Abstract
Simultaneous localization and mapping (SLAM) has a wide range for applications in mobile robotics. Lightweight and inexpensive vision sensors have been widely used for localization in GPS-denied or weak GPS environments. Mobile robots not only estimate their pose, but also correct their position according to the environment, so a proper mathematical model is required to obtain the state of robots in their circumstances. Usually, filter-based SLAM/VO regards the model as a Gaussian distribution in the mapping thread, which deals with the complicated relationship between mean and covariance. The covariance in SLAM or VO represents the uncertainty of map points. Therefore, the methods, such as probability theory and information theory play a significant role in estimating the uncertainty. In this paper, we combine information theory with classical visual odometry (SVO) and take Jensen-Shannon divergence (JS divergence) instead of Kullback-Leibler divergence (KL divergence) to estimate the uncertainty of depth. A more suitable methodology for SVO is that explores to improve the accuracy and robustness of mobile devices in unknown environments. Meanwhile, this paper aims to efficiently utilize small portability for location and provide a priori knowledge of the latter application scenario. Therefore, combined with SVO, JS divergence is implemented, which has been realized. It not only has the property of accurate distinction of outliers, but also converges the inliers quickly. Simultaneously, the results show, under the same computational simulation, that SVO combined with JS divergence can more accurately locate its state in the environment than the combination with KL divergence.
Highlights
As computer technology rapidly grows, multimedia applications have penetrated into almost every aspect of our daily life
semi-direct visual odometry (SVO) is integrated with a probabilistic mapping method, which is robust to outlier measurements, so it can achieve real-time performance on a low-cost computing platform, like microaerial vehicle (MAV)
The systemic performance was evaluated by using the TUM RGB-D and EUROC MAV
Summary
As computer technology rapidly grows, multimedia applications have penetrated into almost every aspect of our daily life. SVO is integrated with a probabilistic mapping method, which is robust to outlier measurements, so it can achieve real-time performance on a low-cost computing platform, like MAVs. the target platform for application is the top-view camera on a MAV. The hybrid system SVO [22] extracts FAST features and makes use of a direct method to track features and any pixel with non-zero intensity gradient, which optimizes camera pose through reprojection errors. In the scene structure analysis of structure-SLAM [25], the author uses cross-entropy to predict the normal of the plane, which reduces the rate of mismatching to a certain extent It consumes a lot of resources when removing outliers, which leads to poor real-time performance. This paper takes MAV and camera as the test platform and SVO as the improved algorithm We named it IT-SVO, which stands for semi-direct visual odometry combined with information theory.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
