We cast vehicle recognition as problem of feature representation and classification, and introduce a sparse learning based framework for vehicle recognition and classification in this paper. After objects captured wit...We cast vehicle recognition as problem of feature representation and classification, and introduce a sparse learning based framework for vehicle recognition and classification in this paper. After objects captured with a GMM background subtraction program, images are labeled with vehicle type for dictionary learning and decompose the images with sparse coding （SC）, a linear SVM trained with the SC feature for vehicle classification. A simple but efficient active learning stategy is adopted by adding the false positive samples into previous training set for dictionary and SVM model retraining. Compared with traditional feature representation and classification realized with SVM, SC method achieves dramatically improvement on classification accuracy and exhibits strong robustness. The work is also validated on real-world surveillance video.展开更多
文摘LG近日推出了一款可以实现一键采集、刻录的GSA-5169D外置DVD刻录机．它可以连接摄像机，录像机等视频设备．自动完成采集刻录工作。这款产品支持16X DVD±R、8X DVD±RW和5X DVD-RAM刻格．规格处于目前主流水平。GSA-5169D为银色机身．边角以圆弧过渡处理，显得非常时尚。前面板除了弹出钮外，还有一个One Touch按钮，后部接口也比普通的外置DVD刻录机多了AV和S端子。这就是GSA-5169D独特的One Touch Video to Disc功能．可以实现一步搞定视频采集和DVD制作。
基金the National Natural Science Foundation of China under Grant NO 61472166,NO 61105015,Jiangsu Provincial Natural Science Foundation under Grant NO BK2010366 and Key Laboratory of Cloud Computing and Intelligent Information Processing of Changzhou City under Grand NO CM20123004
文摘We cast vehicle recognition as problem of feature representation and classification, and introduce a sparse learning based framework for vehicle recognition and classification in this paper. After objects captured with a GMM background subtraction program, images are labeled with vehicle type for dictionary learning and decompose the images with sparse coding （SC）, a linear SVM trained with the SC feature for vehicle classification. A simple but efficient active learning stategy is adopted by adding the false positive samples into previous training set for dictionary and SVM model retraining. Compared with traditional feature representation and classification realized with SVM, SC method achieves dramatically improvement on classification accuracy and exhibits strong robustness. The work is also validated on real-world surveillance video.
