In this thesis, a framework based on open-source hardware is proposed and built to study the practicability of its use in indoor robotics research. Two Raspberry Pi camera modules are used as a range sensor for indoor robot triangulation in a static scene, which infers 3D information from 2D space using stereo vision. The local Block Matching method and Semi-Global matching method are implemented in dense disparity map estimations. 3D reconstructions are performed and binary 2D maps are generated. Previous work has paid attention to iterative methods to minimize the global energy function in solving matching problems. This thesis presents two vectorized methods that are suitable in stereo vision triangulation and acceptable for use in robotic applications. Results show that the depth estimation of both methods can be accurate to centimeters in between half a meter to four meters of range. Real-time implementation of these approaches has not been investigated.