To address the problem that the RANdom SAmple Consensus (RANSAC) algorithm in the ORB-SLAM2 system has a low efficiency due to the randomness of the algorithm when eliminating mismatches and fails to build dense point cloud map in ORB-SLAM2 system, a PROgressive SAmple Consensus (PROSAC) algorithm was adopted to improve the mismatch elimination in the ORB-SLAM2 system and the dense point cloud map and the octree map building threads were added in this system. Firstly, compared with RANSAC algorithm, in PROSAC algorithm, the feature points were preordered according to the evaluation function, and the feature points with high evaluation quality were selected to solve the homography matrix. According to the solution of the homography matrix and the matching error threshold, the mismatches were eliminated. Secondly, the pose estimation and relocation of the camera were carried out according to the ORB-SLAM2 system. Finally, the dense point cloud map and the octree map were constructed according to the selected key frames. According to the experimental results on TUM dataset, PROSAC algorithm took about 50% time to perform the mismatch elimination of the same images compared to RANSAC algorithm, and the proposed system had the absolute trajectory error and relative pose error basically consistent with the ORB-SLAM2 system, showing good robustness. Besides, compared with the sparse point cloud map, the proposed new maps could be directly used for robot navigation and path planning.

To address the problem that dynamic objects affect pose estimation in indoor Simultaneous Localization And Mapping (SLAM) systems, a semantic segmentation based SLAM system in dynamic scenes was proposed. Firstly, an image was semantically segmented by the Pyramid Scene Parsing Network (PSPNet) after being captured by the camera. Then image feature points were extracted, feature points distributed in the dynamic object were removed, and camera pose was estimated by using static feature points. Finally, the semantic point cloud map and semantic octree map were constructed. Results of multiple comparison tests on five dynamic sequences of public datasets show that compared with the SLAM system using SegNet network, the proposed system has the standard deviation of absolute trajectory error improved by 6.9%-89.8%, and has the standard deviation of translation and rotation drift improved by 73.61% and 72.90% respectively in the best case in high dynamic scenes. The results show that the improved method can significantly reduce the error of pose estimation in dynamic scenes, and can correctly estimate the camera pose in dynamic scenes.

To enhance the weak edges and textures and to avoid the staircase effect, an image enlargement method was proposed which coupled anisotropic forth-order partial differential equation to second-order partial differential equation. In the method, the weak edges and textures were enhanced and staircase was reduced by improved anisotropic forth-order partial differential equation with adaptive diffusion coefficient to threshold value constrained by pixel's local variance, improved total variance and adaptive amplitude shock filters controlled by gradient were coupled with the forth-order differential equation to enhance the edges, and the bi-orthogonal projection was used to realize the constraint of the degradation model. Simulation experiment results validate the proposed method on enhancing the edges, details and textures and reducing staircases. Compared with other existing second-order PDE-based zoom methods, the zoomed images using the proposed method have better visual effect and higher Peak Signal-to-Noise Ratio (PSNR) and Mean Structural Similarity Measure (MSSIM), for example, PSNR of zoomed image with larger smooth part by the proposed method is about 0.1 dB higher than that by improved Total Variance (TV) enlargement method and PSNR of zoomed image with larger weak edges and textures by the proposed method is above 0.5 dB higher than that by improved TV enlargement method. Therefore, the zoomed image of the method looks more natural, and the resolution of the weak edges and textures of the image are enhanced better.