.
In one embodiment, the determining a target pixel used for shooting the color sphere based on the complex light and shadow level and the environment characteristic parameter includes:
fusing the environmental characteristic parameters by using a self-adaptive weighted average algorithm to obtain a plurality of target characteristic vectors of the environmental characteristic parameters;
constructing a target environment characteristic parameter data set related to the environment characteristic parameters according to the plurality of target characteristic vectors;
carrying out normalization processing on the data in the target environment characteristic parameter data set;
calculating an increment sequence of the shadow distribution sequence of the normalized data;
assigning the increment sequence, and grading the assignment result;
calculating an environment feature level matrix in the target environment according to the divided levels, the assignment result and the probability distribution of the increment sequence;
dividing the shooting pixels into a plurality of grades based on the environment characteristic grade matrix and preset complex light and shadow grade parameters;
corresponding the shooting pixels of multiple grades to the environment characteristic grade matrix and the preset complex light and shadow grade parameters to obtain a pixel reference table;
determining a target environment characteristic grade corresponding to the environment characteristic parameter according to the environment characteristic grade matrix;
and obtaining target pixels corresponding to the target environment characteristic grade and the complex light and shadow grade in the pixel reference table based on the target environment characteristic grade and the complex light and shadow grade.
The beneficial effects of the above technical scheme are: the environment grade corresponding to the environment characteristic parameters in the target environment is evaluated in a mode of utilizing the environment characteristic grade matrix, the target environment characteristic grade corresponding to the environment characteristic parameters can be quickly and accurately evaluated from the matrix, the whole process does not need manual participation, the influence of human factors on calculation results is avoided, the precision of data is improved, furthermore, the target pixels needed for shooting a first video are determined according to the target environment grade and the complex light and shadow grade, different shooting pixels can be switched according to different environments, the shot video is guaranteed to meet the actual requirement, the practicability is improved, and meanwhile, good data support can be improved for follow-up detection of the motion path of the color sphere.
In one embodiment, the preprocessing the first video according to the pixel color gray scale variation, the pixel color gray scale offset, and the pixel color gray scale difference value in the target environment to obtain a second video includes:
detecting a first brightness of the target environment under a complex light and shadow condition and a second brightness of the target environment under a non-lighting condition;
calculating the light brightness in the first video according to the first brightness and the second brightness:
wherein L is represented as a first light brightness within the first video, L1Expressed as said first luminance, k represents the extinction coefficient within the target environment, d1Expressed as the table length, L, of the target billiard table2Expressed as said second luminance, d2Expressed as the table width of the target billiard table, D is expressed as the focal length when the first video is shot, D1Representing an object distance of a shot product from the target billiard table when the first video is shot;
calculating the target light brightness of the preprocessed first video according to the first light intensity in the first video, the pixel color gray scale variable quantity, the pixel color gray scale offset and the pixel color gray scale difference value in the target environment:
wherein L' represents the brightness of the target light of the processed first video, W represents the gray scale variation of the pixel color, and theta1Expressed as the weight value of the pixel color gray scale variable quantity relative to the first video preprocessing, the value is 0.2, E is expressed as the pixel color gray scale offset, theta2The value of the weighted value of the pixel color gray scale offset to the first video preprocessing is 0.3, Q is the pixel color gray scale difference value, and theta3The weighted value of the pixel color gray scale difference value to the first video preprocessing is expressed, and the value is 0.5; beta is expressed as other interference factors in the target environment and takes the value of [0.05, 0.1%]，
Video quality expressed as said first video, with a value of [0.5, 1%]；
After the target light brightness of the processed first video is determined, preprocessing the first video to obtain a second video, and determining whether the second light brightness in the second video is equal to the target light brightness, if so, determining that the second video is qualified in quality, otherwise, preprocessing the first video again until the second light brightness of the preprocessed second video is equal to the target light brightness.
The beneficial effects of the above technical scheme are: the actual light brightness in the shot first video can be obtained according to the influence of the shot product on the ambient brightness by calculating the first light brightness in the first video, and then a target is provided for the follow-up pretreatment of the first video.
This embodiment also discloses a color sphere motion detection system under the condition of complicated light and shadow, as shown in fig. 4, the system includes:
the acquiring module 401 is configured to acquire a motion video of a color sphere under a complex light and shadow condition;
the detection module 402 is configured to analyze the motion video, perform color sphere motion path detection on the analyzed motion video by using a preset color overlay filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere, and acquire a detection result;
and the verification module 403 is configured to verify the detection result, and display the detection result after the verification is passed.
The working principle and the advantageous effects of the above technical solution have been explained in the method claims, and are not described herein again.
It will be understood by those skilled in the art that the first and second terms of the present invention refer to different stages of application.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A color sphere motion detection method under a complex light and shadow condition is characterized by comprising the following steps:
acquiring a motion video of the color sphere under a complex light and shadow condition;
analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color superposition filtering algorithm and scattering effects of light in a target environment on the color sphere at different angles to obtain a detection result;
and verifying the detection result, and displaying the detection result after the verification is passed.
2. The method for detecting motion of a color sphere under a complex light and shadow condition as claimed in claim 1, wherein before obtaining the motion video of the color sphere under the complex light and shadow condition, the method further comprises:
acquiring target position information of a target billiard table where the colorful ball is located;
detecting target light and shadow distribution information on the target billiard table;
analyzing the environmental characteristic parameters of the target environment of the target billiard table according to the target position information and the target light and shadow distribution information, wherein the environmental characteristic parameters comprise: simulating light and shadow parameters;
determining the complex light and shadow grade on the target billiard table according to the target light and shadow distribution information on the target billiard table;
and determining a target pixel used for shooting the color sphere based on the complex light and shadow grade and the environment characteristic parameters.
3. The method for detecting the motion of the color sphere under the complex light and shadow condition as claimed in claim 2, wherein the obtaining of the motion video of the color sphere under the complex light and shadow condition comprises:
locking the shooting main body as the target billiard table;
recording a first video of a color ball on the target billiard table in the moving process by using the target pixel;
preprocessing the first video according to the pixel color gray scale variable quantity, the pixel color gray scale offset and the pixel color gray scale difference value in the target environment to obtain a second video;
and determining the second video as the motion video of the color sphere under the complex light shadow.
4. The method for detecting motion of a color sphere under a complex light and shadow condition as claimed in claim 1, wherein before analyzing the motion video, performing color sphere motion path detection on the analyzed motion video by using a preset color overlay filtering algorithm and scattering effects of light in a target environment on the color sphere at different angles, and obtaining a detection result, the method further comprises:
acquiring a mass of preset videos, and detecting the qualification of the mass of preset videos;
reserving a first number of first preset videos with the eligibility being larger than or equal to a preset threshold value, and removing a second number of second preset videos with the eligibility being smaller than the preset threshold value;
performing data sampling on the first number of first preset videos to obtain a first number of sampling data;
performing test calculation by using the first quantity of sampling data to design a first color superposition filtering algorithm;
verifying the first color superposition filtering algorithm by using a third number of preset spherical motion track videos, and if all the videos pass the verification, determining the first color superposition filtering algorithm as the preset color superposition filtering algorithm;
if any preset sphere motion track video verification fails, perfecting the first color superposition filtering algorithm to obtain a second color superposition filtering algorithm, and verifying the second color superposition filtering algorithm until the second color superposition filtering algorithm passes the verification;
and determining the second color filtering and overlaying algorithm as the preset color overlaying algorithm.
5. The method according to claim 1, wherein the analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color overlay filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere to obtain a detection result comprises:
dividing the motion video into N frames of images;
performing multi-dimensional channel decomposition and mathematical transformation on each frame of image in HSV, YUV and YCBCR color spaces by using the preset color superposition filtering algorithm to obtain a first processing result;
determining scattering coefficients of light in a target environment on the colored sphere at different angles, and optimizing the first processing result according to the scattering coefficients of the light in the target environment on the colored sphere at different angles to obtain a second processing result;
fusing the N second processing results to obtain a target color sphere motion path video corresponding to the motion video;
detecting a color sphere motion path in the target color sphere motion path video to obtain a color sphere motion path drawing graph;
and drawing the color sphere motion path as the detection result to be output.
6. The method for detecting the movement of the color sphere under the complex light and shadow condition as claimed in claim 2, wherein the step of verifying the detection result and displaying the detection result after the verification is passed comprises:
the method comprises the following steps of collecting motion trail parameters corresponding to the motion of color balls on a target billiard table by utilizing a preset sensing unit, wherein the motion trail parameters comprise: a track amplitude parameter;
verifying the detection result by using the motion trail parameters, and confirming whether the detection result accords with the motion trail parameters, if so, confirming that the detection result passes the verification, otherwise, confirming that the detection result cannot pass the verification;
and displaying the detection result through a preset display unit after the detection result passes the verification.
7. The method for detecting motion of a color sphere under a complex light and shadow condition of claim 1, further comprising: and determining the initial color of each color ball by using a preset color reduction technology under the complex light and shadow condition.
8. The method for detecting motion of a color sphere under a complex light and shadow condition according to claim 2, wherein the determining a target pixel used for capturing the color sphere based on the complex light and shadow level and the environment characteristic parameters comprises:
fusing the environmental characteristic parameters by using a self-adaptive weighted average algorithm to obtain a plurality of target characteristic vectors of the environmental characteristic parameters;
constructing a target environment characteristic parameter data set related to the environment characteristic parameters according to the plurality of target characteristic vectors;
carrying out normalization processing on the data in the target environment characteristic parameter data set;
calculating an increment sequence of the shadow distribution sequence of the normalized data;
assigning the increment sequence, and grading the assignment result;
calculating an environment feature level matrix in the target environment according to the divided levels, the assignment result and the probability distribution of the increment sequence;
dividing the shooting pixels into a plurality of grades based on the environment characteristic grade matrix and preset complex light and shadow grade parameters;
corresponding the shooting pixels of multiple grades to the environment characteristic grade matrix and the preset complex light and shadow grade parameters to obtain a pixel reference table;
determining a target environment characteristic grade corresponding to the environment characteristic parameter according to the environment characteristic grade matrix;
and obtaining target pixels corresponding to the target environment characteristic grade and the complex light and shadow grade in the pixel reference table based on the target environment characteristic grade and the complex light and shadow grade.
9. The method of claim 3, wherein the preprocessing the first video according to the pixel color gray scale variation, the pixel color gray scale offset, and the pixel color gray scale difference in the target environment to obtain a second video comprises:
detecting a first brightness of the target environment under a complex light and shadow condition and a second brightness of the target environment under a non-lighting condition;
calculating the light brightness in the first video according to the first brightness and the second brightness:
wherein L is represented as a first light brightness within the first video, L1Expressed as said first luminance, k represents the extinction coefficient within the target environment, d1Expressed as the table length, L, of the target billiard table2Expressed as said second luminance, d2Expressed as the table width of the target billiard table, D is expressed as the focal length when the first video is shot, D1Representing an object distance of a shot product from the target billiard table when the first video is shot;
calculating the target light brightness of the preprocessed first video according to the first light intensity in the first video, the pixel color gray scale variable quantity, the pixel color gray scale offset and the pixel color gray scale difference value in the target environment:
wherein L' represents the brightness of the target light of the processed first video, W represents the gray scale variation of the pixel color, and theta1Expressed as the weight value of the pixel color gray scale variable quantity relative to the first video preprocessing, the value is 0.2, E is expressed as the pixel color gray scale offset, theta2The value of the weighted value of the pixel color gray scale offset to the first video preprocessing is 0.3, Q is the pixel color gray scale difference value, and theta3Representing as pixel color gray level difference values for a first videoProcessing the occupied weight value to be 0.5; beta is expressed as other interference factors in the target environment and takes the value of [0.05, 0.1%]，
Video quality expressed as said first video, with a value of [0.5, 1%]；
After the target light brightness of the processed first video is determined, preprocessing the first video to obtain a second video, and determining whether the second light brightness in the second video is equal to the target light brightness, if so, determining that the second video is qualified in quality, otherwise, preprocessing the first video again until the second light brightness of the preprocessed second video is equal to the target light brightness.
10. A system for detecting motion of a color sphere under complex light and shadow conditions, the system comprising:
the acquisition module is used for acquiring a motion video of the color sphere under the complex light and shadow condition;
the detection module is used for analyzing the motion video, and performing color sphere motion path detection on the analyzed motion video by using a preset color superposition filtering algorithm and scattering effects of light in a target environment at different angles on the color sphere to obtain a detection result;
and the verification module is used for verifying the detection result and displaying the detection result after the verification is passed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011497227.3A CN112686926B (en) | 2020-12-17 | 2020-12-17 | Method and system for detecting motion of colored sphere under complex light and shadow conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011497227.3A CN112686926B (en) | 2020-12-17 | 2020-12-17 | Method and system for detecting motion of colored sphere under complex light and shadow conditions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112686926A true CN112686926A (en) | 2021-04-20 |
| CN112686926B CN112686926B (en) | 2022-05-31 |
Family
ID=75448730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011497227.3A Active CN112686926B (en) | 2020-12-17 | 2020-12-17 | Method and system for detecting motion of colored sphere under complex light and shadow conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686926B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030085523A1 (en) * | 2001-08-02 | 2003-05-08 | Spaulding Glenn F. | Novel paintball velocimeter and closed-loop regulation |
| US20040132535A1 (en) * | 2003-01-07 | 2004-07-08 | Sumko Michael H. | Laser billiard ball positioning apparatus |
| CN103871078A (en) * | 2013-07-12 | 2014-06-18 | 北京瑞盖科技有限公司 | Billiard ball hitting key information detection method and system |
| CN104954750A (en) * | 2015-06-18 | 2015-09-30 | 北京共创普惠科技有限公司 | Data processing method and device for billiard system |
| US9256957B1 (en) * | 2012-09-13 | 2016-02-09 | Bae Systems Information And Electronic Systems Integration Inc. | Method for moving-object detection tracking identification cueing of videos |
| US20160045786A1 (en) * | 2011-05-11 | 2016-02-18 | Karsten Manufacturing Corporation | Systems, methods, and articles of manufacture to measure, analyze and share golf swing and ball motion characteristics |
| CN110006921A (en) * | 2019-01-25 | 2019-07-12 | 杭州晶耐科光电技术有限公司 | A kind of larger radius of curvature spherical optics element automation pose method of adjustment and device |
| CN111602172A (en) * | 2017-08-04 | 2020-08-28 | 文塔纳医疗系统公司 | Color unmixing with scatter correction |
-
2020
- 2020-12-17 CN CN202011497227.3A patent/CN112686926B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030085523A1 (en) * | 2001-08-02 | 2003-05-08 | Spaulding Glenn F. | Novel paintball velocimeter and closed-loop regulation |
| US20040132535A1 (en) * | 2003-01-07 | 2004-07-08 | Sumko Michael H. | Laser billiard ball positioning apparatus |
| US20160045786A1 (en) * | 2011-05-11 | 2016-02-18 | Karsten Manufacturing Corporation | Systems, methods, and articles of manufacture to measure, analyze and share golf swing and ball motion characteristics |
| US9256957B1 (en) * | 2012-09-13 | 2016-02-09 | Bae Systems Information And Electronic Systems Integration Inc. | Method for moving-object detection tracking identification cueing of videos |
| CN103871078A (en) * | 2013-07-12 | 2014-06-18 | 北京瑞盖科技有限公司 | Billiard ball hitting key information detection method and system |
| CN104954750A (en) * | 2015-06-18 | 2015-09-30 | 北京共创普惠科技有限公司 | Data processing method and device for billiard system |
| CN111602172A (en) * | 2017-08-04 | 2020-08-28 | 文塔纳医疗系统公司 | Color unmixing with scatter correction |
| CN110006921A (en) * | 2019-01-25 | 2019-07-12 | 杭州晶耐科光电技术有限公司 | A kind of larger radius of curvature spherical optics element automation pose method of adjustment and device |
Non-Patent Citations (2)
| Title |
|---|
| 丁莹等: "基于不同颜色空间的运动目标检测算法分析", 《长春理工大学学报(自然科学版)》 * |
| 丁莹等: "基于不同颜色空间的运动目标检测算法分析", 《长春理工大学学报(自然科学版)》, vol. 35, no. 04, 15 December 2012 (2012-12-15), pages 1 - 4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112686926B (en) | 2022-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110490914B (en) | Image fusion method based on brightness self-adaption and significance detection | |
| CN109903312A (en) | A kind of football sportsman based on video multi-target tracking runs distance statistics method | |
| CN108492262B (en) | No-ghost high-dynamic-range imaging method based on gradient structure similarity | |
| US10515471B2 (en) | Apparatus and method for generating best-view image centered on object of interest in multiple camera images | |
| CN111079740A (en) | Image quality evaluation method, electronic device, and computer-readable storage medium | |
| CN103198467B (en) | Image processing apparatus and image processing method | |
| CN110675328A (en) | Low-illumination image enhancement method and device based on condition generation countermeasure network | |
| CN108074234A (en) | A kind of large space flame detecting method based on target following and multiple features fusion | |
| CN110738160A (en) | human face quality evaluation method combining with human face detection | |
| CN110458964B (en) | Real-time calculation method for dynamic illumination of real environment | |
| Pan et al. | No-reference assessment on haze for remote-sensing images | |
| CN108564057B (en) | Method for establishing person similarity system based on opencv | |
| CN110910365A (en) | Quality evaluation method for multi-exposure fusion image of dynamic scene and static scene simultaneously | |
| CN113344843B (en) | Image quality evaluation method, device and system | |
| CN112686926B (en) | Method and system for detecting motion of colored sphere under complex light and shadow conditions | |
| CN114067172A (en) | Simulation image generation method, simulation image generation device and electronic equipment | |
| CN102148919B (en) | Method and system for detecting balls | |
| CN107194954B (en) | Player tracking method and device of multi-view video | |
| CN112508998A (en) | Visual target alignment method based on global motion | |
| CN109658405B (en) | Image data quality control method and system in crop live-action observation | |
| CN110602411A (en) | Method for improving quality of face image in backlight environment | |
| Huda et al. | Effects of pre-processing on the performance of transfer learning based person detection in thermal images | |
| CN112818950B (en) | Lip language identification method based on generation of countermeasure network and time convolution network | |
| CN114463664A (en) | Novel ice hockey tracking method for ice hockey sports | |
| CN109977819B (en) | Weak supervision single action positioning method applying template matching method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |