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.
- T. Ahmad, G. Bebis, M. Nicolescu, A. Nefian, and T. Fong. An edge-less approach to horizon line detection. In ICMLA, 2015.Google ScholarCross Ref
- G. Baatz, O. Saurer, K. Köser, and M. Pollefeys. Large scale visual geo-localization of images in mountainous terrain. In ECCV. 2012.Google ScholarCross Ref
- L. Baboud, M. Čadík, E. Eisemann, and H.-P. Seidel. Automatic photo-to-terrain alignment for the annotation of mountain pictures. In CVPR, 2011. Google ScholarDigital Library
- M. Bansal, H. S. Sawhney, H. Cheng, and K. Daniilidis. Geo-localization of street views with aerial image databases. In ACM MM, 2011. Google ScholarDigital Library
- P. Dollár, Z. Tu, and S. Belongie. Supervised learning of edges and object boundaries. In CVPR, 2006. Google ScholarDigital Library
- P. Dollár and C. L. Zitnick. Structured forests for fast edge detection. In ICCV, 2013.Google ScholarDigital Library
- D. Kingma and J. Ba. Adam: A method for stochastic optimization. In ICLR, 2015.Google Scholar
- I. Kokkinos. Surpassing humans in boundary detection using deep learning. ICLR, 2016.Google Scholar
- C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu. Deeply-supervised nets. AISTATS, 2015.Google Scholar
- S. Lee, H. Zhang, and D. J. Crandall. Predicting geo-informative attributes in large-scale image collections using convolutional neural networks. In WACV, 2015. Google ScholarDigital Library
- H. Noh, S. Hong, and B. Han. Learning deconvolution network for semantic segmentation. In ICCV, 2015. Google ScholarDigital Library
- V. Ordonez and T. L. Berg. Learning high-level judgments of urban perception. In ECCV. 2014.Google ScholarCross Ref
- L. Porzi, S. Rota Bulò, P. Valigi, O. Lanz, and E. Ricci. Learning contours for automatic annotations of mountains pictures on a smartphone. In ICDSC, 2014. Google ScholarDigital Library
- O. Saurer, G. Baatz, K. Köser, M. Pollefeys, et al. Image based geo-localization in the alps. IJCV, pages 1--13, 2015. Google ScholarDigital Library
- K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556, 2014.Google Scholar
- L. Tao, L. Yuan, and J. Sun. Skyfinder: attribute-based sky image search. In ACM TOG, volume 28, page 68, 2009. Google ScholarDigital Library
- W. Wang, G. Chen, A. T. T. Dinh, J. Gao, B. C. Ooi, K.-L. Tan, and S. Wang. Singa: Putting deep learning in the hands of multimedia users. In ACM MM, 2015. Google ScholarDigital Library
- R. Xiaofeng and L. Bo. Discriminatively trained sparse code gradients for contour detection. In NIPS, 2012. Google ScholarDigital Library
- S. Xie and Z. Tu. Holistically-nested edge detection. In ICCV, 2015. Google ScholarDigital Library
- M. D. Zeiler and R. Fergus. Visualizing and understanding convolutional networks. In ECCV. 2014.Google ScholarCross Ref
- B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, and A. Oliva. Learning deep features for scene recognition using places database. In NIPS, 2014. Google ScholarDigital Library
Index Terms
A Deeply-Supervised Deconvolutional Network for Horizon Line Detection
Recommendations
Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection
MM '16: Proceedings of the 24th ACM international conference on MultimediaThis paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, the local, global, and contextual ...
Efficient Horizon Line Detection Using an Energy Function
RACS '17: Proceedings of the International Conference on Research in Adaptive and Convergent SystemsIn this work we propose a new method for horizon line detection in marine environment images captured by either visible light or infrared cameras. A common method for horizon line detection is based on edge detection and Hough transform. This method has ...
A novel approach for detecting the horizon using a convolutional neural network and multi-scale edge detection
This paper proposes a novel method for horizon detection that combines a multi-scale approach and a convolutional neural network (CNN). The ability to detect the horizon is the first step toward situational awareness of autonomous ships, which have ...
Comments