CN111986312A - A ship trajectory drawing method, terminal device and storage medium - Google Patents

Abstract

The present invention relates to a ship trajectory drawing method, a terminal device and a storage medium. The method includes: S1: photographing an object with known coordinates through a camera; S2: pairing the two-dimensional image with the known coordinates of the object The camera device is calibrated; S3: the ship image in a continuous time is collected by the calibrated camera device, and after the ship image is filtered by the nonlinear gradient domain guided filtering algorithm, feature extraction is performed on the ship features in each ship image; S4: Convert the two-dimensional coordinates of the ship features in the image to the three-dimensional coordinates in the world coordinate system according to the extracted ship features and the calibration data of the camera device; S5: According to the three-dimensional coordinates corresponding to the ship features in each ship image in continuous time The coordinates are displayed on the chart and connected to form the ship's trajectory. The invention realizes the display of the longitude and latitude of the monitoring ship on the chart.

Description

A ship trajectory drawing method, terminal device and storage medium

technical field

The invention relates to the field of trajectory drawing, in particular to a ship trajectory drawing method, a terminal device and a storage medium.

Background technique

In order to enhance the display function of the electronic chart, the existing technology superimposes the AIS information on the electronic chart for display, which is beneficial for the operator to make various responses quickly and accurately according to the displayed information. However, the use of "AIS" equipment and ship identification codes of some fishing boats is not standardized, and illegal behaviors such as "inconsistent vessel codes, multiple codes for one vessel, and multiple vessels for one code" have brought huge risks to the safe navigation of fishing vessels and search and rescue in distress. Hidden dangers have become a "big problem" that threatens the safety of fishermen's lives and property at all times.

SUMMARY OF THE INVENTION

In order to make the navigation trajectories of fishing boats, dredgers, etc. without AIS installed, be perceived by other ships around the channel to increase navigation safety, the present invention provides a ship trajectory drawing method, terminal equipment and storage medium.

The specific plans are as follows:

A method for drawing a ship trajectory, comprising the following steps:

S1: photographing objects with known coordinates through a camera;

S2: The camera is calibrated according to the captured two-dimensional image and the known coordinates of the object;

S3: Collect ship images in continuous time through the calibrated camera device, and filter the ship images through the nonlinear gradient domain guided filtering algorithm, and then perform feature extraction on ship features in each ship image;

S4: According to the extracted ship features and camera device calibration data, convert the two-dimensional coordinates of the ship features in the image into three-dimensional coordinates in the world coordinate system;

S5: Display on the chart according to the three-dimensional coordinates corresponding to the ship features in each ship image in a continuous time, and connect lines to form a ship trajectory.

Further, filtering by the nonlinear gradient domain guided filtering algorithm includes the following steps:

S31: initialization parameters, the parameters include a window size and a regularization parameter λ;

S32: For each window, calculate its corresponding first coefficient and second coefficient:

Among them, α represents the index, w _k represents the window centered on the pixel point k, a _k and b _k represent the first and second coefficients corresponding to the window centered on the pixel point k, k represents the pixel point, and γ represents the distinction parameters of edges and smooth regions, Γ represents the edge-perceptual weighting parameter, I _i represents the ith pixel in the guide image, pi represents the filter input corresponding to the ith pixel, _i represents the pixel, and |w _k | The number of pixels contained in the window w _k ;

S33: For each pixel point, calculate the average value of the first coefficient coefficients and the average value of the second coefficient coefficients of all the windows included in it:

和

分别表示第一系数和第二系数的平均值，|w|表示图像中包含的窗口的个数；in,

and

represent the average value of the first coefficient and the second coefficient, respectively, and |w| represents the number of windows included in the image;

S34: Calculate the pixel value of the filtered image according to the following formula:

Among them, qi represents the pixel value of the _ith pixel in the filtered image.

Further, the calculation formula of the edge perception weighting parameter Γ is:

Among them, N represents the number of pixels in the image, χ(j) represents the variance of the pixel value of the window where the pixel point j is located, j represents the pixel point, χ(j') represents the variance of the pixel value of the window where the pixel point j' is located, pixel The pixel value of the window where the point j' is located is the pixel value of the linearly transformed image of the guide image, and ε represents a positive number that prevents the denominator from being 0.

Further, the calculation formula of the parameter γ that distinguishes the edge and the smooth region is:

where η is an intermediate variable and μ represents the average of all χ(j) values.

A ship trajectory drawing terminal device, comprising a processor, a memory, and a computer program stored in the memory and running on the processor, and the processor implements the above-mentioned embodiments of the present invention when the processor executes the computer program. steps of the method.

A computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the steps of the foregoing method in the embodiment of the present invention.

The present invention adopts the above technical scheme to realize the display of the longitude and latitude of the monitoring ship on the chart, and in order to reduce the influence of sea fog on the monitoring video image, the non-linear gradient domain guided filtering algorithm is used to filter the image to improve the clarity of the image. Spend.

Description of drawings

FIG. 1 is a flowchart of Embodiment 1 of the present invention.

Detailed ways

To further illustrate the various embodiments, the present invention is provided with the accompanying drawings. These drawings are a part of the disclosure of the present invention, which are mainly used to illustrate the embodiments, and can be used in conjunction with the relevant description of the specification to explain the operation principles of the embodiments. With reference to these contents, one of ordinary skill in the art will understand other possible embodiments and advantages of the present invention.

The present invention will now be further described with reference to the accompanying drawings and specific embodiments.

Example 1:

An embodiment of the present invention provides a method for drawing a ship trajectory, as shown in FIG. 1 , including the following steps.

S1: The object with known coordinates is photographed by the camera device.

In this embodiment, the camera device is a camera. Objects with known coordinates can be ships or other objects, which are not limited here.

S2: The camera is calibrated according to the captured two-dimensional image and the known coordinates of the object.

The calibration and calibration of the camera is the basis of 3D reconstruction.

The basic coordinate systems related to camera imaging include pixel coordinate system, image coordinate system and world coordinate system. The transformation relationship between the 3D scene and the 2D imaging plane of the video image captured by the camera is as follows:

In the formula, (X _w , Y _w , Z _w ) are the three-dimensional coordinates in the three-dimensional scene, (x, y) are the coordinates in the two-dimensional imaging plane of the image captured by the camera, R is the rotation matrix, and t is the translation vector. ɑ _x , ɑ _y , u ₀ and v ₀ are all transformation and camera internal parameters, and γ is the radial distortion correction amount.

Expand formula (1) into:

Considering the particularity of the sea surface, taking Z _w = 0, equation (2) can be simplified as:

Computer vision technology obtains the two-dimensional information of objects or scenes in space through the camera, and combines the internal and external parameters of the camera to restore the three-dimensional information of space objects, including the size, position, and motion state of the object. In the whole process, the camera calibration needs to be performed first, that is, the various parameters of the camera, including optical parameters and geometric parameters, are obtained through operations. The optical parameters are the internal parameters of the camera, and the geometric parameters are the external parameters of the camera, including the rotation matrix and translation vector generated by the motion of the camera in space.

S3: Collect the ship images in a continuous time through the calibrated camera device, and filter the ship images through the nonlinear gradient domain guided filtering algorithm, and then perform feature extraction on the ship features in each ship image.

The nonlinear gradient domain guided filtering algorithm is described in detail below.

(1) Gradient Domain Guided Filtering Algorithm

In the gradient domain guided filtering algorithm, the filtered image q is assumed to be a linear transformation of the guided image I in the window Ω:

q=aI+b (4)

where a and b represent two coefficients, respectively.

The cost function is defined as:

Among them, X represents the image to be filtered, j represents the pixel in the image, λ represents the regularization parameter, and Γ represents the edge-aware weighting parameter, which is defined as:

Among them, N represents the number of image pixels, χ(j) represents the variance of the pixel value of the window where the pixel point j is located, j represents the pixel point, χ(j') represents the variance of the pixel value of the window where the pixel point j' is located, and the pixel point j 'The pixel value of the window is the pixel value in the linearly transformed image of the guide image, and ε represents a positive number that prevents the denominator from being 0.

γ represents the coefficient to distinguish between edges and smooth regions, and is defined as:

Among them, μ represents the average value of all χ(j) values, and the calculation formula of the intermediate variable η is:

(2) Nonlinear gradient domain guided filtering algorithm

Suppose the filtered image q is a nonlinear transformation of the guide image I:

q=aI ^α +b (9)

where α represents the exponent, and a and b represent the first and second coefficients, respectively.

To avoid gradient reversal, the following constraints are set:

1≤α≤2 (10)

When α=1, it is the traditional gradient-guided filtering algorithm, that is, equation (9) degenerates into equation (4). Therefore, the traditional gradient domain guided filtering algorithm is a special case of the nonlinear gradient domain guided filtering algorithm proposed in this embodiment.

Theorem 1: The optimal values of a and b are calculated as follows:

where w _k represents the window centered on pixel k, a _k and b _k represent the first and second coefficients corresponding to the window centered on pixel k, k represents the pixel, and I _i represents the The ith pixel, pi represents the filter input corresponding to the ith pixel, _i represents the pixel, and |w _k | represents the number of pixels contained in the window w _k .

Proof: Noise is defined as

n=q-p (13)

Substitute (11) into (13) to get:

n= ^aIα +bp (14)

The ultimate goal is to minimize this noise. Therefore, the cost function can be written as:

The partial derivatives of the network parameters can be obtained:

So the following results hold:

Substitute (19) into (18) to get:

From formula (20), we can get:

In this way, the proof of Theorem 1 is completed. Apply the above model to the entire image filtering window. But each pixel is contained in multiple windows. For example, if a 3*3 window filter is used, all points except edge regions will be contained in nine windows. Therefore, we will get | _{w k} |=9 qi values. set up:

和

分别表示第一系数和第二系数的平均值，|w|表示图像中包含的窗口的个数。in,

and

represent the average value of the first coefficient and the second coefficient, respectively, and |w| represents the number of windows included in the image.

Take the average of all _qi values to get the final result.

Among them, qi represents the pixel value of the _ith pixel in the filtered image.

The features mainly include feature points, feature lines and regions. In most cases, feature points are used as matching primitives, and the feature point extraction algorithm can use commonly used algorithms, such as the method based on directional derivatives, the method based on image brightness contrast relationship, the method based on mathematical morphology and so on.

S4: Convert the two-dimensional coordinates of the ship features in the image into three-dimensional coordinates in the world coordinate system according to the extracted ship features and the camera device calibration data.

That is to find the coordinates (X _w , Y _w , Z _w ) of the ship features in each ship image corresponding to the world coordinate system.

S6: Display on the chart according to the three-dimensional coordinates corresponding to the ship features in each ship image in a continuous time, and connect lines to form a ship trajectory.

In this embodiment, considering the particularity of the sea surface, Z _w =0 is taken, and (X _w , Y _w ) in the coordinates in the world coordinate system characterized by the ship is displayed on the chart.

Experimental verification:

Taking the Haicang Bridge in Xiamen as an example, the coordinates of the beacon are shown in Table 1:

Table 1

beacon latitude longitude high image coordinates Haicang Bridge No. 1 Bridge Culvert 24°29'49.5"N 118°04'14.7"E 55 meters (277,250) Haicang Bridge No. 2 Bridge Culvert 24°29'49.6"N 118°04'06.6"E 55 meters (950,335) Haicang Bridge No. 3 Bridge Culvert 24°29'49.7"N 118°03'59.1"E 55 meters (1206,379) Cow Dung Reef Light Pile 24°29'56.7"N 118°04'15.9"E 0 (1269,490)

Substitute into formula (2) to get:

Solutions have to:

Therefore, the transformation relationship between the 3D scene and the 2D imaging plane of the image captured by the camera is:

Through the surveillance video on the buoy, the trajectory positions of the ship in the image are (1220, 500), (1250, 510), (1280, 520) respectively. The latitude and longitude are obtained as shown in Table 2:

Table 2

image coordinates latitude longitude high (1220,500) 24°29.848N 118°4.042E 0 (1250,510) 24°29.798N 118°4.03E 0 (1280,520) 24°29.781N 118°4.016E 0

The first embodiment of the present invention displays the longitude and latitude of the monitoring ship on the chart, and in order to reduce the influence of sea fog on the monitoring video image, a nonlinear gradient domain guided filtering algorithm is used to filter the image to improve the clarity of the image.

Embodiment 2:

The present invention also provides a terminal device for drawing ship trajectory, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the present invention when the processor executes the computer program Steps in the above method embodiment of Embodiment 1.

Further, as an executable solution, the ship trajectory drawing terminal device may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The ship trajectory drawing terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the composition structure of the above-mentioned ship trajectory drawing terminal equipment is only an example of the ship trajectory drawing terminal equipment, and does not constitute a limitation on the ship trajectory drawing terminal equipment, and may include more or less components than the above, Or combine some components, or different components, for example, the ship trajectory drawing terminal device may further include an input and output device, a network access device, a bus, etc., which is not limited in this embodiment of the present invention.

Further, as an executable solution, the so-called processor may be a central processing unit (Central Processing Unit, CPU), and may also be other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuits) Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor is the control center of the ship trajectory drawing terminal device, and uses various interfaces and lines to connect the entire ship trajectory drawing terminal. parts of the device.

The memory can be used to store the computer program and/or module, and the processor implements the ship by running or executing the computer program and/or module stored in the memory and calling the data stored in the memory. Traces draw various functions of the terminal device. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system and an application program required for at least one function; the storage data area may store data created according to the use of the mobile phone, and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory such as hard disk, internal memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card , a flash memory card (Flash Card), at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The present invention further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the foregoing method in the embodiment of the present invention are implemented.

If the modules/units integrated in the ship trajectory drawing terminal device are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, the steps of the foregoing method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, and the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, ROM, Read-Only Memory) ), random access memory (RAM, Random Access Memory), and software distribution media.

Although the present invention has been particularly shown and described in connection with preferred embodiments, it will be understood by those skilled in the art that changes in form and detail may be made to the present invention without departing from the spirit and scope of the invention as defined by the appended claims. Various changes are made within the protection scope of the present invention.

Claims (6)

1. a ship trajectory drawing method, is characterized in that, comprises the following steps: S1: photographing objects with known coordinates through a camera; S2: The camera is calibrated according to the captured two-dimensional image and the known coordinates of the object; S3: Collect ship images in continuous time through the calibrated camera device, and filter the ship images through the nonlinear gradient domain guided filtering algorithm, and then perform feature extraction on ship features in each ship image; S4: According to the extracted ship features and camera device calibration data, convert the two-dimensional coordinates of the ship features in the image into three-dimensional coordinates in the world coordinate system; S5: Display on the chart according to the three-dimensional coordinates corresponding to the ship features in each ship image in a continuous time, and connect lines to form a ship trajectory. 2. ship trajectory drawing method according to claim 1 is characterized in that: the nonlinear gradient domain guided filtering algorithm filtering comprises the following steps: S31: initialization parameters, the parameters include a window size and a regularization parameter λ; S32: For each window, calculate its corresponding first coefficient and second coefficient:

Among them, α represents the index, w _k represents the window centered on the pixel point k, a _k and b _k represent the first and second coefficients corresponding to the window centered on the pixel point k, k represents the pixel point, and γ represents the distinction parameters of edges and smooth regions, Γ represents the edge-perceptual weighting parameter, I _i represents the ith pixel in the guide image, pi represents the filter input corresponding to the ith pixel, _i represents the pixel, and |w _k | The number of pixels contained in the window w _k ; S33: For each pixel point, calculate the average value of the first coefficient coefficients and the average value of the second coefficient coefficients of all the windows included in it:

in,

and

represent the average value of the first coefficient and the second coefficient, respectively, and |w| represents the number of windows included in the image; S34: Calculate the pixel value of the filtered image according to the following formula:

Among them, qi represents the pixel value of the _ith pixel in the filtered image. 3. ship trajectory drawing method according to claim 2, is characterized in that: the calculation formula of edge perception weighting parameter Γ is:

Among them, N represents the number of pixels in the image, χ(j) represents the variance of the pixel value of the window where the pixel point j is located, j represents the pixel point, χ(j') represents the variance of the pixel value of the window where the pixel point j' is located, pixel The pixel value of the window where the point j' is located is the pixel value of the linearly transformed image of the guide image, and ε represents a positive number that prevents the denominator from being 0. 4. ship trajectory drawing method according to claim 3 is characterized in that: the calculation formula of the parameter γ of distinguishing edge and smooth area is:

where η is an intermediate variable and μ represents the average of all χ(j) values. 5. A ship trajectory drawing terminal device, characterized in that: it comprises a processor, a memory and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, The steps of any one of claims 1-4. 6. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, characterized in that: when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented .

Images