Recently I've been reading some interesting papers on SLAM algorithm specifically using cameras. Some of these really broadened my mind. Some of interesting algorithm incluedes the most fundamental one, mono SLAM [1], and the recent one, ORB-SLAM [2]. I'm now studying these frameworks in my spare time and see if there's any possibility our framework can extends with image input.
Papers:
[1] Davison, Andrew J., et al. "MonoSLAM: Real-time single camera SLAM." IEEE Transactions on Pattern Analysis & Machine Intelligence 6 (2007): 1052-1067.
[2] Mur-Artal, Raul, Jose Maria Martinez Montiel, and Juan D. Tardos. "ORB-SLAM: a versatile and accurate monocular SLAM system." IEEE transactions on robotics 31.5 (2015): 1147-1163.