Real Time Object Tracking in a Video Sequence Using a Fixed Point DSP

Real-time object detection and tracking

“…• Compute correspondence of similar pixels between the two frames using correlation. In this method first consecutive difference images are formed by differencing consecutive frames of a video [13]. Then for each pixel in these difference images, the pixels in its local surrounding, of some size, are replaced either by bit 1 if they are greater than this pixel or by 0 if otherwise and in this way a bit-string, called signature vector, is generated in for each pixel [12], [13].…”

“…This is shown in Figure 3. Then separate lists for each image are generated which contain signature vectors for all pixels with the corresponding pixel positions [12], [13] This algorithm is immune to noise and illumination changes because the value of any pixel depends upon the values of the surrounding pixels and change in one pixel does not affect the output much. Furthermore, it consumes lesser time and is faster and more accurate than the previous algorithm but still, it is not suitable for hardware implementation in mobile robots.…”

Towards the Optimal Hardware Architecture for Computer Vision

“…These operations were related mainly with low-level image processing (Baumgartner et al, 2009), where parallelism and data access enable a large performance increase. Stereo vision (Lin & Chiu, 2008), Fourier transform (Sun & Yu, 2009) or video matching and tracking (Shah et al, 2008) are some samples. However, higher level algorithms also suit for DSPs, specially in industrial tasks (Suzuki et al, 2007) (Neri et al, 2005).…”