This gives the following calculation:Ĭalculation for European plates in cm: 200 × 2.7 ÷ 1 = 540 pixelsĬalculation for US plates in inches: 78 × 2.7 ÷ 0.27 = 780 pixelsīecause US plates use a font with a narrow stroke, a higher resolution is needed than for European plates. If the lens has barrel distortion it is best to look up the HFOV in the specification sheet. If the field of view is not known, it can be calculated for a rectilinear lens using the equation in Table 5. Example 2: My FOV is 500mmX600mm and my smallest feature is 2mm. A camera with a resolution of 640x480 will work because 200 is less than the smallest dimension which is 480. Following the equation, the needed minimum sensor resolution is 200 pixel. The recommended resolution of the stroke thickness is 2.7 pixels/stroke, and the physical stroke thickness is 1 cm for a European plate and 0.27 inches for a US plate. Given a lens and camera, it is possible to calculate the image resolution by using the simple equations below. Calculate sensor resolution: Example 1: My FOV is 100mm and my smallest feature is 1mm. You can also do a physical measuring of the area of interest if you need to know the exact width. We estimate that the horizontal width is 200 cm/78 inches, as we assume the width of a standard car is 177 cm/70 inches, and besides that we add ~10% for the extra space. The calculation is based on the width of a car. In this example we explain how to do a simple image quality calculation and find a suitable resolution for LPR. The lower you can set the acceptable resolution, the better CPU-performance and the higher detection rate you get. On the other hand, if the video resolution is too high, the CPU might be overloaded with the risk of skipped or faulty detections. Image quality and resolution is important for a successful license plate recognition. This page is not yet available in your language.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |