Resource Efficient Mountainous Skyline Extraction using Shallow Learning

  title={Resource Efficient Mountainous Skyline Extraction using Shallow Learning},
  author={Touqeer Ahmad and Ebrahim Emami and Martin Cad{\'i}k and George Bebis},
  journal={2021 International Joint Conference on Neural Networks (IJCNN)},
Skyline plays a pivotal role in mountainous visual geo-localization and localization/navigation of planetary rovers/UAVs and virtual/augmented reality applications. We present a novel mountainous skyline detection approach where we adapt a shallow learning approach to learn a set of filters to discriminate between edges belonging to sky-mountain boundary and others coming from different regions. Unlike earlier approaches, which either rely on extraction of explicit feature descriptors and their… Expand

Figures and Tables from this paper


A Deeply-Supervised Deconvolutional Network for Horizon Line Detection
A novel approach for skyline detection is introduced, which adheres to a learning-based paradigm and exploits the representation power of deep architectures to improve the horizon line detection accuracy. Expand
Comparison of semantic segmentation approaches for horizon/sky line detection
This paper provides a quantitative comparison of four recently proposed segmentation methods for autonomous horizon/sky line detection on an extensive data set and reports average accuracy and average absolute pixel error for each of the presented formulation. Expand
Skyline localization for mountain images
A novel method for automatically locating the skyline that represents the shape of mountains by linking of incomplete fragments of skyline is formulated as a shortest path problem and solved by dynamic programming strategy. Expand
Sky Segmentation Approach to obstacle avoidance
The main contribution of this article is the presentation of a feasible approach to obstacle avoidance based on the segmentation of camera images into sky and non-sky regions, named the Sky Segmentation Approach (SSA). Expand
Large Scale Visual Geo-Localization of Images in Mountainous Terrain
This work targets mountainous terrain and uses digital elevation models to extract representations for fast visual database lookup and validate the system on the scale of a whole country Switzerland, 40 000km2 using a new dataset of more than 200 landscape query pictures with ground truth. Expand
Automatic photo-to-terrain alignment for the annotation of mountain pictures
A novel automatic technique is proposed to avoid the burden of manual registration of a given photograph with a 3D geo-referenced terrain model, able to automatically derive the pose of the camera relative to the geometric terrain model. Expand
Robust Horizon Detection Using Segmentation for UAV Applications
A fast and robust technique for precise detection of the horizon path based on existence of a unique light field that occurs in imagery where the horizon is viewed, which is shown to have robust performance and accuracy, speed, and extraction of the path as curves are shown. Expand
A Machine Learning Approach to Horizon Line Detection Using Local Features
This paper proposes a machine learning approach for horizon line detection using edge images and local features i.e., SIFT and uses the SVM classifier to fill in small gaps in the horizon line; this is in contrast to the traditional dynamic programming approach which relies on mere interpolation. Expand
Image Based Geo-localization in the Alps
This work targets mountainous terrain and uses digital elevation models to extract representations for fast visual database lookup and proposes an automated approach for very large scale visual localization that can efficiently exploit visual information and geometric constraints at the same time. Expand
GeoPose3K: Mountain landscape dataset for camera pose estimation in outdoor environments
Several novel future use-cases of the new GeoPose3K dataset are proposed, which contains over three thousand precise camera poses of mountain landscape images for training and evaluation of computer vision methods and applications in the context of outdoor scenes. Expand