A Neuromorphic Approach to Object Detection and Recognition in Airborne Videos with Stabilization
Research has shown that the application of an attention algorithm to the front-end of an object recognition system can provide a boost in performance over extracting regions from an image in an unguided manner. However, when video imagery is taken from a moving platform, attention algorithms such as saliency can lose their potency. In this paper, we show that this loss is due to the motion channels in the saliency algorithm not being able to distinguish object motion from motion caused by platform movement in the videos, and that an object recognition system for such videos can be improved through the application of image stabilization and saliency. We apply this algorithm to airborne video samples from the DARPA VIVID dataset and demonstrate that the combination of stabilization and saliency significantly improves object recognition system performance for both stationary and moving objects.
KeywordsSupport Vector Machine Classifier Scale Invariant Feature Transform Saliency Detection Scale Invariant Feature Transform Feature Video Stabilization
Unable to display preview. Download preview PDF.
- 4.Guo, C., Ma, Q., Zhang, L.: Spatio-temporal Saliency Detection Using Phase Spectrum of Quaternion Fourier Tranform. In: Proc. CVPR, pp. 1–8 (2008)Google Scholar
- 5.Hou, X., Zhang, L.: Saliency Detection: A Spectral Residual Approach. In: Proc. CVPR, pp. 1–8 (2007)Google Scholar
- 7.Huber, D., Khosla, D.: A Bio-Inspired Method and System for Visual Object-Based Attention and Segmentation. In: Proc. SPIE DSS, vol. 7696 (2010)Google Scholar
- 8.Chikkerur, S., Serre, T., Poggio, T.: Attentive Processing Improves Object Recognition. Massachusetts Institute of Technology Technical Report: MIT-CSAIL-TR-2009-046 (2009)Google Scholar
- 9.Rutishauser, U., Walther, D., Koch, C., Perona, P.: Is Bottom-Up Attention Useful for Object Recognition? In: Proc. CVPR, vol. 2, pp. 37–44 (2004)Google Scholar
- 11.Mutch, J., Lowe, D.: Multiclass Object Recognition with Sparse, Localized Features. In: Proc. CVPR, pp. 11–18 (2006)Google Scholar