Abstract
In this paper, we propose three sets of multi-channel image patch features for monocular visual-IMU (Inertial Measurement Unit) odometry. The proposed feature sets extract image patch exemplars from multiple feature maps of an image. We also modify an existing visual-IMU odometry framework by using different salient point detectors and feature sets and replacing the inlier selection approach with a self-adaptive scheme. The modified framework is used to examine the proposed feature sets. In addition to the Root Mean Square Error (RMSE) metric, we use the Hausdorff distance to measure the inconsistency between the estimated and ground-truth trajectories. Compared to the point-wise comparison used by RMSE, the Hausdorff distance takes the shape inconsistency of two trajectories into account and is hence more perceptually consistent. Experimental results show that the multi-channel feature sets outperform, or perform comparably to, the single gray level channel feature sets examined in this study. Particularly, the multi-channel feature set that uses integral channels, i.e., ICIMGP (Integral Channel Image Patches), outperforms two state-of-the-art feature sets: SIFT (Scale Invariant Feature Transform) and SURF (Speed Up Robust Features). Besides, ICIMGP performs better than the two multi-channel feature sets that are designed based on derivative channels and gradient channels respectively. These promising results are attributed to the fact that the multi-channel features encode richer image characteristics than their single gray level channel counterparts.
Highlights
Accurate and reliable ego-motion estimation in dynamic and unknown surroundings plays an important role in the autonomous robot navigation and localization tasks
We investigated the effect of the size of image patches on the best multi-channel feature set obtained in the first experiment
It can be seen that: (1) Inertial Measure Unit (IMU) often suffers the error accumulation issue when the path is long and complicated. It performs properly when the path is straight and the speed is high. This should be attributed to the fact that IMU is suitable for the case of the high speed, linear motion; (2) the combination of monocular camera and IMU can reduce the drift issue; (3) the three multi-channel feature sets perform better than the gray level image patch feature set, and outperform, or perform comparably to, Scale Invariant Feature Transform (SIFT) [24] and Speed Up Robust Features (SURF) [2]; (4) the multi-channel feature set using integral channels, i.e., integral channel image patch (ICIMGP), outperforms all its counterparts tested in this experiment regardless of whether the experiment is conducted in the residential area or on the highway; (5) no matter which performance measure is used, the performance of all the methods obtained on different paths are similar
Summary
Accurate and reliable ego-motion estimation in dynamic and unknown surroundings plays an important role in the autonomous robot navigation and localization tasks. The motion trajectory of cameras is normally estimated by tracking the matched (feature) points between consecutive image frames. Cameras are able to successfully track features at low velocities. The IMU has large measurement uncertainty at low-speed motion, it is able to capture high velocities and accelerations promptly. This characteristic makes cameras be complementary to the IMU system [7]. The vison-aided inertial navigation system is able to achieve better performance than the pure IMU system
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
