Feature: Machine vision
Figure 4. A cylindrical projection algorithm
Tis resulted in a more complete output image formation and artefacts were removed; see Figure 6. 3. Noise generated by overlapping points Because of the cylindrical projection algorithm, many points on the overlapping region end up getting the same resting coordinates on the 2D projected output. Tis creates noise as the background pixels overlap those in the foreground. To fix this problem, the radial distance of each point is compared with an existing point, with the point being replaced only if the distance from the camera origin is smaller than the existing point, improving projection quality; see Figure 7.
Suitable for edge computing systems Tis algorithm can stitch images from different cameras with less than 5° of overlap compared to a minimum of 20° of overlap as needed
Figure 5. Issues with 2D projection
2. Filling unmapped pixels While projecting the 3D point cloud onto a 2D plane, there are unmapped/unfilled regions in the 2D image. Many point cloud (3D) pixels get mapped to the same 2D pixel, thus several 2D pixels remain blank, resulting in a stretch pattern as shown in Figure 6. To fix this, a 3 × 3 filter was used that fills the unmapped pixels with the average IR/ depth value of its neighbouring 8 pixels that have valid values.
Table 1. Traditional algorithms vs. proposed algorithm for a 512 × 512 QMP input, as computational complexity comparison
Figure 6. Filling unmapped pixels 20 July/August 2025
www.electronicsworld.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44
