CN103336282B - A kind of cabin locating device and localization method thereof automatically - Google Patents

Abstract

The invention discloses an automatic cabin locating device and a locating method thereof. The locating device is installed on a quay wall shifting ship loader. The positioning method includes: Step 1. The cantilever of the ship loader is retracted and raised to an angle of 70 degrees with the ground, and the cart is moved to the side of the bow of the ship, and the cart runs from the bow of the ship to the stern of the ship at a given speed Step 2, run the automatic cabin positioning device, scan the ship to obtain the two-dimensional coordinate information of the ship; Step 3, the industrial computer performs preprocessing to obtain the adaptive grayscale image value of the ship; Step 4, the industrial computer extracts the ship's The feature of the two-dimensional grayscale image is to obtain the edge of the ship near the sea; step 5, the industrial computer performs binarization processing on the two-dimensional grayscale image of the ship to obtain the position of the ship's cabin. The invention is not affected by the environment and temperature, can effectively and accurately detect the position of the cabin and related information, and monitor the whole process in real time. The device has simple structure, simple operation and low cost.

Description

An automatic cabin positioning device and its positioning method

technical field

The invention relates to a cabin positioning device and method, in particular to an automatic cabin positioning device and a positioning method thereof.

Background technique

Today, more and more ports are shifting from artificial mechanized ports to unmanned intelligent ports. With the continuous development of international shipping and bulk cargo logistics, the automation of bulk cargo terminals will also be an inevitable trend. In the prior art, a digital camera is used as an image sensor, and a standardized marker image needs to be fixed on the control target in advance. With the aid of markers, the vision system can be used to calculate the three-dimensional coordinates of the target. The digital camera method applies to the machine itself. However, this approach is limited for automatic control of bulk terminal machinery. It is very difficult to install standard marking images on dry bulk cargo and bulk carriers, and the environment of bulk cargo terminals is very harsh. Using digital cameras and standard marking images will reduce the reliability of digital video camera vision systems.

Contents of the invention

The purpose of the present invention is to provide an automatic cabin positioning device and its positioning method, which can effectively and accurately detect the position and related information of the cabin without being affected by the environment and temperature, and monitor the whole process in real time. The device structure is simple, Simple operation and low cost.

In order to achieve the above object, the present invention is achieved through the following technical solutions: an automatic cabin positioning device installed on a shore wall shifting ship loader, which is characterized in that it includes: a two-dimensional laser radar and an industrial computer;

The above two-dimensional laser radar is installed on the square maintenance platform of the ship loader;

The data is transmitted between the above-mentioned two-dimensional laser radar and the industrial computer through optical fiber and shielded twisted pair;

The above-mentioned two-dimensional laser radar is used as a visual sensor to transmit the scanned image data to the industrial computer;

The aforementioned industrial computer processes and analyzes the scanned image;

The aforementioned industrial computer is also connected with a display capable of displaying the current scanning picture in real time.

A positioning method for the above-mentioned automatic cabin positioning device,

The positioning methods mentioned above include:

Step 1. The cantilever of the ship loader retracts and rises to an angle of 70 degrees to the ground, and the cart runs to the bow side of the ship, and the cart runs from the bow to the stern of the ship at a given speed;

Step 2, run the automatic cabin positioning device, the two-dimensional laser radar starts to work, scans the ship, and obtains the two-dimensional coordinate information of the ship;

Step 3, the industrial computer performs preprocessing to obtain the adaptive grayscale image value of the ship;

Step 4, the industrial computer extracts the two-dimensional grayscale image features of the ship, and obtains the edge of the ship near the sea;

Step 5. The industrial computer performs binarization processing on the two-dimensional grayscale image of the ship to obtain the position of the ship's cabin.

The above step 2 also includes the following steps:

Step 2.1, the above two-dimensional laser radar scans the ship in the direction of the coast every 20ms, and each section corresponds to a value of the position encoder of the cart;

Step 2.2, establishing a two-dimensional Cartesian coordinate system;

Step 2.3, the industrial computer obtains the point cloud data formed by the straight-line distance from the two-dimensional laser radar to the scanning point of the ship;

In step 2.4, the industrial computer converts the point cloud data into two-dimensional coordinate information corresponding to the section.

The two-dimensional Cartesian coordinate system in the above step 2.2 is established with the position of the two-dimensional laser radar as the coordinate origin, the positive direction of the Y axis vertically downward, and the positive direction of the X axis on the coast side.

The above step 3 also includes the following steps:

Step 3.1, the industrial computer obtains the adaptive grayscale pixel value according to the distance from the ship outline data point to the two-dimensional laser radar;

Step 3.2, the industrial computer obtains the distance between adjacent scanning sections according to the running speed information of the cart;

Step 3.3, the industrial computer spatially reorganizes all the cross-sectional data scanned by the two-dimensional laser radar, interpolates the cross-section every 10cm, and removes redundant cross-sectional data;

Step 3.4, the industrial computer reconstructs the two-dimensional grayscale image of the ship, and performs filtering and denoising processing on the two-dimensional grayscale image.

In the above-mentioned step 3.1, the ship outline data points are obtained by the following methods;

The industrial computer customizes the grayscale pixel threshold k. When y>k, it means that the point scanned at this time is the interior of the ship cabin or the water surface. At this time, the pixel of this point is defined as 0; when y<=k, it means that the point is Ship outline data points.

The above step 4 also includes the following steps:

Step 4.1, when the ship docks, the industrial computer calibrates the coast side;

Step 4.2, the image matrix of the custom reconstruction of the industrial computer is , where i, j correspond to the rows and columns of the two-dimensional grayscale image matrix, respectively;

Step 4.3, the industrial computer defines a scanning matrix P, the rows of the matrix P take values according to the actual situation and requirements on site, and the columns of the matrix P are taken as j;

Step 4.4, the scanning matrix P scans from top to bottom in the image matrix H to obtain the outline of the ship;

Step 4.4, the industrial computer calculates the gray pixel point distribution density ρ of the ship according to the outline of the ship;

Step 4.5, the industrial computer obtains the edge of the seaside of the ship according to the change of the value of ρ.

The gray pixel point distribution density ρ of the ship in the above step 4.4 is obtained by the following method:

Each element in the scanning matrix P corresponds to a pixel in the current scanning position of the image matrix H, and the element When , it means that the point is black, indicating that the point is not the outline of the ship; ρ is the ratio of the number of black point elements in the current scanning area to all elements in the scanning matrix P.

Step 5 above includes:

Step 5.1, the industrial computer customizes a square scanning matrix T;

Step 5.2. Scanning matrix T starts from the upper left corner of image matrix H and traverses image matrix H at intervals of 1 or 2 pixels from left to right and from top to bottom until ρ in current T is less than a given value. After the scan is over, the four edges of the adjacent ship's cabin are obtained;

Step 5.3, the industrial computer calculates the position and size of the ship's cabin according to the four edges of the ship;

Step 5.4, the industrial computer corresponds the position of the ship's cabin to the value of the cart position encoder;

Step 5.5, move the cart to the designated ship cabin.

At the end of the scan in the above step 5.2, the coordinates of the midpoint of the scan matrix T are in the cabin of the ship, thus leading to two imaginary straight lines in the horizontal and vertical directions. When non-zero pixels appear for the first time respectively, the adjacent The four edges of the ship's cabin.

Compared with the prior art, an automatic cabin positioning device and its positioning method of the present invention have the following advantages: because a two-dimensional laser radar is provided, the two-dimensional image of the ship can be scanned in real time; Find the edge of the seaside of the ship; due to the square scanning matrix T, the position of the cabin can be quickly located.

Description of drawings

Fig. 1 is a schematic diagram of the automatic cabin positioning device of the present invention.

Fig. 2 is a flow chart of the automatic cabin positioning method of the present invention.

Fig. 3 is a schematic diagram of two-dimensional image reconstruction and feature extraction of the automatic cabin positioning device of the present invention.

Detailed ways

The present invention will be further elaborated below by describing a preferred specific embodiment in detail in conjunction with the accompanying drawings.

As shown in Figure 1, an automatic cabin positioning device is installed on the shore wall shifting ship loader, including: two-dimensional laser radar 1 and industrial computer; two-dimensional laser radar 1 is installed on the bucket square maintenance platform of the ship loader In the above, it is used as the visual sensor part for the positioning of the ship’s third cabin, which obtains the outline data of the ship’s third cargo hold and transmits it to the industrial computer. The two-dimensional laser radar 1 has a wide scanning coverage and a scanning angle of 270 degrees; the industrial computer and the two-dimensional laser radar 1 to transmit data through optical fiber and shielded twisted pair, and the industrial computer has a display, which can display the current scanning screen in real time.

As shown in Figure 2 and Figure 3, a flow chart of a positioning method for the above-mentioned automatic cabin positioning device, the positioning method includes:

Step 1. The cantilever of the ship loader shrinks and rises to an angle of 70 degrees with the ground, and the cart 2 runs to the bow side of the ship 3, and the cart 2 runs from the bow of the ship 3 to the ship 3 at a given speed stern.

Step 2, run the automatic cabin positioning device, the two-dimensional laser radar 1 starts to work, scans the ship 3, and obtains the two-dimensional coordinate information of the ship 3;

Step 2.1, the two-dimensional laser radar 1 scans the ship 3 in 4 directions on the coast every 20ms, and each section corresponds to a value of the position encoder of the cart 2;

Step 2.2, take the location of the two-dimensional laser radar 1 as the coordinate origin, vertically downward as the positive direction of the Y axis, and the coast side 4 as the positive direction of the X axis to establish a two-dimensional rectangular coordinate system;

Step 2.3, the industrial computer obtains the point cloud data formed by the linear distance from the two-dimensional laser radar 1 to the scanning point of the ship 3;

In step 2.4, the industrial computer converts the point cloud data into two-dimensional coordinate information corresponding to the section.

Step 3, the industrial computer performs preprocessing to obtain the adaptive grayscale image value of the ship 3;

Step 3.1. The industrial computer obtains the adaptive grayscale pixel value according to the distance from the ship 3 outline data point to the two-dimensional laser radar 1. The industrial computer defines the grayscale pixel threshold k. When y>k, it means the point scanned at this time It is the interior of the cabin of the ship 3 or the water surface. At this time, the pixel of this point is defined as 0; when y<=k, it means that the point is the outline data point of the ship 3;

Step 3.2, the industrial computer obtains the distance between adjacent scanning sections according to the running speed information of the cart 2;

Step 3.3, the industrial computer spatially reorganizes all the cross-sectional data scanned by the two-dimensional laser radar 1, interpolates the cross-section every 10cm, and removes redundant cross-sectional data;

Step 3.4, the industrial computer reconstructs the two-dimensional grayscale image of the ship 3, and performs filtering and denoising processing on the two-dimensional grayscale image.

As shown in Figure 3, in step 4, the industrial computer extracts the two-dimensional grayscale image features of the ship 3 to obtain the edge of the ship 3 near the sea;

Step 4.1, when the ship 3 docks, the industrial computer calibrates the coast side 4;

Step 4.2, the image matrix of the custom reconstruction of the industrial computer is , where i, j correspond to the rows and columns of the two-dimensional grayscale image matrix, respectively;

Step 4.3, the industrial computer defines a scanning matrix P, the rows of the matrix P take values according to the actual situation and requirements on site, and the columns of the matrix P are taken as j;

Step 4.4, the scan matrix P is scanned from top to bottom in the image matrix H to obtain the outline of the ship 3, each element in the scan matrix P corresponds to a pixel in the current scan position of the image matrix H, and the element ρ means that the point is black, indicating that the point is not the outline of the ship 3; ρ is the ratio of the number of black point elements in the current scanning area to all elements in the scanning matrix P. ;

Step 4.4, the industrial computer calculates the gray pixel point distribution density ρ of the ship 3 according to the outline of the ship 3;

Step 4.5, the industrial computer obtains the seaside edge of the ship 3 according to the change of the value of ρ.

Step 5, the industrial computer performs binarization processing on the two-dimensional grayscale image of the ship 3 to obtain the position of the cabin of the ship 3;

Step 5.1, the industrial computer customizes a square scanning matrix T;

Step 5.2. Scanning matrix T starts from the upper left corner of image matrix H and traverses image matrix H at intervals of 1 or 2 pixels from left to right and from top to bottom until ρ in current T is less than a given value. At the end of the scan, the four edges of the neighboring ship's cabin 3 are obtained. At the end of the scan, the coordinates of the midpoint of the scanning matrix T are in the ship's cabin 3, thus leading to two false horizontal and vertical straight lines, which appear for the first time in each When the pixel is non-zero, the four edges of the adjacent ship 3 cabins are obtained;

Step 5.3, the industrial computer calculates the position and size of the 3 cabins of the ship according to the four edges of the ship;

Step 5.4, the industrial computer corresponds the position of the 3rd cabin of the ship to the value of the position encoder of the cart 2;

Step 5.5, move the cart 2 to the designated cabin of the ship 3 .

Although the content of the present invention has been described in detail through the above preferred embodiments, it should be understood that the above description should not be considered as limiting the present invention. Various modifications and alterations to the present invention will become apparent to those skilled in the art upon reading the above disclosure. Therefore, the protection scope of the present invention should be defined by the appended claims.

Claims (8)

1. a localization method for automatic cabin locating device, comprises automatic cabin locating device, and this automatic cabin locating device is arranged on bulkhead wall moving type ship loader, and this device comprises two-dimensional laser radar (1) and industrial computer; What described two-dimensional laser radar (1) was arranged on ship loader slips on the square maintenance platform of bucket; Data are transmitted by optical fiber and Shielded Twisted Pair between described two-dimensional laser radar (1) and industrial computer; Scan image data, as vision sensor, is transferred to industrial computer by described two-dimensional laser radar (1); Described industrial computer carries out Treatment Analysis to scan image; Described industrial computer is also connected with the display that can show Current Scan picture in real time, it is characterized in that, described localization method comprises:

Step 1, ship loader cantilever shrink and rise, rising to ground is 70 degree of angles, cart (2) is moved to boats and ships (3) fore side, and cart (2) moves to boats and ships (3) stern with given speed from boats and ships (3) fore;

Step 2, run automatic cabin locating device, two-dimensional laser radar (1) is started working, and scans boats and ships (3), obtains the two-dimensional coordinate information of boats and ships (3);

Step 3, industrial computer carry out pre-service, obtain the self-adaptation grayscale image values of boats and ships (3);

Step 4, industrial computer extract the 2-D gray image feature of boats and ships (3), obtain the edge of boats and ships (3) by extra large side;

Step 5, the industrial computer 2-D gray image to boats and ships (3) carries out binary conversion treatment, and obtain the cabin position of boats and ships (3), wherein said step 5 comprises:

The self-defined square scan matrix T of step 5.1, industrial computer;

Step 5.2, scan matrix T from the image array H upper left corner with the interval of 1 or 2 pixel according to from left to right, order traversal image array H from top to bottom, until when the ρ in current T is less than set-point, the end of scan, obtains the four edges edge of contiguous boats and ships (3) cabin;

Step 5.3, industrial computer calculate position and the size of boats and ships (3) cabin according to the four edges edge of boats and ships;

Step 5.4, industrial computer are corresponding with the value of cart (2) position coder by the position of boats and ships (3) cabin;

Step 5.5, cart (2) is moved to boats and ships (3) cabin of specifying.

2. cabin localization method automatically as claimed in claim 1, it is characterized in that, described step 2 also comprises following steps:

Step 2.1, described two-dimensional laser radar (1) do seashore side (4) scanning direction every 20ms to boats and ships (3), and each cross section corresponds to a value of cart (2) position coder;

Step 2.2, set up two-dimensional direct angle coordinate system;

Step 2.3, industrial computer obtain the cloud data that two-dimensional laser radar (1) is formed to the air line distance of boats and ships (3) analyzing spot;

Cloud data is converted into the two-dimensional coordinate information corresponding with cross section, place by step 2.4, industrial computer.

3. cabin localization method automatically as claimed in claim 2, it is characterized in that, two-dimensional direct angle coordinate system in described step 2.2 is for true origin with two-dimensional laser radar (1) position, be Y-axis positive dirction straight down, seashore side (4) are the foundation of X-axis positive dirction.

4. cabin localization method automatically as claimed in claim 1, it is characterized in that, described step 3 also comprises following steps:

Step 3.1, industrial computer obtain self-adaptation gray-scale pixel values according to boats and ships (3) number of contours strong point to the distance of two-dimensional laser radar (1);

Step 3.2, industrial computer obtain the distance of adjacent scanning cross-section according to the travelling speed information of cart (2);

Two-dimensional laser radar (1) is scanned all cross-section datas and carries out spatial recomposition by step 3.3, industrial computer, does interpolation, remove unnecessary cross-section data every 10cm pair cross-section;

Step 3.4, industrial computer rebuild the 2-D gray image of boats and ships (3), and carry out filtering and noise reduction process to 2-D gray image.

5. cabin localization method automatically as claimed in claim 4, it is characterized in that, in described step 3.1, boats and ships (3) number of contours strong point is obtained by following method;

The self-defined gray-scale pixels threshold value k of industrial computer, as y>k, represent that the point now swept to is boats and ships (3) cabin inside or the water surface, now defining this pixel is 0; As y<=k, represent that this point is boats and ships (3) number of contours strong point.

6. cabin localization method automatically as claimed in claim 1, it is characterized in that, described step 4 also comprises following steps:

When step 4.1, boats and ships (3) pull in shore, industrial computer is demarcated seashore side (4);

The image array of the self-defined reconstruction of step 4.2, industrial computer is $H=\left[\begin{array}{ccc}{a}_{11}& \mathrm{\&Lambda;}& a_{1j}\\ M& O& M\\ a_{i1}& \mathrm{\&Lambda;}& a_{ij}\end{array}\right],$ The wherein row and column of the corresponding 2-D gray image matrix of i, j difference;

The row of step 4.3, industrial computer self-defined a scan matrix P, matrix P is according to on-site actual situations and require value, and the row of matrix P are taken as j;

Step 4.4, scan matrix P scan from top to bottom in image array H, obtain the profile of boats and ships (3);

Step 4.4, industrial computer are according to the gray pixels point distribution density ρ of the profile Ship ' (3) of boats and ships (3);

Step 4.5, industrial computer, according to the change of ρ value, obtain the edge of boats and ships (3) by extra large side.

7. cabin localization method automatically as claimed in claim 6, it is characterized in that, the gray pixels point distribution density ρ of the boats and ships (3) in described step 4.4 is obtained by following method:

Each element in scan matrix P corresponds to the pixel in image array H present scanning position, element P _xyrepresent when=0 that this point is black, illustrate that this point is not boats and ships (3) profile; ρ is the ratio that the number of black color dots element in Current Scan region accounts for all elements in scan matrix P.

8. cabin localization method automatically as claimed in claim 1, it is characterized in that, in described step 5.2 during the end of scan, the middle point coordinate of scan matrix T is in boats and ships (3) cabin, draw the level of two illusions and the straight line of vertical direction thus, when non-zero pixels point appears in first time separately, obtain the four edges edge of contiguous boats and ships (3) cabin.