Geospatial imaging technique has opened a door for researchers to implement multiple beneficial applications in many fields, including military investigation, disaster relief, and urban traffic control. As the resolution of geospatial images has increased in recent years, the detection of geospatial objects has attracted a lot of researchers. Mask R-CNN had been designed to identify an object outlines at the pixel level (instance segmentation), and for object detection in natural images. This study describes the Mask R-CNN model and uses it to detect objects in geospatial images. This experiment was prepared an existing dataset to be suitable with object segmentation, and it shows that Mask R-CNN also has the ability to be used in geospatial object detection and it introduces good results to extract the ten classes dataset of Seg-VHR-10.

Visual SLAM (Simultaneous Localization and Mapping) is widely used in autonomous robots and vehicles for autonomous navigation. Trajectory estimation is one part of Visual SLAM. Trajectory estimation is needed to estimate camera position in order to align the real image locations. In this paper, we present a new framework for trajectory estimation aided by Monocular Visual Odometry. Our proposed method combines the feature points extracting and matching based on ORB (Oriented FAST and Rotated BRIEF) and PnP (Perspective-n-Point). Thus, it was used a Matlab® dynamic model and an OpenCV/C++   computer graphics platform to perform a very robust monocular Visual Odometry mechanism for trajectory estimation in outdoor environments. Our proposed method displays that meaningful depth estimation can be extracted and frame-to-frame image rotations can be successfully estimated and can be translated in large view even texture-less. The best key-points has been extracted from ORB key point detectors depend on their key-point response value. These extracted key points are used to decrease trajectory estimation errors. Finally, the robustness and high performance of our proposed method were verified on image sequences from public KITTI dataset.