Real-Time Stereo Vision Techniques

This PhD aims at the design and implementation of real-time hardware-based stereo vision systems. Stereo vision deals with images acquired by a stereo camera setup, where the disparity between the stereo images allows depth estimation within a scene. In the first part of my research a new hardwareefficient real time disparity map computation module was developed which involved a fully parallel-pipelined design, for the overall module, realized on a single FPGA device. The design technique was extended to include the hardware implementation of a fuzzy inference system (FIS), to deal more efficiently with the detection of conjugate pairs in stereo images, which is a challenging research problem known as the correspondence problem, i.e. to find for each point in the left image, the corresponding point in the right one. The performance of the hardware implemented design methodologies was evaluated against the state of the art methods to prove their efficiency.