J. Rafid Siddiqui
ABSTRACT
Animals have evolved to restrict their sensing capabilities to certain region of electromagnetic spectrum. This is surprisingly a very narrow band on a vast scale which makes one think if there is a systematic bias underlying such selective filtration. The situation becomes even more intriguing when we find a sharp cutoff at Near-infrared point whereby almost all animal vision systems seem to have a lower bound. This brings us to an interesting question: did evolution "intentionally" performed such a restriction in order to evolve higher visual cognition? In this work this question is addressed by experimenting with Near-infrared images for their potential applicability in higher visual processing such as semantic segmentation. A modified version of Fully Convolutional Networks is trained on NIR images and RGB images respectively and compared for their respective effectiveness in the context of semantic segmentation. The results from the experiments show that visible part of the spectrum alone is sufficient for the robust semantic segmentation of the indoor as well as outdoor scenes.
- Gerald H. Jacobs. "The Verriest Lecture Recent progress inunderstanding mammalian color vision.", Ophthalmic and PhysiologicalOptics, vol. 30(5), 422--434, September 2010. Google Scholar
Cross Ref
- A. T. D. Bennett and I. C. Cuthill. "Ultraviolet vision in birds: What is its function?", Vision Research, vol. 34(11), pp. 1471--1478, June 1994. Google ScholarCross Ref
- Innes C. Cuthill, Julian C. Partridge, Andrew T. D. Bennett, Stuart C. Church, Nathan S. Hart, and Sarah Hunt. "Ultraviolet Vision in Birds, Advances in the Study of Behavior", vol. 29, pp. 159--214., 2000. Google ScholarCross Ref
- Richard C. Goris, "Infrared Organs of Snakes: An Integral Part of Vision.", Journal of Herpetology, vol. 45(1), pp. 2--14, March 2011. Google ScholarCross Ref
- Elena O, Gracheva, Nicholas T. Ingolia, Yvonne M. Kelly, Julio F. Cordero-Morales, Gunther Hollopeter, Alexander T. Chesler, Elda E. Sánchez, John C. Perez, Jonathan S. Weissman, and David Julius, "Molecular basis of infrared detection by snakes.", Nature, vol. 464(7291), pp. 1006--1011, April 2010.Google ScholarCross Ref
- J. R. Siddiqui, H. Andreasson, D. Driankov, and A. J. Lilienthal. "Towards visual mapping in industrial environments - a heterogeneous task-specific and saliency driven approach.", In 2016 IEEE InternationalConference on Robotics and Automation (ICRA), pp. 5766--5773, May 2016.Google ScholarDigital Library
- Steve Brown, "Analysis of the State of the Art: Near-Infrared Spectroscopy.", Spectroscopy, vol. 30, June 2015.Google Scholar
- T. Funane, "Wearable near-infrared spectroscopy neuroimaging and its Applications", 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 4025--4028, August 2015. Google ScholarCross Ref
- U. Mahmood. "Near infrared optical applications in molecular imaging.", IEEE Engineering in Medicine and Biology Magazine, vol. 23(4), pp. 58--66, July 2004. Google ScholarCross Ref
- A. S. Nunez and M. J. Mendenhall. "Detection of Human Skin in Near Infrared Hyperspectral Imagery.", In IEEE International Geoscience and Remote Sensing Symposium, volume 2, pp. II-621--II-624, July 2008. Google ScholarCross Ref
- Simone Bassis, Anna Esposito, Francesco Carlo Morabito, and Eros Pasero, "Smart Innovation, Systems and Technologies", Advances in Neural Networks, vol. 54, Springer International Publishing, Cham, 2016.Google ScholarCross Ref
- Mohammad Havaei, Axel Davy, David Warde-Farley, Antoine Biard, Aaron Courville, Yoshua Bengio, Chris Pal, Pierre-Marc Jodoin, and Hugo Larochelle. "Brain tumor segmentation with deep neural networks.", Medical Image Analysis, 2016.Google Scholar
- Mohammad Havaei, Pierre-Marc Jodoin, and Hugo Larochelle. "Efficient Interactive Brain Tumor Segmentation as Within-Brain kNN Classification.", In ICPR, pp. 556--561, 2014. Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. "ImageNet Classification with Deep Convolutional Neural Networks.", In F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 25, pp. 1097--1105., 2012.Google Scholar
- J. Long, E. Shelhamer, and T. Darrell. "Fully convolutional networks for semantic segmentation.", In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431--3440, June 2015. Google ScholarCross Ref
- K. Simonyan and A. Zisserman. "Very Deep Convolutional Networks for Large-Scale Image Recognition.", CoRR, abs/1409.1556, 2014.Google Scholar
- Neda Salamati, Diane Larlus, Gabriela Csurka, and Sabine Susstrunk. "Incorporating near-infrared information into semantic image segmentation.", arXiv preprint arXiv:1406.6147, 2014.Google Scholar
- Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla, "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation.", 2015.Google Scholar
Index Terms
- Did Evolution get it right?: An evaluation of Near-Infrared Imaging for Semantic Scene Segmentation
Recommendations
Scene Segmentation Assisted by Stereo Vision
3DIMPVT '11: Proceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and TransmissionStereo vision systems for 3D reconstruction have been deeply studied and are nowadays capable to provide a reasonably accurate estimate of the 3D geometry of a framed scene. They are commonly used to merely extract the 3D structure of the scene. However,...
Evolved open-endedness, not open-ended evolution
Open-endedness is often considered a prerequisite property of the whole evolutionary system and its dynamical behaviors. In the actual history of evolution on Earth, however, there are many examples showing that open-endedness is rather a consequence of ...
Motion based image segmentation for video coding
ICIP '95: Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3 - Volume 3A robust and stable scene segmentation is a prerequisite for the object based coding. Various approaches to this complex task have been proposed, including segmentation of optic flow, grey-level based segmentation or simple division of the scene into ...
Comments