Hardware in machine vision systems

A complete machine vision system design is mainly divided into software design and hardware design, of which the hardware of the machine vision system is mainly composed of the following parts:

1. Industrial computer

The industrial computer can be understood as a PC host, but this host is stronger in image acquisition and processing and related controls and interfaces. In the machine vision system, the performance of the industrial computer directly affects the processing speed and running time of the entire vision system, which is the key of the entire vision system. The choice of industrial computer needs to be considered from the following four aspects:

1) Size

2) Installation method

3) Configuration

------ Select an appropriate configuration based on your application scenario.

4) Interface

------- It is important to determine the number of cameras in the vision system, the light source controller and the connection method. If the system has 8 cameras, 4 light sources need to be controlled, the camera is connected through the network cable, the light source controller is 232 interface, so you can determine the network interface of the industrial computer, the number of serial ports.

2. Camera

2.1 Camera Type

Lattice camera/area camera

Area array camera: achieves pixel matrix shooting. In the image taken by the camera, the detail of the image is not determined by the number of pixels, but by the resolution. Resolution is determined by the focal length of the selected lens, the same camera, the selection of different focal lengths of the lens, the resolution is different. The number of pixels does not determine the resolution (sharpness) of the image, so what are the benefits of a large pixel camera? There is only one answer: reduce the number of shots and improve the test speed.

Line array camera: As the name suggests, it is in a "line" shape. It's also a two-dimensional image, but it's extremely long. A few kilobytes in length, but only a few pixels wide. Generally, this camera is only used in two cases: first, the measured field of view is a slender band, which is mostly used for detection problems on the drum.

Two, need a great field of view or very high precision. In the second case (which requires a very large field of view or very high accuracy), the camera needs to be activated several times with the excitation device, take many pictures, and then combine the multiple "bar" images taken into a large picture.

Therefore, with a line array camera, you must use a capture card that can support line array cameras. Line formation camera is expensive, and in the case of large field of view or high precision detection, its detection speed is slow - the general camera image is 400K ~ 1M, and the combined image has several M so large, the speed is naturally slow. Slow work makes good work. For these two reasons, linear array cameras are only used in very special cases.

CCD camera /CMOS camera

CCD cameras can provide good image quality, noise resistance, although due to the addition of external circuits to make the size of the system larger, the reproduction of improved, but in the circuit designer can be more flexible, better to improve the CCD camera some special attention to performance. CCD is more suitable for the camera performance requirements are very high and the cost control is not too strict in the application field, such as astronomy, high-definition medical X-ray images, other need long exposure, image noise requirements more stringent applications.

CMOS camera has the advantages of high yield, high integration, low power consumption and low price. But the image itself has more noise. The current CMOS technology continues to develop, has overcome many of the early shortcomings, and has developed to the level of image quality can compete with CCD technology.

CMOS is suitable for applications requiring small space, small size, low power consumption, and not particularly high image noise and quality requirements. For example, most industrial inspection applications of auxiliary light lighting, security and security applications, and most consumer commercial digital cameras. At present, CCD industrial cameras still occupy a dominant position in visual inspection schemes.

2.2 Resolution

The number of pixels of each image acquired by the camera generally corresponds to the number of pixels arranged on the target surface of the photoelectric sensor. The choice of resolution also needs to be determined according to the use scenario and accuracy requirements, not the higher the better.

2.3-pixel depth

The number of bits of data per pixel, commonly 8bit, 10bit, 12bit. Resolution and pixel depth together determine the size of the image. For example, for 5 million pixels with a pixel depth of 8bit, the whole picture should be 5 million *8/1024/1024=37M(1024Byte=1KB, 1024KB=1M). Increasing the pixel depth can improve the accuracy of the measurement, but it also reduces the speed of the system and increases the difficulty of system integration (more cables, larger size, etc.).

2.4 Frame rate

The speed at which the camera captures and transmits images is generally the number of Frames per second (Sec) for the planar array camera and the number of lines per second (HZ) for the linear array camera. The selection of frame rate needs to consider the shooting of dynamic scenes.

2.5 Exposure

Industrial linear array cameras are line by line exposure mode, you can choose a fixed line frequency and external trigger synchronization, exposure time can be consistent with the line cycle, you can also set a fixed time; Surface array cameras have several common ways of frame exposure, field exposure and rolling exposure, industrial digital cameras generally provide the function of external trigger sampling, the shutter speed is generally up to 10ms, and high-speed cameras will be faster.

2.6 Noise

Noise refers to the signal outside the actual imaging target that is not wanted to be collected during the imaging process. Generally, there are two categories: one is the shot noise caused by the effective signal, which exists for any camera; The other is the signal independent noise inherent in the camera itself. It is due to the inherent noise caused by the image sensor readout circuit, camera signal processing and amplification circuit, and the inherent noise of each camera is different.

2.7 Developing Interfaces

For the development of visual projects using the camera, the control of the camera (taking photos, videography, saving, setting parameters, etc.) is essential, generally manufacturers will provide control Demo, the development needs to apply the control function to our project.

3. Lens

The camera and the lens are generally matched, the selection of the lens mainly considers the visual distance of the image, the lens selection steps:

1) Calculate the number of pixels corresponding to the short side E=B/C, and the number of pixels of the long side and the short side of the camera should be greater than E;

2) Pixel size = product short side size B/ Number of short side pixels of the selected camera

3) Magnification = the selected camera chip short film size/field of view on the short side of the camera

4) Discernible product accuracy = pixel size/magnification (determine whether it is less than C)

5) Focal length of objective lens = working distance /(1+1/ magnification) Unit: mm

6) The resolution of the image surface should be greater than 1/(2×0.1× magnification) Unit: lp/mm

The selected lens support CCD size should be greater than or equal to the size of the camera CCD sensor chip, and the mounting base is C, CS or F interface should also be matched, while considering the working distance of the lens, whether there is enough space. If you are still unsure about the choice of lens, you can consult the technical support of the manufacturer, so that the manufacturer can recommend the right lens according to your application scenario.

4. Light Source

If you simply increase the exposure time of the camera, it will increase the noise of the image and reduce the quality of the image. It is necessary to choose the appropriate light source. The selection of light source is divided into two parts: light source lamp and light source controller.

4.1 Light Source Lamp

The light source provided by machine vision is also very rich, this is because the vision industry is very widely used, and the right light source needs to be selected according to the specific project to achieve the ideal effect.

Common light source lamp types are as follows, which can be selected according to specific projects.

4.2 Light Source Controller

The light source controller is to provide lighting for the test environment, and generally provides a development interface to control the specified output port to light up and turn off, mainly to cooperate with the camera to provide the software with the required images.

5. Physical environment

The machine vision system has relatively high requirements for the test environment, involving camera, light source, location of the target to be tested and other issues, and the principle is to provide a set of stable and high-quality images. The test environment may also need to be designed by professional institutions, if it is a simple environment for experiments, you can buy experimental supports online.