Abstract
Camera position and attitude estimation is an important part of SLAM (Simultaneous Locolization and Mapping), which is directly related to the accuracy and efficiency of SLAM. The traditional SLAM algorithm for camera pose estimation is based on feature points. However, when the environmental brightness and contrast change too much, there will be many feature points matching errors and the camera pose estimation is not accurate. In order to solve the above problems, the feature contour is extracted before the traditional algorithm. Therefore, An improved SLAM algorithm based on feature contour extraction for camera pose estimation is proposed. Experimental results show that the degree of error between the camera pose estimation result based on the improved algorithm and the actual result fluctuates between 0.1-2 degrees. Compared with the traditional algorithm, the error degree and the error fluctuation range are small. The improved algorithm has higher accuracy of pose estimation than traditional algorithms.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
