A strategy of color image based human face representation is first proposed. Then, based on this representation, complex Eigenfaces technique is developed for facial feature extraction. Finally, we test our idea using...
详细信息
This paper proposed a practical approach to personalized tutoring planning by exploiting existing tutoring resources (e.g., a book, a courseware). More exactly, it does not build an instructional course from scratch -...
详细信息
In the advanced Audio Video coding Standard (AVS), many efficient coding tools are adopted in motion compensation, such as new motion vector prediction, direct mode matching, variable block-sizes etc. However, these f...
详细信息
In this paper we proposed a simple but effective method for simultaneously detecting video shot transitions of various types by means of combining threshold and SVM based method. Our method first selects the suspiciou...
详细信息
In this paper we proposed a simple but effective method for simultaneously detecting video shot transitions of various types by means of combining threshold and SVM based method. Our method first selects the suspicious transition candidates using a low threshold method and then judges the candidates by using the SVM base method. In selecting the low threshold, we use only two simply features: histogram and mutual information. Due to this low threshold, we do not need to extract complex features around every frame changes, so our method can run over real time. The most important problem of the system is its fail to distinct gradual transition and motion in some times. This is because we use little information about the camera motion and object motion. In the future we will use more information about the camera motion to alleviate this problem. The test result on TRECVID benchmark shows our approach is effective for shot boundary detection.
In this paper, an improved 3D recursive searching (3DRS) algorithm for video de-interlacing is proposed. This algorithm solves the error propagation problem which exists in the original 3DRS by using bi-directional bl...
详细信息
ISBN:
(纸本)300018726X
In this paper, an improved 3D recursive searching (3DRS) algorithm for video de-interlacing is proposed. This algorithm solves the error propagation problem which exists in the original 3DRS by using bi-directional block matching. It also improves the precision of motion estimation by using multi-resolution searching to adjust the matching block size according to the video content. Experiments show that the proposed algorithm generates better subjective and objective results than the original 3DRS algorithm on most tested sequences. video de-interlacing, 3D recursive searching, bi-directional block matching, multi-resolution searching.
While a lot of research has been done on some important aspects of WSN such as architecture and protocol design, supporting Quality of Service in WSN is still a largely unexplored research field. An application-specif...
详细信息
This paper investigates adult images detection based on the shape features of skin regions. In order to accurately detect skin regions, we propose a skin detection method using multi-Bayes classifiers in the paper. Ba...
详细信息
Remote experimentation is the process of conducting real lab experiments without being physically in contact with lab devices. Recently, the development of Internet technologies fostered the spread of online laborator...
详细信息
Routing is one of the fundamental but challenging issues in mobile ad hoc networks. During the past several years, a large number of routing protocols have been proposed, which can basically be categorized into three ...
详细信息
Time synchronization is a critical middleware service of wireless sensor networks. Researchers have already proposed some time synchronization algorithms. However, due to the demands for various synchronization precis...
详细信息
Time synchronization is a critical middleware service of wireless sensor networks. Researchers have already proposed some time synchronization algorithms. However, due to the demands for various synchronization precision, existing time synchronization algorithms often need to be adapted. So it is necessary to evaluate these adapted algorithms before use. Software simulation is a valid and quick way to do it. In this paper, we present a time synchronization simulator, Simsync, for wireless sensor networks. We decompose the packet delay into 6 delay components and model them separately. The frequency of crystal oscillator is modeled as Gaussian. To testify its effectiveness, we simulate the reference broadcast synchronization algorithm (RBS) and the timing-sync synchronization algorithm (TPSN) on Simsync. Simulated results are also presented and analyzed.
暂无评论