KR101894204B1 - Realtime container truck monitoring method and system - Google Patents

Abstract

The disclosed technology relates to a real-time container truck monitoring method and system, the method comprising the following steps: capturing a plurality of different images by a monitoring system that photographs the ground on which a container truck is moving by using a plurality of cameras disposed on the container truck; generating an image of a road through which the container truck passes by matching the plurality of different images; measuring a distance on the front portion of a container connected to the container truck by using a pair of distance sensors disposed on the rear surface of the container truck body; calculating a rotation angle of the container truck based on the measured distance; and merging images of the container truck having the rotation angle reflected into an image of the road and outputting the merged image on a screen. Therefore, there is an effect that real-time monitoring can be performed using more accurate images of the road and container truck.

Description

REALTIME CONTAINER TRUCK MONITORING METHOD AND SYSTEM [0001]

The disclosed technique relates to a method and system for monitoring container trucks in real time.

Various types of cameras are used regardless of the size or type of the vehicle. Most commonly, various types of cameras are used, ranging from a rear camera for parking assistance to a black box for storing images in case of an accident.

These cameras can adjust the installation position and angle so that all the 360 degrees of the surroundings of the vehicle can be photographed, or a high-performance camera capable of shooting a wider range can be used.

On the other hand, since it is troublesome for the user or the administrator to check each of these images, a technique of matching these images to one image so that the user can easily confirm such images is recently used. Korean Patent Laid-Open No. 10-2017-0026750 (entitled " manual correction device and method for vehicle image registration "), when an image is photographed using a plurality of cameras mounted on a vehicle, And the like.

However, such a method can be used without difficulty in a general passenger car, but it is difficult to use it in a vehicle in which a large container is connected behind the body of a vehicle such as a trailer.

The disclosed technique is to provide a method and system for monitoring a container truck using a plurality of images captured in real time.

According to a first aspect of the present invention, there is provided a method of monitoring a container truck, the method comprising: capturing a plurality of different images using a plurality of cameras arranged on a container truck, A distance between the container truck and the front portion of the container connected to the container truck by using a pair of distance sensors disposed on a rear surface of the container truck, Calculating a rotation angle of the container truck on the basis of a result of measuring the distance, and outputting the merged image of the container truck reflecting the rotation angle on the image of the road to the screen, To provide a real-time container truck monitoring method There is.

According to a second aspect of the present invention, there is provided a container truck, comprising: a plurality of cameras arranged on a container truck to capture a plurality of different images by photographing a ground on which the container truck is moving; A pair of distance sensors for measuring a distance between the container truck and a front portion of a container connected to the container truck, a controller for receiving the different images from the plurality of cameras and matching the images to one image, And a controller for receiving a distance value measured from the pair of distance sensors and measuring a front portion of the container, calculating a rotation angle of the container truck, and calculating a rotation angle of the container truck, A processor for merging an image of said bottle To provide a real-time container truck monitoring system that includes a monitor for outputting the image.

Embodiments of the disclosed technique may have effects that include the following advantages. It should be understood, however, that the scope of the disclosed technology is not to be construed as limited thereby, since the embodiments of the disclosed technology are not meant to include all such embodiments.

According to one embodiment of the disclosed technology, a real-time container truck monitoring method and system has the effect of real-time monitoring using more accurate roads and images of container trucks.

In addition, there is an effect that an alarm is generated by detecting a foreign object located outside the sight of the driver during driving.

1 is a flow diagram of a method for monitoring a real-time container truck according to an embodiment of the disclosed technique.
2 is a block diagram of a real-time container truck monitoring system in accordance with one embodiment of the disclosed technology.
Figure 3 illustrates matching different images according to one embodiment of the disclosed technique.
4 is a diagram illustrating measuring the angle of rotation of a container in accordance with one embodiment of the disclosed technique.
5 is a diagram illustrating a camera that captures a blind spot in accordance with one embodiment of the disclosed technique.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terms first, second, A, B, etc., may be used to describe various components, but the components are not limited by the terms, but may be used to distinguish one component from another . For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that the singular < RTI ID = 0.0 > terms < / RTI > used herein should be interpreted to include a plurality of representations unless the context clearly dictates otherwise. And "comprises ", when used in this specification, specify the presence of stated features, numbers, steps, operations, elements, parts, or combinations thereof, Or combinations thereof, as a matter of course.

Before describing the drawings in detail, it is to be clarified that the division of constituent parts in this specification is merely a division by main functions of each constituent part. That is, two or more constituent parts to be described below may be combined into one constituent part, or one constituent part may be divided into two or more functions according to functions that are more subdivided.

In addition, each of the constituent units described below may additionally perform some or all of the functions of other constituent units in addition to the main functions of the constituent units themselves, and that some of the main functions, And may be carried out in a dedicated manner. Accordingly, the presence or absence of each component described in this specification should be interpreted as a function.

1 is a flow diagram of a method for monitoring a real-time container truck according to an embodiment of the disclosed technique. Referring to FIG. 1, a real-time container truck monitoring method includes the following steps.

In step 110, the monitoring system acquires a plurality of different images using a plurality of cameras disposed on the container truck. In one embodiment, a plurality of cameras may be pre-positioned on a container truck and different images may be obtained from each of the cameras. Here, the plurality of cameras can photograph the ground of the place where the container truck is moving at the position where each of the cameras is disposed.

Meanwhile, as described above, a plurality of cameras are disposed on the container truck, and the container truck may be disposed at a position spaced apart by a predetermined width so as to obtain a plurality of images with respect to the moving ground, or a camera may be disposed for each direction. For example, as shown in FIG. 3, a plurality of cameras may be disposed on the front, rear, and side surfaces of the container truck, respectively, to obtain different images from the cameras.

Meanwhile, the container truck referred to in the disclosed technology means a large-sized vehicle in which a predetermined container is connected through a connection portion provided at a rear portion of a truck body. Unlike passenger cars or small cars, these large vehicles can be moved in different directions and angles than the intention of the driver due to the power of the truck. In this case, the driver will inadvertently monitor the situation while driving, because it will intentionally invade the lane or affect other vehicles in the vicinity. Thus, the disclosed technique allows the driver to monitor such situation directly.

In step 120, the monitoring system generates images of roads passing through the container trucks by matching a plurality of different images obtained in step 110. [ In one embodiment, the coordinates of each of the plurality of different images and the positions of the plurality of cameras are corrected to generate an image of the road.

3, the monitoring system includes an image 301 obtained from a camera installed on a front surface of a truck, images 302 and 303 obtained from a camera installed on a side surface of the truck, The images 304 and 305 obtained from the camera and the image 306 obtained from the camera installed on the rear surface of the container can be matched and matched to one road image. Various techniques for image registration are disclosed in the related art, but in the disclosed technology, images can be registered considering the positions where the cameras are installed. In addition, the monitoring system captures images of different coordinate axes according to the position where each camera is disposed. Therefore, the monitoring system corrects coordinate positions of the respective images and the positions of the respective images, It is possible to match with the road image.

In step 120, the monitoring system may generate an image of the road by matching the outline of the road included in each of the plurality of images. In one embodiment, some of the images captured by the cameras may be overlapping areas, where the monitoring system may generate a single road image by searching for road contours of the images and matching them.

In step 130, the monitoring system measures the distance between the truck and the container using the distance sensor. In one embodiment, the distance from the front portion of the container connected to the container truck can be measured using a pair of distance sensors disposed on the rear surface of the container truck. 4, a pair of distance sensors disposed to the left and right with respect to the center axis of the container truck respectively irradiate light in a direction perpendicular to the back surface of the truck or emit ultrasonic waves to measure the respective distance values . The distance 401 between the right rear portion of the truck and the right front portion of the container, and the distance 402 between the left rear portion of the truck and the left front portion of the container, respectively.

On the other hand, in step 130, the monitoring system can replace the distance sensor with a camera. For example, each distance can be estimated using a method in which the same camera as the image of the road is photographed on the left and right sides of the rear portion of the truck and the depth of the image is calculated by photographing the left and right sides of the container, respectively.

On the other hand, the monitoring system calculates the rotation angle of the container truck based on the result of measuring the distance between the left and right sides of the container in accordance with step 140. For example, the angle between the body of the truck and the container can be calculated based on the difference of the two distance values. Container truck, as mentioned above, the truck itself is moving accurately according to the power, but the container connected to the rear is dragged according to the power of the truck. When the truck turns left or right, the turning angle changes according to the turning radius. At this time, unlike the driver's intention, a part of the container body may hit the other vehicle, or the lane may be separated. Therefore, in order to monitor the situation, the system calculates the rotation angle based on the measured distance .

On the other hand, in step 140, the monitoring system can determine whether the rotation angle exceeds the threshold value and photograph the blind spot 501 generated between the cameras when the container truck rotates. For example, referring to FIG. 5, a camera 502 may be further provided on one side of the rear surface of the container truck. The camera 502 on the rear side of the truck waits in a sleep state unlike other cameras. If the monitoring system determines that the rotation angle exceeds the threshold value, the camera 502 transmits an operation signal to the camera 502, The blind spot 501 can be photographed. Further, the photographed image can be further matched to generate an image of the road. Also for this purpose, the camera 502 disposed on the rear side of the container truck may replace the function of the distance sensor 220 measuring the distance between the container truck and the container.

In step 150, the monitoring system generates an image of the container truck reflecting the calculated rotation angle. Then, the image of the container truck is merged on the created road image and outputted to the screen. The operator of the container truck can monitor the driving situation using one image generated in real time. In one embodiment, when the monitoring system displays on the screen that the container truck has entered the road boundary, an alarm may be generated through a speaker provided in the vehicle.

2 is a block diagram of a real-time container truck monitoring system in accordance with one embodiment of the disclosed technology. Referring to FIG. 2, the real-time container truck monitoring system includes a plurality of cameras 210, a distance sensor 220, a processor 230, and a monitor 240.

The plurality of cameras 210 are disposed in a container truck, and photographs the ground on which the container truck is moving to acquire different images. Here, the term "different images" means that each of the cameras shoots the floor where the container truck passes, but the images are also different because the positions of the actual cameras are different.

In one embodiment, the plurality of cameras 210 may be disposed on the front, back, and sides of the container truck, as shown in FIG. 3, to obtain different images for the container truck being moved.

The distance sensor 220 is disposed on the rear surface of the container truck to measure the distance from the front surface of the container connected to the container truck. In one embodiment, the distance sensing sensors 220 may be disposed on the left and right sides of the center axis of the container truck. And the left and right distances of the front portion of the container can be respectively measured.

Here, the distance sensor 220 may use a sensor that emits light such as infrared rays, or a sensor that measures the speed at which ultrasonic waves are reflected. In addition, the same camera as the camera 210 may be used. If the distance is measured using the camera 210, the depth can be estimated by applying an algorithm for estimating the depth of the front surface of the container in the photographed image. The measured distance value is transmitted to the processor 230 by using the distance sensor 220 in various ways.

The processor 230 receives different images from the plurality of cameras 210 and registers them as one image. As described above with reference to FIG. 1, the images can be matched in such a manner that the angles and directions of different images are corrected based on the coordinate axes of the different images and the locations of the plurality of cameras stored in advance. The image of the road can be generated by matching the outline of the road included in each of the different images. In this case, an error value may be generated between the images of the respective cameras according to the height or angle of the camera installed. The error value for correction may be stored in advance in the processor by checking this point in advance. can do.

Meanwhile, the processor 230 calculates the rotation angle of the container truck using the distance value received from the distance sensor 220 in order to reflect the image of the container truck in merging the image of the container truck onto the image of the road. In one embodiment, the angle of rotation can be calculated based on the difference between the distance values 401 and 402 that occur between the rear of the truck and the front of the container, as shown in FIG. Then, the computed rotation angle is reflected on the image of the truck and merged with the image of the road. The processor 230 generates images for roads and container trucks in real time in this manner.

On the other hand, the rotation angle calculated by the processor 230 may not necessarily coincide with the angle at which the actual road is bent. This is because the processor is not inaccurate but can vary due to the state of the driving road, the speed of the vehicle, or other variables. Therefore, the processor must be able to calculate whether the container leaves the lane or affect other vehicles in the vicinity as the truck rotates and inform the driver of the result. For example, an operation signal that generates an alarm can be transmitted when the container touches the boundary of the road during rotation.

The monitor 240 outputs an image merged by the processor 230. In one embodiment, the monitor can output an image input in real time to the screen according to the image quality supported by the device. The monitor 240 can be replaced with a navigation or other display device that is typically connected to the vehicle. The operator can prevent an accident that may occur during the running of the container truck through the image outputted through the monitor in real time.

Although the method and system for real-time container truck monitoring according to an embodiment of the disclosed technology has been described with reference to the embodiments shown in the drawings for the sake of understanding, it is to be understood that those skilled in the art It will be understood that various modifications and equivalent embodiments are possible. Accordingly, the true scope of protection of the disclosed technology should be determined by the appended claims.

110: Multiple images acquisition 120: Road image creation
130: Distance measurement 140: Rotation angle calculation
150: Merge images
200: system 210: camera
220: distance sensor 230: processor
240: Monitor

Claims (13)

The monitoring system capturing a plurality of different images by photographing the ground while the container truck is moving using a plurality of cameras disposed on the container truck;
Creating an image of a road through which the container truck passes by matching the plurality of different images;
Measuring a distance to a front portion of a container connected to the container truck using a pair of distance sensors disposed on a rear surface of the container truck;
Calculating a rotation angle of the container truck based on a result of measuring the distance; And
Merging an image of the container truck reflecting the rotation angle on an image of the road and outputting the merged image to a screen,
The monitoring system transmits an operation signal to a camera which is in a sleep state on the rear surface of the container truck when the rotation angle exceeds a threshold value, captures a blind spot between the cameras, A further method for monitoring real time container trucks is to match. 2. The method of claim 1,
And arranging the plurality of cameras on the front, back, and sides of the container truck to acquire different images from the cameras. 2. The method of claim 1, wherein generating the image of the road comprises:
And generating an image of the road by correcting a coordinate axis of each of the plurality of different images and a position of the plurality of cameras. 4. The method of claim 3, wherein generating the image of the road further comprises:
And generating an image of the road by matching outlines of roads included in each of the plurality of different images. The method according to claim 1,
And generating an alarm when the container truck violates a boundary of the road. 2. The method of claim 1, wherein measuring the distance comprises:
And measuring the left and right distances of the front portion of the container using the pair of distance sensors disposed to the left and right with respect to the center axis of the container truck. delete A plurality of cameras disposed on the container truck and capturing a plurality of different images by photographing the ground on which the container truck is moving;
A pair of distance sensors disposed on a rear surface of the container truck for measuring a distance to a front portion of a container connected to the container truck;
Receiving the different images from the plurality of cameras and matching them to one image, generating an image of a road passing through the container truck based on the registered images, measuring the front part of the container from the pair of distance sensors A processor for receiving a distance value to calculate a rotation angle of the container truck and to merge an image of the container truck reflecting the rotation angle on the image of the road; And
And a monitor for outputting the merged image,
The processor transmits an operation signal to a camera whose back surface of the container truck is in a sleep state when the rotation angle exceeds a threshold value, captures a blind spot between cameras, and generates a photographed image of the road Further matching real-time container truck monitoring system. 9. The method of claim 8,
Wherein the plurality of cameras are disposed on the front, back, and sides of the container truck to obtain different images for each of the container trucks being moved. 9. The method of claim 8,
Wherein the processor generates an image of the road by correcting angles and directions of the different images based on coordinate axes of the plurality of different images and locations of the plurality of cameras stored in advance. 11. The method of claim 10,
Wherein the processor is configured to match an outline of a road included in each of the plurality of different images to generate an image of the road. 9. The method of claim 8,
Wherein the processor transmits an operation signal to an alarm pre-installed in the vehicle when the container truck violates the boundary of the road. 9. The method of claim 8,
Wherein the pair of distance sensing sensors are disposed to the left and right with respect to the center axis of the container truck and measure the distance between the left and right sides of the front portion of the container and transmit the distance value to the processor.

Images