In practical applications, how to achieve a perfect balance between high accuracy and computational efficiency can be the main challenge for simultaneous localization and mapping (SLAM). To solve this challenge, we propose SD-VIS, a novel fast and accurate semi-direct visual-inertial SLAM framework, which can estimate camera motion and structure of surrounding sparse scenes. In the initialization procedure, we align the pre-integrated IMU measurements and visual images and calibrate out the metric scale, initial velocity, gravity vector, and gyroscope bias by using multiple view geometry (MVG) theory based on the feature-based method. At the front-end, keyframes are tracked by feature-based method and used for back-end optimization and loop closure detection, while non-keyframes are utilized for fast-tracking by direct method. This strategy makes the system not only have the better real-time performance of direct method, but also have high accuracy and loop closing detection ability based on feature-based method. At the back-end, we propose a sliding window-based tightly-coupled optimization framework, which can get more accurate state estimation by minimizing the visual and IMU measurement errors. In order to limit the computational complexity, we adopt the marginalization strategy to fix the number of keyframes in the sliding window. Experimental evaluation on EuRoC dataset demonstrates the feasibility and superior real-time performance of SD-VIS. Compared with state-of-the-art SLAM systems, we can achieve a better balance between accuracy and speed.
Kanade-Lucas-Tomasi (KLT) optical flow algorithm based on the brightness constancy assumption is widely used in visual simultaneous localization and mapping (SLAM) and visual odometry (VO). However, the automatic adjustment of camera exposure time, the attenuation factor of sensor irradiance caused by vignetting, and the nonlinear camera response function will cause the same feature point to have different brightness values on different image frames, thus breaking this assumption. Hence, we propose a gain-adaptive KLT optical flow algorithm with online photometric calibration, and on this basis, design a monocular visual-inertial odometry which is insensitive to brightness changes. This method can calibrate the photometric parameters online in real time, meet the assumption of constant brightness in practical applications, and make the algorithm more robust and accurate in the case of dynamic changes in brightness. Experimental results on the TUM Mono and EuRoC datasets show that the proposed algorithm can reliably calibrate the photometric parameters of any video sequence and perform well in the environment with varying brightness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.