Sun, WeiWadud, Rushmian2021-12-172021-12-172021https://hdl.handle.net/11244/332396Simultaneous Localization & Mapping (SLAM) is considered as the process of building a mutual relationship between localization and mapping of the subject in its surrounding environment. With the help of different sensors, different types of SLAM systems have been developed to simplify the problem of building the relationship between localization and mapping. A limitation in the SLAM process is to consider dynamic objects into calculation of mapping the environment, which is computationally heavier. Dynamic objects have not been taken into consideration while building a SLAM system until recently. The proposed system, DyOb-SLAM, is a Visual SLAM system which can produce an output considering dynamic objects in the environment. With the help of a neural network and a dense optical flow algorithm, dynamic objects and static objects in an environment can be differentiated. DyOb-SLAM creates two separate maps, for both static and dynamic contents. For the static features, a sparse map is obtained. For the dynamic contents, a trajectory global map is created as output. As a result, a frame to frame real-time based dynamic object tracking system is obtained. Through the pose calculation of the dynamic objects and the camera, DyOb-SLAM can estimate the speed of the dynamic objects with time. The performance of DyOb-SLAM is observed by comparing it with a similar Visual SLAM system, VDO-SLAM and the performance is measured by calculating the camera and object pose errors as well as the object speed error. In the following chapters, the entire SLAM system along with some details of its predecessors are explained.Computer Vision, Robotics, SLAM, Object Detection, Cloud Computing