Open Access Open Access  Restricted Access Subscription Access

Random Decision Forests for Object Detection

Juanjuan Ma, Quan Pan, Chunhui Zhao, Yizhai Zhang, Liu Liu, Yang Lv

Abstract


The image streams from the optical sensors in UAV (Unmanned Aerial Vehicle) are very large and highly dimensional, with considerable noise. Moreover, it is required to be capable of real-time information processing. In this paper we take advantage of random decision forests to learn a computationally efficient and accurate visual object detector for UAV. The random decision forests are learned with discriminative decision trees, where every tree internal node is a discriminative classifier. The experimental results show that our object detection approach achieves real-time performance and good object detection results.

Full Text:

PDF

References


T. Malisiewicz, A. Gupta and A. A. Efros, “Ensemble of exemplar-SVMs for object detection and beyond,” IEEE International Conference on Computer Vision, 2011.

L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, 2001, pp.5–32.

P. Dollar and C. L. Zitnick, “Structured forests for fast edge detection,” IEEE International Conference on Computer Vision, 2013, pp. 1-3.

B. Ommer and J. Buhmann, “Learning the compositional nature of visual object categories for recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010.

B. Leibe, A. Leonardis, and B. Schiele, “Robust object detection with interleaved categorization and segmentation,” International Journal of Computer Vision, vol. 77, 2008, pp.259-289.

L. Breiman, “Bagging predictors,” Machine Learning, vol. 24, no. 2, 1996.

A. Criminisi, J. Shotton, and E. Konukoglu, “Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning,” Foundations and Trends in Computer Graphics and Vision, vol7, no. (2-3), February 2012, pp.2-4.

A. Criminisi, J. Shotton, and E. Konukoglu, Decision Forests for Computer Vision and Medical Image Analysis. Springer London Heidelberg New York Dordrecht, February 2013, ch. 1-4.

N. Oza and S. Russell, “Online bagging and boosting,” Proceedings Artificial Intelligence and Statistics, 2010, pp. 105-112.

B. Yao, A. Khosla, and L. Fei-Fei, “Combining randomization and discrimination for fine-grained image categorization,” IEEE Conference on Computer Vision and Pattern Recognition 2011, pp. 1-4.

J. Shotton, M. Johnson, and R. Cipolla, “Semantic texton forests forimage categorization and segmentation,” IEEE Conference on Computer Vision and Pattern Recognition 2008.

J. Marın, D. Va´zquez, A. M. Lopez, J. Amores and B. Leibe, “Random forests of local experts for pedestrian detection,” IEEE International Conference on Computer Vision, 2013, pp. 1-3.

C. Lampert, M. Blaschko, and T. Hofmann. “Beyond sliding windows:

Object localization by efficient subwindow search,” IEEE Conference on Computer Vision and Pattern Recognition 2008.

J. Gall and V. Lempitsky, “Class-specific hough forests for object detection,” IEEE Conference on Computer Vision and Pattern Recognition 2009, pp. 1-6.

D. G. Lowe, “Distinctive image features from scale-invariant keypoints,” International Journal of Computer Vision, vol. 60, num. 2, 2004, pp. 91- 110.

A. Saffari, C. Leistner and J. Santner, M. Godec and H. Bischof, “On-line random forests,” IEEE International Conference on Computer Vision, 2009.

J. Shotton, M. Johnson, and R. Cipolla, “Semantic texton forests for image categorization and segmentation,” IEEE Conference on Computer Vision and Pattern Recognition 2008.

J. M. Winn and J. Shotton. “The layout consistent random field for

recognizing and segmenting partially occluded objects,” Conference on Computer Vision and Pattern Recognition (1), 2006, pp. 37–44.

B. Hariharan, C. L. Zitnick and P. Dollar, “Detecting Objects using Deformation Dictionaries,” IEEE Conference on Computer Vision and Pattern Recognition 2014.

W. Ouyang and X. Wang, “Joint deep learning for pedestrian detection,” IEEE International Conference on Computer Vision, 2013.

P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan.

Object detection with discriminatively trained part-based models. PAMI, 32(9), 2010.

J. Gall, A. Yao, N. Razavi, L. V. Gool and V. Lempitsky, “Hough forests for object detection, tracking, and action recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, num. 11, November 2011. pp. 1-6.

D. K. Prasad, “Survey of the problem of object detection in real images,” International Journal of Image Processing, Vol. 6, 2012.

G. Ghiasi and C. C. Fowlkes, “Occlusion coherence: localizing occluded faces with a hierarchical deformable part Model,” IEEE Conference on Computer Vision and Pattern Recognition 2014.

S. Agarwal, A. Awan, and D. Roth, “Learning to detect objects in images via a sparse, part-based representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.26, num.11, 2004, pp. 1475-1490.

S. Schultery, C. Leistnerz, P. Wohlharty, P. M. Rothy and H. Bischofy, “Alternating regression forests for object detection and pose estimation,” IEEE International Conference on Computer Vision, 2013.

S. Schultery, C. Leistnerz, P. Wohlharty, P. M. Rothy and H. Bischofy, “Accurate object detection with joint classification-regression random forests,” IEEE Conference on Computer Vision and Pattern Recognition 2014.

P. F. Felzenszwalb, R. B. Girshick and D. McAllester, “Cascade Object Detection with Deformable Part Models,” IEEE Conference on Computer Vision and Pattern Recognition 2010.

J. Mutch and D. G. Lowe, “Multiclass object recognition with sparse,

localized features,” Conference on Computer Vision and Pattern Recognition (1), 2006, pp. 11–18.




DOI: http://dx.doi.org/10.21535%2FProICIUS.2014.v10.271

Refbacks

  • There are currently no refbacks.