Yilmaz, OzgurKarakus, Fatih2025-10-242025-10-2420161300-06321303-6203https://doi.org/10.3906/elk-1401-273https://search.trdizin.gov.tr/tr/yayin/detay/246154https://hdl.handle.net/20.500.12899/3844Robust and accurate 3D reconstruction of a scene is essential for many robotic and computer vision applications. Although recent studies propose accurate reconstruction algorithms, they are only suitable for indoor operation. We are proposing a system solution that can accurately reconstruct the scene both indoors and outdoors, in real time. The system utilizes both active and passive visual sensors in conjunction with peripheral hardware for communication and suggests an accuracy improvement in both reconstruction and pose estimation accuracy over state-of-the-art SLAM algorithms via stereo visual odometry integration. We also introduce the concept of multisession reconstruction, which is relevant for many real-world applications. In our solution to this concept, distinct regions in a scene can be reconstructed in detail in separate sessions using the KinectFusion framework and merged into a global scene using continuous visual odometry camera tracking.eninfo:eu-repo/semantics/openAccess3D reconstruction; SLAM; stereo; Kinect; visual odometry; iterative closest point; fusionArticle10.3906/elk-1401-273244275627702-s2.0-84974695652Q2246154WOS:000374325800052Q4