CN111948214A - Device and method for classifying image pollution levels - Google Patents

Abstract

The invention relates to a device and a method for classifying image dirt grades. The method comprises the steps of shooting a dirty image by a camera in a dark box, graying the image, and classifying the dirty grade of the image according to the gray value. The invention provides the image pollution grade classification method and the image pollution grade classification equipment which are easy to operate and feasible, provides a feasible solution for domestic image pollution grade classification, and fills some blanks of domestic and foreign image pollution grade classification.

Description

A device and method for classifying image contamination levels

technical field

The present invention relates to the technical field of intelligent driving, and in particular, to a device and method for classifying image contamination levels.

Background technique

Intelligent driving cars need to install various sensors on the vehicle to perceive the surrounding environment. At present, almost all smart cars use cameras to perceive the surrounding environment. In the process of driving a smart car, the camera sensor collects surrounding information and transmits it to the car, and the smart car makes decisions based on this information. Therefore, in order to ensure the safety of the car, the information transmitted by the camera sensor to the car must be accurate.

However, in the process of driving, due to the uncertainty of the road, the cameras will be polluted to varying degrees, and there will be deviations between the road information collected by the polluted cameras and the actual road information, which may cause the wrong judgment of the smart car. Because it is necessary to study image smudge processing. Therefore, there must be a unified standard for classification of image contamination levels to be studied. In this way, it is convenient for researchers to conduct research, and after the classification of the level of dirt, the smart car can be told which level of dirt it is through the judgment of the subsequent algorithm, and the smart car will respond accordingly according to the level of dirt.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide an apparatus and method for classifying image contamination levels in order to overcome the above-mentioned defects in the prior art.

The object of the present invention can be realized through the following technical solutions:

A device for classifying image contamination levels, the device includes a camera obscura, a base for placing related devices and an LED light box for providing a stable light source to ensure that the light source for each photo is consistent, the base is provided with A first retractable bracket and a second retractable bracket are arranged thereon, a camera is arranged on the first retractable bracket, and a dirty image is arranged on the second retractable bracket.

Further, the camera obscura consists of a skeleton and a full shading cloth.

Further, the skeleton is made of aluminum profiles.

Further, the structure of the skeleton is a cubic structure.

Further, the top of the first retractable support is provided with a platform, and the camera is placed on the platform.

Further, the top of the second retractable support is provided with a retractable support platform, and a plurality of acrylic plates are arranged on the retractable support platform, and the dirty image is arranged on a surface formed by a plurality of the acrylic plates. within the space.

Further, both the first telescopic support and the second telescopic support adopt a two-section sleeve-rod type telescopic support.

Further, the camera is a single-lens reflex camera.

The present invention also provides a method for classifying image contamination levels using the device for classifying image contamination levels, the method specifically includes: opening the LED light box in the dark box, and adjusting the parameters of the camera , and after adjusting the relative positions of the camera and the dirty image through the first retractable bracket and the second retractable bracket, respectively, the dirty image is captured, and the grayscale of the captured image is The corresponding contamination level of the classified image is determined according to the grayscale value of the grayscaled image.

Further, the corresponding contamination levels of the image are divided into 256 levels in total.

Compared with the prior art, the present invention has the following advantages:

(1) To provide a simple, easy-to-operate, and highly operable image contamination level classification device, the device includes a camera obscura, a base is set in the obscura, and an LED light box is placed on the base to provide a controllable and stable light source, And there are also two retractable stands, one for the camera and one for dirty images. After adjusting the light source, the camera and the position of the dirty image, take a picture of the dirty image, convert the image to grayscale, and determine the dirty level of the image by the grayscale value of the dirty image.

(2) The skeleton of the camera obscura in the device of the present invention is constructed of aluminum profiles, and the cube is covered with a full shading cloth to form a dark room, avoiding the influence of sunlight, lights and other light sources and other incoherent factors.

(3) Based on the classification method proposed by the device of the present invention, according to the characteristics of image contamination and gray value. A feasible image contamination level classification standard and method are provided.

Description of drawings

1 is a schematic diagram of the overall structure of an apparatus for classifying image contamination levels according to the present invention;

2 is a side view of a soiled image placement platform in the apparatus for classifying image soiling levels according to the present invention;

In the figure, 1 is the camera obscura, 2 is the camera, 3 is the first retractable bracket, 4 is the base, 5 is the LED light box, 6 is the second retractable bracket, 7 is the first acrylic plate, 8 is the second acrylic plate, 9 is a retractable support platform.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Example

The present invention provides a device and method for classifying image contamination levels, the structure of which is shown in FIG. 1 . It includes a camera obscura 1, a base 4 arranged in the obscura 1, a first retractable bracket 3 and a second retractable bracket 6, one for placing the camera and the other for placing the dirty image.

The skeleton of the camera obscura 1 is constructed of aluminum profiles, and the cube is covered with a full shading cloth to form a dark room, which avoids the influence of sunlight, lights and other light sources and other incoherent factors. In addition, a base 4 is added to the camera obscura 1 for placing the first retractable bracket 3, the second retractable bracket 6 and the LED light box 5. The function of the light box is to provide a continuous and stable light source and keep the light source consistent for each photo.

The first telescopic support 3 and the second telescopic support 6 are of the two-section sleeve rod type. And the retractable sleeve rod is connected to a platform for placing things. The first retractable bracket 3 is used to place the camera, and the second retractable bracket 6 is used to place the dirty image. The design of the platform above the second telescopic support 6 is shown in FIG. 2 , and is composed of a telescopic support platform 9 and a first acrylic plate 7 and a second acrylic plate 8 fixed on it.

It has been verified by experiments that the gray value of the dirty images shot through the acrylic sheet and the directly shot dirty images are basically unchanged after grayscale. Between the first acrylic plate 7 and the second acrylic plate 8, it plays a fixed role.

The SLR camera used in Camera 2 in this example, the camera parameters use the factory default parameters.

After adjusting the parameters of the camera 2, the heights of the first retractable bracket 3, the second retractable bracket 6, and the LED light source 5, take a picture. Remove the captured image. Grayscale the captured dirty image, and obtain its grayscale value. Because the grayscale value of the image represents the black and white characteristics of the image, and the grayscale value ranges from 0 to 255, the grayscale value is used to represent its contamination level, and the image contamination level is divided into 256 levels. The 0 level represents the most dirty image, and the 255 level represents the cleanest image.

Therefore, in this example, after the gray value is obtained, the contamination level of the image is obtained.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalents within the technical scope disclosed by the present invention. Modifications or substitutions should be included within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (10)

1. The utility model provides a device for image dirt grade classification, its characterized in that, the device include camera bellows (1), be equipped with in camera bellows (1) and be used for placing base (4) of relevant device and be used for providing stable light source in order to ensure the unanimous LED lamp house (5) of light source of shooing at every turn, be equipped with first telescopic bracket (3) and second telescopic bracket (6) on base (4), be equipped with camera (2) on first telescopic bracket (3), be equipped with dirty image on second telescopic bracket (6).

2. The apparatus for image stain level classification as claimed in claim 1, wherein the dark box (1) is composed of a skeleton and a full-shading cloth.

3. The apparatus according to claim 2, wherein the frame is made of aluminum profile.

4. The apparatus according to claim 2, wherein the skeleton has a cubic structure.

5. An apparatus for image stain level classification as claimed in claim 1, wherein the top end of the first telescopic support (3) is provided with a platform on which the camera (2) is placed.

6. The apparatus according to claim 1, wherein the second telescopic bracket (6) is provided with a telescopic bracket platform (9) at the top end, a plurality of acrylic plates are arranged on the telescopic bracket platform (9), and the dirty image is arranged in a space formed by the acrylic plates.

7. The apparatus for image stain level classification as claimed in claim 1, wherein said first telescoping support (3) and said second telescoping support (6) are each two-bar telescoping supports.

8. The apparatus for image contamination level classification as claimed in claim 1, wherein the camera (2) is a single lens reflex camera.

9. An image contamination level classification method using the apparatus for image contamination level classification according to any one of claims 1 to 8, the method comprising: opening the LED lamp box (5) in the camera shelter (1), adjusting parameters of the camera (2), respectively adjusting the relative positions of the camera (2) and the dirty images through the first telescopic support (3) and the second telescopic support (6), shooting the dirty images, graying the shot images, and judging the corresponding dirty grade of the classified images according to the gray values of the grayed images.

10. The image contamination level classification method using the apparatus for image contamination level classification according to claim 9, wherein the corresponding contamination levels of the images are classified into 256 levels in total.

Images