Robustness and non-monotonic performance of deep feature-based VIO under low-frequency sampling
TL;DR
A tightly-coupled stereo VIO system driven by deep features is constructed, utilizing the SuperPoint network to extract semantic features, paired with a brute-force descriptor matching strategy for large-parallax scenarios, offering a fresh theoretical perspective for designing robot navigation systems in resource-constrained environments.
Abstract
Traditional VIO suffers from optical flow tracking failures and severe localization drift at low frequencies, primarily due to large disparities between consecutive frames. To resolve this issue, a tightly-coupled stereo VIO system driven by deep features was constructed. Instead of a conventional optical flow front-end, the SuperPoint network is utilized to extract semantic features, paired with a brute-force descriptor matching strategy for large-parallax scenarios. Systematic down-sampling simulations (from 20Hz to 1Hz) were performed on the EuRoC dataset. The quantitative results indicate that even at an extreme 1Hz frequency, the proposed system maintains a complete trajectory estimate, demonstrating remarkable survivability. Furthermore, a non-monotonic performance trend was observed. At a 2Hz sampling rate, the strong geometric constraints provided by the wide baseline effectively mitigated IMU integration drift. Consequently, the localization accuracy (RMSE of 0.21m) outperformed the 5Hz midfrequency range and even surpassed the 20Hz baseline. This finding challenges the conventional assumption that higher frequencies inherently yield better accuracy, offering a fresh theoretical perspective for designing robot navigation systems in resource-constrained environments.