No abstract

Estimating the depth of image and egomotion of agent are important for autonomous and robot in understanding the surrounding environment and avoiding collision. Most existing unsupervised methods estimate depth and camera egomotion by minimizing photometric error between adjacent frames. However, the photometric consistency sometimes does not meet the real situation, such as brightness change, moving objects and occlusion. To reduce the influence of brightness change, we propose a feature pyramid matching loss (FPML) which captures the trainable feature error between a current and the adjacent frames and therefore it is more robust than photometric error. In addition, we propose the occlusion-aware mask (OAM) network which can indicate occlusion according to change of masks to improve estimation accuracy of depth and camera pose. The experimental results verify that the proposed unsupervised approach is highly competitive against the state-of-the-art methods, both qualitatively and quantitatively. Specifically, our method reduces absolute relative error (Abs Rel) by 0.017–0.088.

In this study, we propose an accurate and efficient algorithm for extrinsic camera calibration that utilizes an accumulator on the sphere and the orthogonal constraint of vanishing points. We develop a nonuniform subdivision method to create an accurate accumulator for validating rotation matrix hypotheses. In contrast with the multiline method for generating rotation matrix hypotheses, we utilize the parallelism and orthogonality of two lines to develop hypotheses in the spherical coordinate. Moreover, we expand our method to the scene that lacks orthogonal information. Our method achieves 99.36% precision and 99.92% recall on the York Urban Database, and it is successfully applied to real-world scenes.

No abstract

No abstract