Image analysis – Learning systems
Reexamination Certificate
2007-07-19
2010-12-14
Seth, Manav (Department: 2624)
Image analysis
Learning systems
C382S103000, C382S168000, C382S195000
Reexamination Certificate
active
07853072
ABSTRACT:
The present invention provides an improved system and method for object detection with histogram of oriented gradient (HOG) based support vector machine (SVM). Specifically, the system provides a computational framework to stably detect still or not moving objects over a wide range of viewpoints. The framework includes providing a sensor input of images which are received by the “focus of attention” mechanism to identify the regions in the image that potentially contain the target objects. These regions are further computed to generate hypothesized objects, specifically generating selected regions containing the target object hypothesis with respect to their positions. Thereafter, these selected regions are verified by an extended HOG-based SVM classifier to generate the detected objects.
REFERENCES:
patent: 5101440 (1992-03-01), Watanabe et al.
patent: 5604822 (1997-02-01), Pearson et al.
patent: 5644386 (1997-07-01), Jenkins et al.
patent: 7688997 (2010-03-01), Gibbins et al.
patent: 2007/0098254 (2007-05-01), Yang et al.
patent: 2007/0237387 (2007-10-01), Avidan et al.
Viola and Jones, Rapid object detection using a boosted cascade of simple features, Proc. 2001 IEEE Computer Soc'y Conf.—Computer Vision & Pattern Recognition 511-18 (2001).
Kuehnle, Symmetry-based recognition of vehicle rears, Pattern Recognition Letters 12:4, 249-58 (1991).
Mallot et al., Inverse perspective mapping simplifies optical flow computation and obstacle detection, Biol. Cybernetics 64:3, 177-85 (1991).
Bertozzi et al., Gold: A parallel real-time stereo vision system for generic obstacle and lane detection, IEEE Transactions on Image Processing 7:1, 62-81 (1998).
Heisele and Ritter, Obstacle detection based on color blob flow, Proc. IEEE Intelligent Vehicles Symp., 282-86 (1995).
Koller et al., Algorithm characterization of vehicle trajectories from image sequences by motion verbs, Proc. 1991 IEEE Computer Soc'y Conf. Computer Vision & Pattern Recognition 90-95 (1991).
Weber et al., Unsupervised learning of models for recognition, Lecture Notes in Computer Sci. Computer Vision Euro. Conf. Computer Vision 1842, 18-32 (2000).
Sung and Poggio, Example-based learning for view-based human face detection, IEEE Transactions on Pattern Analysis & Machine Intelligence 20:1, 39-51 (1998).
van der Wal et al., The Acadia vision processor, Proc. 5th IEEE Int'l Workshop on Computer Architectures for Machine Perception 31-40 (2000).
Lowe, Distinctive image features from scale-invariant keypoints, Int'l J. Computer Vision 60:2, 91-110 (2004).
Osuna et al., Training support vector machines: an application to face detection, Proc. 1997 IEEE Computer Soc'y Conf. Computer Vision & Pattern Recognition 130-36 (1997).
Vapnik, The Nature of Statistical Learning Theory, 139-169 (2d ed. 2000).
Agarwal et al., Learning to detect objects in images via a sparse, part-based representation, IEEE Transactions on Pattern Analysis & Machine Intelligence 26:11, 1475-1490 (2004).
Zielke et al., Intensity and edge-based symmetry detection with an application to car following, CVGIP: Image Understanding 58, 177-90 (1993).
Viola et al., Detecting pedestrians using patterns of motion and appearance, Int'l J. Computer Vision 63:2, 153-61 (2005).
Agarwal and Roth, Learning a sparse representation for object detection, Proc. 7th Euro. Conf. Computer Vision 1, 113-30 (2002).
Leibe et al., Pedestrian detection in crowded scenes, IEEE Computer Soc'y Conf. Computer Vision and Recognition 1, 878-85 (2005).
Leibe et al., Combined object categorization and segmentation with an implicit shape model, Euro. Conf. Computer Vision Works. on Statistical Learning in Computer Vision, 17-32 (2004).
Dalal and Triggs, Histograms of oriented gradients for human detection, IEEE Computer Soc'y Conf. Computer Vision and Recognition 1, 886-93 (2005).
Belongie et al., Shape matching and object recognition using shape contexts, IEEE Transactions on Pattern Analysis & Machine Intelligence 24:4, 502-22 (2002).
Freeman and Roth, Orientation histograms for hand gesture recognition, IEEE Intl. Works. on Automatic Face and Gesture Recognition, 296-301 (1995).
Freeman et al., Computer vision for computer games, Proc. 2d Int'l Conf. Automatic Face and Gesture Recognition, 100-105 (1996).
Heisele et al, Hierarchical classification and feature reduction for fast face detection with support vector machines, Pattern Recognition 36, 2007-17 (2003).
Romdhani et al., Computationally efficient face detection, Proc. 8th Int'l Conf. on Computer Vision 1, 695-700 (2001).
Everingham et al., The 2005 pascal visual object classes challenge, Proc. 1st PASCAL Challenges Works. (2005).
Shan et al., Learning Exemplar-Based Categorization for the Detection of Multi-View Multi-Pose Objects, Proc. 2006 IEEE Computer Soc'y Conf. Computer Vision & Pattern Recognition 2, 1431-38 (2006).
Cekander Ryan
Han Feng
Kumar Rakesh
Sawhney Harpreet S.
Shan Ying
Lowenstein & Sandler PC
Sarnoff Corporation
Seth Manav
LandOfFree
System and method for detecting still objects in images does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for detecting still objects in images, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for detecting still objects in images will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4197227