IoTs Enable Active Contour Modeling Based Energy Efficient and Thermal Aware Object Tracking on FPGA

Abstract

Object tracking based on active contour modeling is an image processing related technology that uses snapshots of the object under consideration to track it via robot in the real world. Nowadays, the word is moving towards the internet of things (IoTs) and having significant effect on our daily life. In this work, we have designed IoTs enable power efficient and thermal aware frame buffer to store the frames and uses that frame to detect changes in object position. In order to make IoTs enable design, we are embedding a 128-bit IPv6 address into frame buffer. In order to test the compatibility of this design with wireless network, we are operating this design with different operating frequency of WLAN channel. The operating frequency of WLAN Channel 802.11ah, 802.11b/g/n, 802.11y, 802.11a/h/j/n/ac, 802.11p and 802.11d are 900 MHz, 2.4, 3.6, 5, 5.9 and 60 GHz respectively. There is no change in signal power, clock power, IO power, when we scale down ambient temperature from 70 to 30 °C. There are 98–89 % saving in signal power, 2–85 % reduction in clock power, 90–99 % saving in IO power with WLAN Channel 802.11ah, 802.11b/g/n, 802.11y, 802.11a/h/j/n/ac, 802.11p in compare to power dissipation with 802.11ad. There is 71.11, 72.60, 73.96, 74.28, and 74.42 % reduction in leakage power with WLAN Channel 802.11ah, 802.11b/g/n, 802.11y, 802.11a/h/j/n/ac, and 802.11p, when we scale down ambient temperature from 70 to 30 °C. IoTs enable frame buffer design can be controlled from any part of this globe. Another design characteristic of this frame buffer is that it is 3-D frame buffer which gives us an added advantage over 2-D frame buffer that store image only in X, Y orientation. Capability to analyze third dimension helps us to track object more efficiently.