DNN-based self-attitude estimation by learning landscape information

Abstract

This paper presents DNN (deep neural network) - based self-attitude estimation by learning landscape information. The network predicts the gravity vector in the camera frame. The input of the network is a camera image, the outputs are a mean vector and a covariance matrix of the gravity. It is trained and validated with a dataset of images and correspond gravity vectors. The dataset is collected in a simulator. Using a simulator breaks the limitation of amount of collecting data with ground truth. The validation showed the network can predict the gravity vector from only a single shot image. It also showed the covariance matrix expresses the uncertainty of the prediction.