Design and validation of a low resource-cost video data processing method for embedded implementation of optical flow extraction

The main goal of the proposed project is to build real-time hardware implementations of Optical Flow methods for tasks like egomotion estimation and/or obstacle avoidance. The current paper presents the theoretical foundations and the development and adaptation of appropriate algorithms needed for the motion detection task and the selection of the most suitable hardware/software design environments that aids the embedded implementation process. Using proper hardware/software co-design techniques, we present the development of a low-power, low resource-cost video data processing algorithm. The developed hardware efficient Optical flow extraction method is validated via software implementation and tested with standard video sequence inputs. We than present the architecture of the same method on an embedded, FPGA-based platform.