Abstract:
In response to the issue of excessive line segment extraction by traditional simultaneous localization and Mapping (SLAM) algorithms in dense environments, a SLAM algorithm that incorporates an enhanced integration of point and line features with a tightly coupled inertial measurement unit (IMU) was proposed, known as IPLI_SLAM. During the data preprocessing phase, Shi-Tomasi features were employed for point feature extraction, and tracking and matching were conducted using the Lucas−Kanade (LK) optical flow. Line features were introduced to improve the line segment detector (LSD) extraction algorithm based on pixel gradient filtering mechanism, filtering out areas with dense line features.By tightly coupling visual point and line information with IMU and adding it to the backend, the accuracy of the algorithm is improved. Finally, the IPLI−SLAM algorithm was tested and validated on the dataset EuRoc and in actual scenes.The results show that compared to the original LSD algorithm, the improved LSD algorithm reduces extraction and matching time by 8.2%; Compared with the VINS_mono and PL_vins algorithms, the IPLI−SLAM algorithm has improved positioning accuracy by 50.7% and 13.2%, respectively. In environments with fast motion speed and blurred scenes, the positioning accuracy has been improved by 55.6% and 25.1%, respectively; In actual multi texture scenes, the distance between the starting and ending points of the localization trajectory using our algorithm is smaller than that of the VINS_mono algorithm, which proves that our algorithm has higher stability and robustness on the basis of significantly improving localization accuracy.