CN113286077A - Full-automatic camera tracking and identifying technology - Google Patents

Full-automatic camera tracking and identifying technology Download PDF

Info

Publication number
CN113286077A
CN113286077A CN202110419310.7A CN202110419310A CN113286077A CN 113286077 A CN113286077 A CN 113286077A CN 202110419310 A CN202110419310 A CN 202110419310A CN 113286077 A CN113286077 A CN 113286077A
Authority
CN
China
Prior art keywords
tracking
camera
actual
image
color
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
Application number
CN202110419310.7A
Other languages
Chinese (zh)
Inventor
鄢梦林
鄢承志
阮国梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ruitai Imaging Technology Shenzhen Co ltd
Original Assignee
Ruitai Imaging Technology Shenzhen Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ruitai Imaging Technology Shenzhen Co ltd filed Critical Ruitai Imaging Technology Shenzhen Co ltd
Priority to CN202110419310.7A priority Critical patent/CN113286077A/en
Publication of CN113286077A publication Critical patent/CN113286077A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules
    • H04N23/695Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/80Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Studio Devices (AREA)

Abstract

The invention relates to the technical field of camera identification, in particular to a full-automatic camera tracking identification technology, which comprises the following steps that a camera tracks colors, distances and shapes, wherein the following steps of tracking the colors comprise the steps of identifying and judging hue H, saturation S and brightness L of color values, automatically identifying specific colors, calculating the size of a pixel occupied by a color area, and calculating the actual size corresponding to the size of the current pixel, the central point of the current color and the difference value of the actual distances between the current pixel and the central point of an image in the X direction and the Y direction through calibration parameters. The invention achieves the purposes of accurate imaging and accurate tracking in a simple and convenient way. The tracking of color, size, distance and shape is carried out by combining with an excellent color recognition algorithm, the effect of basically no error (the error is less than 1mm) can be realized, more functions can be realized by adjusting related parameters, and great demands are placed on life and industry.

Description

Full-automatic camera tracking and identifying technology
Technical Field
The invention relates to the technical field of image identification, tracking and identification, in particular to a full-automatic camera tracking and identification technology.
Background
Aiming at the increasing demand of the X-ray protective screen on the market at present and the continuous development of the technology at present, people pursue simpler life and simpler mechanical structure. In order to save energy and make the equipment more convenient, the protective equipment of the type in a seeing hospital and the like has a large amount of messy cable interleaving, the detection equipment and the control end transmit information through a large amount of cables, and a special computer is required to be configured, so that the maintenance of the equipment and the action of technicians and patients are not convenient. The related technologies used for related devices in the market at present include infrared/laser correlation sensors, laser distance sensors, stay wire sensors (similar to encoder forms) and the like, and the technologies can only realize up-and-down following, and meanwhile, the physical connection of cables is required between the devices and a flat panel detector of the conventional DR device, and the required number and size of the cables are different according to different sensors; and the existing type equipment can not realize the adjustment of the projection visual field size, and has single function.
Therefore, a camera tracking and recognizing method capable of quickly tracking a target and automatically performing accurate and clear imaging on the size, color, distance and shape is needed.
Disclosure of Invention
In view of the above, the present invention provides a fully automatic camera tracking and recognizing technology to solve the problems in the background art.
The full-automatic camera tracking and identifying technology comprises the following steps that a camera tracks colors, sizes, distances and shapes, the tracking of the colors comprises the steps of identifying and judging hue H, saturation S and brightness L of color values, automatically identifying specific colors, calculating the size of a pixel occupied by a color area, and calculating the actual size corresponding to the size of the current pixel, the central point of the current color and the difference value of the actual distances between the current pixel and the central point of an image in the X direction and the Y direction through calibration parameters.
Further, the tracking of the color and the distance firstly calibrates an imaging area of the camera when the camera leaves a factory, and a calibrated linear equation can be obtained according to the linear equation in two points, wherein the calibrated linear equation is shown as a formula (1);
(S-S1)/(S2-S1) ═ X-X1)/(X2-X1) (1)
Wherein S represents the actual distance, and X represents the number of identified pixels;
automatically acquiring a pixel value Xn at any position in a tracked image visual area, calculating the actual distance from the Xn to a tracked color code in front by a linear equation, wherein the actual size represented by each pixel point is RX/Xn as the actual value in the X direction of the color code, and then identifying the imaging area below the visual area to calculate the actual size of the current area.
Further, when the pixel value is obtained, the image is subjected to binarization processing, after binarization is performed through a threshold value, the threshold value is converted through RGB (red, green and blue) three primary colors, and the number of effective pixels and the size of an area are counted.
Further, tracking the distance, where the size of the tracked color scale is fixed in all products at the time of factory shipment, for example, the pixel value in the image is Xn, and the actual distance obtained according to equation (2) is:
sn ═ ((Xn-X1) × (S2-S1)/(X2-X1)) -S1) formula (2).
Further, for the tracking of the shape, firstly, the shape of the tracked target is set, the shape of the tracked target is factory-set to be a specific shape in a unified mode, and a shape recognition tracking mode is customized according to the specific shape.
Further, the tracked image target center coincides with the view center of the camera, that is, it indicates that the tracking is finished, and since there may be a problem that the camera center is not on the same horizontal line with the target position center for the physical position of the camera, the tracked image target center does not coincide with the view center of the actual position when the tracking is finished, which causes deviation, the deviation is corrected by the formula (3), as shown in the formula (3);
SX-X, SY-Y type (3)
Wherein SX is the actual deviation in the X direction, and SY is the actual deviation in the Y direction.
The full-automatic camera tracking device comprises a high-definition camera, wherein the camera comprises an image control processor, and the camera is used for acquiring images in a visual field in real time and transmitting the images to the image control processor to identify image contents, so that the full-automatic camera tracking device executes any one of the above full-automatic camera tracking identification technologies. The camera is used for collecting images, image recognition and operation are carried out through the processor, the current equipment position height and the target position height difference are calculated, meanwhile, the light field visual field size is also calculated, the relevant result is transmitted to the relevant movement mechanism, and up-down following and light field visual field size adjustment are achieved.
The full-automatic camera tracking identification technology has the beneficial effects that: the invention achieves the purposes of accurate imaging and accurate tracking in a simple and convenient way. The tracking of color, size, distance and shape is carried out by combining with an excellent color recognition algorithm, the effect of basically no error (the error is less than 1mm) can be realized, more functions can be realized by adjusting related parameters, and great demands are placed on life and industry. The invention can also carry out self calibration, and can basically eliminate the distance deviation between the camera and the target by adjusting the X, Y coordinate, so that the invention becomes more intelligent and innovative, fills in the gap which can not be automatically adjusted by the machine in the market at present, and improves the practicability of the invention greatly. The camera full automation has been realized, single with a camera alright in order to realize snatching, the formation of image to the pursuit of the arbitrary colour of target, size, distance, shape, the unable problem of carrying out automatically regulated to the field of vision size of realization type equipment on the market. Realize full automatically regulated light field size and follow from top to bottom automatically, compare with equipment of the same type, realized need not the wiring, just usable equipment. Meanwhile, the device is not limited by cable connection when moving (in the actual use process, the device moving requirement exists). And the workload of the technician can be greatly reduced, and the operation of the technician can be simplified.
Drawings
FIG. 1 is a schematic diagram of the calibration structure of the present invention;
FIG. 2 is a schematic diagram of the present invention for performing binarization processing on an image;
FIG. 3 is a schematic diagram of the automatic compensation configuration of the present invention;
FIG. 4 is a schematic view of the position of the camera of the present invention on the device when in use;
Detailed Description
The present invention will be described in detail with reference to the drawings and specific embodiments, and it is to be understood that the described embodiments are only a few embodiments of the present application, and not all embodiments, and all other embodiments obtained by those skilled in the art without any inventive step based on the embodiments in the present application are within the scope of the present application.
In this embodiment, the full-automatic camera tracking and identifying technology of the present invention includes tracking colors, distances, and shapes by a camera, where tracking colors includes identifying and judging hue H, saturation S, and brightness L of a color value, automatically identifying a specified color, calculating a pixel size occupied by the color area, and calculating an actual size corresponding to a current pixel size, a center point of the current color, and a difference between actual distances in an X direction and an actual distance in a Y direction from the center point of an image by using calibration parameters.
In this embodiment, the tracking of the color and the distance is performed by calibrating an imaging area of the camera when the camera leaves a factory, as shown in fig. 1, heights of two longitudinal graphs are L1 and L2, respectively, it is assumed that a measured value of S2 is 80cm, a value of S1 is 100cm, pixel points are 8pix and 10pix, respectively, and if a pixel mapped by a target is 9pix, the position of the pixel can be determined to be 90 cm.
Calibrating the outgoing camera, as shown in fig. 1, in order to realize the function of automatically calculating the distance, therefore, when setting parameters, calibration is required at the time of production to indicate an actual conversion coefficient, wherein calibration of two different distances is required to be performed on a color scale (which can be any color, and is preferably larger in color difference with the current color) of the same size, actual positions of the two distances and actual size of a target color scale are recorded, and a calibration linear equation as formula (1) can be obtained according to a linear equation in two points;
(S-S1)/(S2-S1) ═ X-X1)/(X2-X1) (1)
Wherein S represents the actual distance, and X represents the number of identified pixels;
automatically acquiring a pixel value Xn at any position in a tracked image visual area, calculating the actual distance from the Xn to a tracked color code in front by a linear equation, wherein the actual size represented by each pixel point is RX/Xn as the actual value in the X direction of the color code, and then identifying the imaging area below the visual area to calculate the actual size of the current area.
In this embodiment, when a pixel value is obtained, an image is binarized through a threshold value, and then the threshold value is converted through RGB three primary colors, so as to obtain the number of effective pixels and the size of an area. As shown in fig. 3:
the grabbing process comprises the steps of illuminating the view field when a tracked target lamp is turned on, enabling the window part to be a high-brightness area, enabling the part to have an obvious brightness difference with other parts, comparing the brightness difference with a threshold value through RGB three-primary-color contrast difference, enabling the white color of the threshold value to be set and the black color to be set to be not set, recording statistics of the target area, and finally calculating the size of the final area, wherein the white area in the graph 2 is the target area.
In this embodiment, for tracking of the distance, the actual size of the tracked color scale is fixed in the factory in all products, for example, the pixel value in the image is Xn, and the actual distance obtained according to equation (2) is:
sn ═ ((Xn-X1) × (S2-S1)/(X2-X1)) -S1) formula (2).
In the embodiment, for the shape tracking, the shape of the tracked object is firstly set, the shape of the tracked object is set to be a uniform shape when the tracked object is shipped, a shape recognition and tracking mode can be customized according to specific requirements, and the tracked shape can be set by a user.
In this embodiment, as shown in fig. 3-4, the tracked image target center coincides with the view center of the camera, that is, it indicates that the tracking is completed, and since there may be a problem that the camera center and the target position center are not on the same horizontal line with respect to the physical position of the camera, the tracked image target center does not coincide with the view center of the actual position when the tracking is completed, which causes a deviation, the deviation is corrected by the formula (3), as shown in the formula (3);
SX-X, SY-Y type (3)
A schematic diagram of the position of the camera on the device when in use is shown, wherein S1 and S2 are divided into a center point of the camera and a center point of the device, X represents the actual physical deviation of the two center points, and Y represents the actual physical deviation value of the two center points in the Y direction. The algorithm of the camera tracking is based on that the center of an image target is coincided with the center of a visual field, namely the tracking is finished. However, when the camera is actually physically installed, the camera is not located at the center of the device, so that after alignment, the actual position is shifted downward by a distance Y, and the X direction is also shifted by a distance X. Therefore, a compensation value is needed at this time to realize the deviation caused by the physical position, and the deviation in the XY direction is compensated back to adjust the center of the device and the target center to be on a horizontal line.
Wherein SX is the actual deviation in the X direction, and SY is the actual deviation in the Y direction. As shown in fig. 3, if the relative actual position deviations SX (X-direction actual deviation) and SY (Y-direction actual deviation) of the target center captured by the camera and the physical center of the camera are simply output, the above-mentioned problem that the two centers cannot be aligned is caused, so that at this time, the value X in fig. 3 is automatically subtracted from SX at the time of result output, and the output result is SX ═ SX-X and SY ═ SY-Y. Therefore, the problem of inaccurate adjustment position caused by the fact that the camera is not in the same horizontal line with the actual center point when the camera is installed can be solved.
In this embodiment, the tracking device includes a high-definition camera, where the camera includes an image control processor, and the camera is configured to acquire an image in a field of view in real time, and transmit the image to the image control processor to identify image content, so that the full-automatic camera tracking device executes any one of the above-described full-automatic camera tracking identification techniques. The camera is used for collecting images, image recognition and operation are carried out through the processor, the current equipment position height and the target position height difference are calculated, meanwhile, the light field view field size is also calculated, the relevant result is transmitted to the relevant motion mechanism, and up-down following and light field view field size adjustment are achieved.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention as defined in the appended claims. The techniques, shapes, and configurations not described in detail in the present invention are all known techniques.

Claims (7)

1. Full-automatic camera tracking and identifying technology, its characterized in that: the method comprises the following steps of tracking colors, distances and shapes, wherein the tracking of the colors comprises the steps of identifying and judging hue H, saturation S and brightness L of color values, automatically identifying specific colors, calculating the size and the position of a pixel occupied by a color area, and calculating the actual size corresponding to the size of the current pixel, the central point of the current color and the difference value of the actual distances in the X direction and the Y direction of the central point of an image through calibration parameters.
2. The full-automatic camera tracking identification technology according to claim 1, wherein for tracking distance, an imaging area of the camera is calibrated at the time of delivery of the camera, and the calibrated linear equation is obtained in a two-point manner according to the linear equation as shown in formula (1);
(S-S1)/(S2-S1) ═ X-X1)/(X2-X1) (1)
Wherein S represents the actual distance, and X represents the number of identified pixels;
automatically acquiring a pixel value Xn at any position in a tracked image visual area, calculating the actual distance from the Xn to a tracked color code in front by a linear equation, wherein the actual size represented by each pixel point is RX/Xn as the actual value in the X direction of the color code, and then identifying the imaging area below the visual area to calculate the actual size of the current area.
3. The full-automatic camera tracking identification technology of claim 2, wherein when the pixel value is obtained, the image is binarized, after binarization is performed through a threshold value, the threshold value is converted through RGB (red, green and blue) three primary colors, and the number of effective pixels and the position and size of the image where the pixel points are located are counted.
4. The fully automatic camera tracking and recognizing technology according to claim 1, wherein the tracking of the distance, in the tracked color scale, the actual size of which is fixed in all products when the product leaves the factory, for example, the pixel value in the image is Xn, and the actual distance obtained according to equation (2) is:
sn ═ ((Xn-X1) × (S2-S1)/(X2-X1)) -S1) formula (2).
5. The fully automatic camera tracking and recognizing technology as claimed in claim 1, wherein for tracking the shape, the shape of the tracked object is firstly set, the shape of the tracked object is set to be a uniform shape at the time of factory shipment, the shape recognition and tracking method can be customized according to specific requirements, and the tracked shape can be set by the user himself/herself afterwards.
6. The fully automatic camera tracking identification technique of claim 1, wherein the tracked image target center coincides with the camera's field of view center, indicating that the tracking is complete. The problem that the center of the camera is not on the same horizontal line with the center of the target position possibly exists in the installation physical position of the camera, so that the center of the tracked image target is not coincident with the center of the visual field of the actual position when tracking is finished, and deviation is caused, and deviation correction is performed through a formula (3), namely the formula (3);
SX-X, SY-Y type (3)
Wherein SX is the actual deviation in the X direction, and SY is the actual deviation in the Y direction.
7. A full-automatic camera tracking device is characterized by comprising a high-definition camera, wherein the camera comprises an image control processor, and the camera is used for acquiring images in a field of view in real time and transmitting the images to the image control processor to identify image contents, so that the full-automatic camera tracking device executes the full-automatic camera tracking identification technology of any one of claims 1 to 6.
CN202110419310.7A 2021-04-19 2021-04-19 Full-automatic camera tracking and identifying technology Pending CN113286077A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110419310.7A CN113286077A (en) 2021-04-19 2021-04-19 Full-automatic camera tracking and identifying technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110419310.7A CN113286077A (en) 2021-04-19 2021-04-19 Full-automatic camera tracking and identifying technology

Publications (1)

Publication Number Publication Date
CN113286077A true CN113286077A (en) 2021-08-20

Family

ID=77276818

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110419310.7A Pending CN113286077A (en) 2021-04-19 2021-04-19 Full-automatic camera tracking and identifying technology

Country Status (1)

Country Link
CN (1) CN113286077A (en)

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090027502A1 (en) * 2006-02-24 2009-01-29 Ktf Technologies, Inc. Portable Apparatuses Having Devices for Tracking Object's Head, and Methods of Tracking Object's Head in Portable Apparatus
CN101986691A (en) * 2009-07-28 2011-03-16 佳能株式会社 Image processing apparatus and image processing method
CN102447832A (en) * 2010-08-18 2012-05-09 佳能株式会社 Tracking apparatus and tracking method
CN103537099A (en) * 2012-07-09 2014-01-29 深圳泰山在线科技有限公司 Tracking toy
CN106502272A (en) * 2016-10-21 2017-03-15 上海未来伙伴机器人有限公司 A kind of target following control method and device
CN107291104A (en) * 2014-07-30 2017-10-24 深圳市大疆创新科技有限公司 Target tracking system and method
CN108875683A (en) * 2018-06-30 2018-11-23 北京宙心科技有限公司 Robot vision tracking method and system
CN109816700A (en) * 2019-01-11 2019-05-28 佰路得信息技术(上海)有限公司 A kind of information statistical method based on target identification
CN111275739A (en) * 2020-01-19 2020-06-12 广东工业大学 Automatic tracking device and method
CN111709968A (en) * 2020-05-08 2020-09-25 中国人民解放军空军工程大学 Low-altitude target detection tracking method based on image processing
CN111880575A (en) * 2020-08-10 2020-11-03 重庆依塔大数据研究院有限公司 Control method and device based on color tracking, storage medium and robot
CN112634356A (en) * 2020-12-30 2021-04-09 欧普照明股份有限公司 Tracking method and system and electronic equipment

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090027502A1 (en) * 2006-02-24 2009-01-29 Ktf Technologies, Inc. Portable Apparatuses Having Devices for Tracking Object's Head, and Methods of Tracking Object's Head in Portable Apparatus
CN101986691A (en) * 2009-07-28 2011-03-16 佳能株式会社 Image processing apparatus and image processing method
CN102447832A (en) * 2010-08-18 2012-05-09 佳能株式会社 Tracking apparatus and tracking method
CN103537099A (en) * 2012-07-09 2014-01-29 深圳泰山在线科技有限公司 Tracking toy
CN107291104A (en) * 2014-07-30 2017-10-24 深圳市大疆创新科技有限公司 Target tracking system and method
CN106502272A (en) * 2016-10-21 2017-03-15 上海未来伙伴机器人有限公司 A kind of target following control method and device
CN108875683A (en) * 2018-06-30 2018-11-23 北京宙心科技有限公司 Robot vision tracking method and system
CN109816700A (en) * 2019-01-11 2019-05-28 佰路得信息技术(上海)有限公司 A kind of information statistical method based on target identification
CN111275739A (en) * 2020-01-19 2020-06-12 广东工业大学 Automatic tracking device and method
CN111709968A (en) * 2020-05-08 2020-09-25 中国人民解放军空军工程大学 Low-altitude target detection tracking method based on image processing
CN111880575A (en) * 2020-08-10 2020-11-03 重庆依塔大数据研究院有限公司 Control method and device based on color tracking, storage medium and robot
CN112634356A (en) * 2020-12-30 2021-04-09 欧普照明股份有限公司 Tracking method and system and electronic equipment

Similar Documents

Publication Publication Date Title
CN107507571B (en) A kind of couple of AMOLED carries out the method and device of external optical compensation
CN108918542B (en) Optical cable surface defect detection device and method
EP2200329B1 (en) Method and apparatus for automatic object detection through illuminant compensation in video signals
US6018361A (en) Apparatus for and method of measuring image qualities of color display unit
WO1998039627A2 (en) Calibration of imaging systems
CN110202576A (en) A kind of workpiece two-dimensional visual guidance crawl detection system and method
KR100939079B1 (en) System for mesurement of the snowfall and method for mesurement of the snowfall
CN107024476A (en) Display panel detecting system and its detection means and detection method
CN113686260B (en) Large-span beam deflection monitoring method and system
CN208459716U (en) A kind of liquid crystal display detection device
CN111261079A (en) Detection method for abnormal phenomena of bright spots and dark spots
CN109596054A (en) The size detection recognition methods of strip workpiece
CN111476785B (en) Night infrared light-reflecting water gauge detection method based on position recording
AU2017218753B2 (en) Imaging device with white balance compensation and related systems and methods
CN113286077A (en) Full-automatic camera tracking and identifying technology
CN204834000U (en) Photochromic homogeneity correcting unit of LED display screen
CN109631763A (en) Irregular part detects localization method
CN106652898B (en) LED shows pointwise correction method
CN106546196B (en) A kind of optical axis real-time calibration method and system
CN112213320A (en) Biscuit detection device and biscuit detection method based on machine vision
US5267038A (en) Synthetic aperture video photometer system
CN115776560B (en) Image stitching and repairing processing system and method based on naked eye 3D technology
CN115876086A (en) Detection method and detection system of high-density connector
CN109632814A (en) Part defect detection method
CN116156127A (en) Image matching system and 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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210820