Guo Ente, Chen Zhifeng, Zhou Yanlin, Wu Dapeng Oliver
College of Physics and Information Engineering, Fuzhou University, Fuzhou 350108, China.
Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL 32611, USA.
Sensors (Basel). 2021 Jan 30;21(3):923. doi: 10.3390/s21030923.
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.
估计图像深度和智能体的自我运动对于自主系统和机器人理解周围环境以及避免碰撞至关重要。大多数现有的无监督方法通过最小化相邻帧之间的光度误差来估计深度和相机自我运动。然而，光度一致性有时不符合实际情况，例如亮度变化、移动物体和遮挡。为了减少亮度变化的影响，我们提出了一种特征金字塔匹配损失（FPML），它捕捉当前帧和相邻帧之间的可训练特征误差，因此比光度误差更稳健。此外，我们提出了遮挡感知掩码（OAM）网络，它可以根据掩码的变化指示遮挡，以提高深度和相机姿态的估计精度。实验结果验证了所提出的无监督方法在定性和定量方面都与现有最先进方法具有高度竞争力。具体而言，我们的方法将绝对相对误差（Abs Rel）降低了0.017 - 0.088。
