A method which extracts traffic information from an MPEG-2 compressed video is proposed. According to the features of vehicle motion, the motion vector of a macro-block is used to detect moving vehicles in daytime, an...A method which extracts traffic information from an MPEG-2 compressed video is proposed. According to the features of vehicle motion, the motion vector of a macro-block is used to detect moving vehicles in daytime, and a filter algorithm for removing noises of motion vectors is given. As the brightness of the headlights is higher than that of the background in night images, discrete cosine transform （DCT）coefficient of image block is used to detect headlights of vehicles at night, and an algorithm for calculating the DCT coefficients of P-frames is introduced. In order to prevent moving objects outside the expressway and video shot changes from disturbing the detection, a driveway location method and a video-shot-change detection algorithm are suggested. The detection rate is 97.4% in daytime and 95.4% in nighttime by this method. The results prove that this vehicle detection method is effective.展开更多
In this paper an efficient compressed domain moving object segmentation algorithm is proposed, in which the motion vector （MV） field parsed from the compressed video is the only cue used for moving object segmentati...In this paper an efficient compressed domain moving object segmentation algorithm is proposed, in which the motion vector （MV） field parsed from the compressed video is the only cue used for moving object segmentation. First the MV field is temporally and spatially normalized, and then accumulated by an iterative backward projection to enhance salient motions and alleviate noisy MVs. The accumulated MV field is then segmented into motion-homogenous regions using a modified statistical region growing approach. Finally, moving object regions are extracted in turn based on minimization of the joint prediction error using the estimated motion models of two region sets containing the candidate object region and other remaining regions, respectively. Experimental results on several H.264 compressed video sequences demonstrate good segmentation performance.展开更多
In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classificrs ...In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classificrs to distinguish faces and non-faces. Moreover, to get more accurate results of the face detection, we present a kernel function and a linear combination to build incrementally the strong classifiers based on the weak classifiers. Through comparing and analyzing results of some experiments on the synthetic data and the natural data, we can get more satisfied results by the strong classifiers than by the weak classifies. Key words weak classifier - boosting algorithm - face detection - compressed domain CLC number TP 391. 41 Foundation item: Supported by the National 863 Program (2002 AA11101) and Open Fund of State Technology Center of Multimedia Software Engineering (621-273128)Biography: CHEN Lei(1978-), male, Master, research direction: image process, image recognition and AI.展开更多
More attention has been paid to the study of video object segmentation in compressed domain these years, which has already led to some practical technology. In this paper, a scheme is put forward for segmentation of h...More attention has been paid to the study of video object segmentation in compressed domain these years, which has already led to some practical technology. In this paper, a scheme is put forward for segmentation of head-shoulder video in MPEG (Motion Picture Experts Group) compressed domain. The conception of DCT (Discrete Cosine Transform) feature plane is defined. In the suggested scheme, firstly, the face region is detected by clustering skin-tone DCT feature points in the DCT feature plane. Secondly, the region of head-shoulder is approximately regarded as combination of the head rectangle and shoulder rectangle, and head rectangle is confirmed by double template matching. Thirdly, Canny operator and morphological operation are applied to the region of head-shoulder in feature plane to get the object mask and the region of object mask is rectified by correlation of DCT blocks to get high-quality segmentation.展开更多
Pornographic image/video recognition plays a vital role in network information surveillance and management. In this paper, its key techniques, such as skin detection, key frame extraction, and classifier design, etc.,...Pornographic image/video recognition plays a vital role in network information surveillance and management. In this paper, its key techniques, such as skin detection, key frame extraction, and classifier design, etc., are studied in compressed domain. A skin detection method based on data-mining in compressed domain is proposed firstly and achieves the higher detection accuracy as well as higher speed. Then, a cascade scheme of pornographic image recognition based on selective decision tree ensemble is proposed in order to improve both the speed and accuracy of recognition. A pornographic video oriented key frame extraction solution in compressed domain and an approach of pornographic video recognition are discussed respectively in the end.展开更多
Straightforward techniques for spatial domain digital video editing (DVE) of compressed video via decompression and recompression are computationally expensive. In this paper, a novel algorithm was proposed for mirror...Straightforward techniques for spatial domain digital video editing (DVE) of compressed video via decompression and recompression are computationally expensive. In this paper, a novel algorithm was proposed for mirror-image special effect editing in compressed video without full frame decompression and motion estimation. The results show that with the reducing of computational complexity, the quality of edited video in compressed domain is still close to the quality of the edited video in uncompressed domain at the same bit rate.展开更多
A content authentication technique based on JPEG-to-JPEG watermarking is proposed in this paper. In this technique, each 8x8 block in a JPEG compressed image is first processed by entropy decoding, and then the quanti...A content authentication technique based on JPEG-to-JPEG watermarking is proposed in this paper. In this technique, each 8x8 block in a JPEG compressed image is first processed by entropy decoding, and then the quantized discrete cosine transform （DCT） is applied to generate DCT coefficients： one DC coefficient and 63 AC coefficients in frequency coefficients. The DCT AC coefficients are used to form zero planes in which the watermark is embedded by a chaotic map. In this way, the watermark information is embedded into JPEG compressed domain, and the output watermarked image is still a JPEG format. The proposed method is especially applicable to content authentication of JPEG image since the quantized coefficients are modified for embedding the watermark and the chaotic system possesses an important property with the high sensitivity on initial values. Experimental results show that the tamper regions are localized accurately when the watermarked JPEG image is maliciously tampered.展开更多
基金The Cultivation Fund of the Key Scientific and Technical Innovation Project of Higher Education of Ministry of Education(No.705020)the Natural Science Foundation of Jiangsu Province ( No.BK2004077)
文摘A method which extracts traffic information from an MPEG-2 compressed video is proposed. According to the features of vehicle motion, the motion vector of a macro-block is used to detect moving vehicles in daytime, and a filter algorithm for removing noises of motion vectors is given. As the brightness of the headlights is higher than that of the background in night images, discrete cosine transform （DCT）coefficient of image block is used to detect headlights of vehicles at night, and an algorithm for calculating the DCT coefficients of P-frames is introduced. In order to prevent moving objects outside the expressway and video shot changes from disturbing the detection, a driveway location method and a video-shot-change detection algorithm are suggested. The detection rate is 97.4% in daytime and 95.4% in nighttime by this method. The results prove that this vehicle detection method is effective.
基金Project supported by the National Natural Science Foundation of China （Grant No.60572127）, the Development Foundation of Shanghai Municipal Commission of Education （Grant No.05AZ43）, and the Shanghai Leading Academic Discipline Project （Grant No.T0102）
文摘In this paper an efficient compressed domain moving object segmentation algorithm is proposed, in which the motion vector （MV） field parsed from the compressed video is the only cue used for moving object segmentation. First the MV field is temporally and spatially normalized, and then accumulated by an iterative backward projection to enhance salient motions and alleviate noisy MVs. The accumulated MV field is then segmented into motion-homogenous regions using a modified statistical region growing approach. Finally, moving object regions are extracted in turn based on minimization of the joint prediction error using the estimated motion models of two region sets containing the candidate object region and other remaining regions, respectively. Experimental results on several H.264 compressed video sequences demonstrate good segmentation performance.
文摘In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classificrs to distinguish faces and non-faces. Moreover, to get more accurate results of the face detection, we present a kernel function and a linear combination to build incrementally the strong classifiers based on the weak classifiers. Through comparing and analyzing results of some experiments on the synthetic data and the natural data, we can get more satisfied results by the strong classifiers than by the weak classifies. Key words weak classifier - boosting algorithm - face detection - compressed domain CLC number TP 391. 41 Foundation item: Supported by the National 863 Program (2002 AA11101) and Open Fund of State Technology Center of Multimedia Software Engineering (621-273128)Biography: CHEN Lei(1978-), male, Master, research direction: image process, image recognition and AI.
基金Supported by the National 973 Project of China (No.2001CB309403).
文摘More attention has been paid to the study of video object segmentation in compressed domain these years, which has already led to some practical technology. In this paper, a scheme is put forward for segmentation of head-shoulder video in MPEG (Motion Picture Experts Group) compressed domain. The conception of DCT (Discrete Cosine Transform) feature plane is defined. In the suggested scheme, firstly, the face region is detected by clustering skin-tone DCT feature points in the DCT feature plane. Secondly, the region of head-shoulder is approximately regarded as combination of the head rectangle and shoulder rectangle, and head rectangle is confirmed by double template matching. Thirdly, Canny operator and morphological operation are applied to the region of head-shoulder in feature plane to get the object mask and the region of object mask is rectified by correlation of DCT blocks to get high-quality segmentation.
基金Supported by the National Natural Science Foundation of China (No.60772069)863 High-Tech Project (2008AA01A313)
文摘Pornographic image/video recognition plays a vital role in network information surveillance and management. In this paper, its key techniques, such as skin detection, key frame extraction, and classifier design, etc., are studied in compressed domain. A skin detection method based on data-mining in compressed domain is proposed firstly and achieves the higher detection accuracy as well as higher speed. Then, a cascade scheme of pornographic image recognition based on selective decision tree ensemble is proposed in order to improve both the speed and accuracy of recognition. A pornographic video oriented key frame extraction solution in compressed domain and an approach of pornographic video recognition are discussed respectively in the end.
文摘Straightforward techniques for spatial domain digital video editing (DVE) of compressed video via decompression and recompression are computationally expensive. In this paper, a novel algorithm was proposed for mirror-image special effect editing in compressed video without full frame decompression and motion estimation. The results show that with the reducing of computational complexity, the quality of edited video in compressed domain is still close to the quality of the edited video in uncompressed domain at the same bit rate.
基金supported by the National Natural Science Foundation of China under Grant No.60702025the Research Fund for the Doctoral Program of Higher Education under Grant No.20070613024Sichuan Youth Science & Technology Foundation under Grant No.07ZQ026-004
文摘A content authentication technique based on JPEG-to-JPEG watermarking is proposed in this paper. In this technique, each 8x8 block in a JPEG compressed image is first processed by entropy decoding, and then the quantized discrete cosine transform （DCT） is applied to generate DCT coefficients： one DC coefficient and 63 AC coefficients in frequency coefficients. The DCT AC coefficients are used to form zero planes in which the watermark is embedded by a chaotic map. In this way, the watermark information is embedded into JPEG compressed domain, and the output watermarked image is still a JPEG format. The proposed method is especially applicable to content authentication of JPEG image since the quantized coefficients are modified for embedding the watermark and the chaotic system possesses an important property with the high sensitivity on initial values. Experimental results show that the tamper regions are localized accurately when the watermarked JPEG image is maliciously tampered.
