Improving Depth Estimation using Location Information

Abstract

The ability to accurately estimate depth information is crucial for many autonomous applications to recognize the surrounded environment and predict the depth of important objects. One of the most recently used techniques is monocular depth estimation where the depth map is inferred from a single image. This paper improves the self-supervised deep learning techniques to perform accurate generalized monocular depth estimation. The main idea is to train the deep model to take into account a sequence of the different frames, each frame is geotagged with its location information. This makes the model able to enhance depth estimation given area semantics. We demonstrate the effectiveness of our model to improve depth estimation results. The model is trained in a realistic environment and the results show improvements in the depth map after adding the location data to the model training phase.

References in corpus (10)

• ORB-SLAM: a Versatile and Accurate Monocular SLAM System
• Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• Depth Extraction from Video Using Non-parametric Sampling
• What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
• Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
• DeepLoc: A Ubiquitous Accurate and Low-Overhead Outdoor Cellular Localization System
• The Tale of Two Localization Technologies: Enabling Accurate Low-Overhead WiFi-based Localization for Low-end Phones
• DynamicSLAM: Leveraging Human Anchors for Ubiquitous Low-Overhead Indoor Localization
• Size-to-depth: A New Perspective for Single Image Depth Estimation