ABSTRACT
In this paper, we describe a general learning architecture for object detection especially car detection. In order to build such a system, we first perform dimension reduction for each example by using maximizing mutual information criterion. The algorithm directly selects projection basis from examples which can minimize Bayes error. This algorithm is named as Maximizing Mutual Information(MMI) method. Given projection basis, all of examples are projected onto these basis and then trained by Support Vector Machine(SVM). This approach can be applied to any object with distinguishable patterns. In test process, we find objects in a image by using our exhaustive search algorithm which is called a Scale based Classifier Activation Map(SCAM). We applied our detection scheme into UIUC car/non-car database [2]. In this experiment we detect 181 cars in 170 images with 200 cars. This result is competitive comparing with other papers [1, 12].
- S. Agarwal and A. Awan. Learning to detect objects in images via a sparse, part-based representation. IEEE Trans. on Pattern Analysis and Machine Intellgence 26(11):1475--1490, 2004. Google ScholarDigital Library
- S. Agarwal and D. Roth. Car detection. http://l2r.cs.uiuc.edu/~cogcomp/Data/Car/2002.Google Scholar
- E. Bingham and H. Mannila. Random projection in dimensionality reduction: applications to image and text data. In proceedings of the 7th ACM SIGKDD international conference on Knowledge discovery and data mining pages 245--250, 2001. Google ScholarDigital Library
- S. Canu. Svm and kernel methods matlab toolbox. Perception Systemes et Information, INSA de Rouen, Rouen, France, 2005.Google Scholar
- R. Cendrillon and B. C. Lovell. Real-time face recognition using eigenfaces.Google Scholar
- N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In international Conf. on Computer Vision and Pattern Recognition volume 2, pages 886--893, June 2005. Google ScholarDigital Library
- Fano. Transmission of information:A statistical theory of communications. American Journal of Physics 29:793--794, November 1961.Google ScholarCross Ref
- Hellman and R. J. M. Probability of error, equivocation, and chernoff bound. IEEE Trans. on Information Theroy 16: 368--372, July 1970.Google ScholarDigital Library
- A. Mohan, C. Papageorgiou, and T. Poggio. Example-based object detection in images by components. IEEE Trans. on Pattern Analysis and Machine Intellgence 23(4):349--361, 2001. Google ScholarDigital Library
- G. B. N. Goel and A. Ne fian. Face recognition experiments with random projection. In SPIE Defense and Security Symposium (Biometric Technology for Human Identification), Orlando, FL 2005.Google Scholar
- E. Osuna, R. Freund, and F. Girosi. Training support vector machines:an application to face detection. International Conf. on Computer Vision and Pattern Recognition 1997. Google ScholarDigital Library
- G. Qiu and J. Fang. Car/non-car classification in an informative sample subspace. In the 18th International Conf. on Pattern Recognition 2006. Google ScholarDigital Library
- H. Rowley, S. Baluja, and T. Kanade. Neural network-based face detection. IEEE Trans. on Pattern Analysis and Machine Intelligence 20(1):23--38, January 1998. Google ScholarDigital Library
- O. Sidla, Y. Lypetskyy, N. Brandle, and S. Seer. Pedestrian detection and tracking for counting applications in crowded situations. In proceedings of the IEEE International Conf. on Video and Signal Based Surveillance page 70, 2006. Google ScholarDigital Library
- K. Torkkola. Feature extraction by non parametric mutual information maximization. Journal of Machine Learning Research 3: 1415--1438, 2003. Google ScholarDigital Library
- UCI. Uci machine learning repository. http://archive.ics.uci. edu/ml/datasets/Statlog+(Landsat+Satellite)1993.Google Scholar
- Q. Zhu and S. Avidan. Fast human detection using a cascade of histograms of oriented gradients. In international Conf. on Computer Vision and Pattern Recognition pages 1491--1498, 2006. Google ScholarDigital Library
Index Terms
- Example based learning for object detection in images
Recommendations
Riemannian Manifold Learning
Recently, manifold learning has been widely exploited in pattern recognition, data analysis, and machine learning. This paper presents a novel framework, called Riemannian manifold learning (RML), based on the assumption that the input high-dimensional ...
Linear projective approach for moving object detection in video
IML '17: Proceedings of the 1st International Conference on Internet of Things and Machine LearningMoving objects detection in video is essential for many computer vision applications and it is considered as a challenging research issue due to dynamic changes in object size, shape, complex background and illumination changes. In this research article ...
Event Detection Based on Noisy Object Information
ACPR '13: Proceedings of the 2013 2nd IAPR Asian Conference on Pattern RecognitionThis paper proposes an event detection method using noisy object information. Some events have a close connection with objects, and the objects related to the event often appear with the event in a video. For example, if an event "Grooming an animal" ...
Comments