Abstract | ||
---|---|---|
Automatic skyline detection from mountain pictures is an important task in many applications, such as web image retrieval, augmented reality and autonomous robot navigation. Recent works addressing the problem of Horizon Line Detection (HLD) demonstrated that learning-based boundary detection techniques are more accurate than traditional filtering methods. In this paper we introduce a novel approach for skyline detection, which adheres to a learning-based paradigm and exploits the representation power of deep architectures to improve the horizon line detection accuracy. Differently from previous works, we explore a novel deconvolutional architecture, which introduces intermediate levels of supervision to support the learning process. Our experiments, conducted on a publicly available dataset, confirm that the proposed method outperforms previous learning-based HLD techniques by reducing the number of spurious edge pixels.
|
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2964284.2967198 | MM '16: ACM Multimedia Conference
Amsterdam
The Netherlands
October, 2016 |
Keywords | Field | DocType |
Horizon detection,Convolutional Neural Network,Edge detection | Skyline,Computer vision,Computer science,Edge detection,Convolutional neural network,Filter (signal processing),Exploit,Augmented reality,Software,Artificial intelligence,Pixel,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-4503-3603-1 | 1 | 0.41 |
References | Authors | |
16 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lorenzo Porzi | 1 | 120 | 11.79 |
Samuel Rota Bulò | 2 | 564 | 33.69 |
Elisa Ricci 0002 | 3 | 1393 | 73.75 |