思政教育在公共课中占有非常重要的地位,但如何针对大学生自身的特点,在公共课的讲授中潜移默化地融入思政元素,并与课程内容完美结合,确实需要任课教师进行深度思考.笔者作为公共课《大学计算机》的负责人,对于思政元素的教学融入方面有了一些探索和实践,取得了良好的效果.

With the development of social life and improvement of computer science and technology, human-computer interaction(HCI) technology has been paid more and more attentions and become an important aspect of research field. Gestures, as a natural ways of communication between people, contain rich information. So gesture recognition has become a branch of human-computer interaction, which has gradually become a hot research topic. This paper presents a method for gesture recognition based on data glove. Sparse decomposition is firstly conducted on the raw data, then a support vector machine(SVM) classifier is applied on the dictionary part to achieve recognition results. The experimental results reveal that our method can achieve very high recognition accuracy on the data glove gestures.

A new technique of scanned image restoration is proposed to save a large amount of important old documents. Firstly, by using a high definition scanner, these obsolete documents are scanned page by page to get the HD images. Secondly, different processing techniques are adopted, including removing black holes, deepening handwriting, denoising, etc., so as to make the contents of the files clearer without changing its original contents. A large number of experiments show that this method is simple and feasible. Not only can this technique protect the original version of these old files, it can also facilitate people to access these documents clearly and efficiently.

A motion-compensated frame interpolation (MCFI) algorithm for multiview video based on inter-view and intra-view correlations is proposed in this paper. First, unidirectional motion estimation (ME) is implemented to obtain forward and backward motion vector fields (MVFs). Subsequently, occlusion blocks in previous and current frames are detected. Then, an inter-view-correlation based method is adopted for occlusion handling. After that, the motion vector (MV) outliers are detected and corrected by considering spatial, color and depth information of current viewpoint video. Finally, MVs are assigned to the interpolated frame for frame reconstruction. Experimental results demonstrate that the proposed algorithm provides better performance than existing 2D and 3D video MCFI methods.

An efficient frame interpolation method for 3D video is proposed in this paper. First, the motion vector field (MVF) of the interpolated frame is estimated using bidirectional motion estimation method. Then, the blocks in the interpolated frame are classified into occlusion and normal blocks according to the depth information. After that, the motion vector (MV) outliers of the normal blocks are detected and corrected. Furthermore, the MVs of the occlusion blocks are post-processed using a foreground matching method, and one occlusion block is segmented into foreground and background parts, which will be interpolated discriminatively. Simulation results show that the proposed method achieves higher PSNR and SSIM values than traditional motion-compensated frame interpolation (MCFI) methods, and moreover, the visual quality of the interpolated frames using the proposed method is better.

In view interpolation, information missing often exists in initial depth map, moreover, disocclusion regions usually occur along the foreground object boundaries after 3D warping. Generally, initial depth map and warped depth map have a strong influence on the performance of view interpolation. However, most of existing view interpolation algorithms only emphasize hole filling of the warped color image. In this paper, a superpixel-based method is proposed for initial depth map enhancement and warped depth map hole filling. Firstly, the color image is segmented using simple linear iterative clustering (SLIC) algorithm, and after that, the associated depth map is segmented with the same label. Then, the depth-missing pixels are recovered by considering color and depth superpixel information jointly. Additionally, holes of the disocclusion regions in the warped depth map can also be filled efficiently via superpixel-based segmentation. Experimental results show that with the proposed method the quality of the interpolated view has been improved significantly in terms of both subjective and objective evaluations.

The paper presents an approach towards tracking and recognizing a set of predefined hand gestures from monocular image sequences. Firstly, a behavioral model of basic hand postures was depicted by mathematical expressions. Secondly, a behavioral model for hand posture tracking and hand posture tracking algorithm based on the behavioral model of hand postures were proposed. Finally, the proposed algorithm was compared and evaluated. Different from existing frame-based hand posture tracking, the proposed hand posture tracking targets at the tracking of users' behavioral model within a certain period. It is innovative because: (1) it discloses the relationship between the operational model and behavioral model and verifies that the operation model can be predicted and evaluated, (2) it uses the operational model to describe the dynamic system model of hand postures. The experimental results confirm the satisfying performance of the proposed algorithm in improving the tracking time, tracking accuracy and cognition load evaluation.

This paper reviewed the classification of hand-gesture recognition system on human-computer interactive method,discussed the commonly used algorithms,and estimated the current situation.Hand gesture recognition is a challenging interdisciplinary research project.At present,it has four methodological limitations in single-color,skin-color segmentation,wrist definition and manual initialization;furthermore,it cannot be applied to real-time recognition system.

Aiming at reducing particle numbers,starting from analyzing operators' cognitive model,a novel particle filtering hand gesture tracking approach is put forward.At first,operators' cognitive psychology during hand gesture operation processes is analyzed and a human hand motion dynamic model is established.Next,some fundamental characteristics of the dynamic model are studied and a description method is presented.Then,a status variable microstructure based hand gesture tracking algorithm is presented.Results show that,using only a small number of particles,comparatively accurate results can be obtained.

Virtual 3D hand is a natural and efficient tool of human-computer interaction (HCI), which is widely used in virtual reality (VR). In order to meet the needs of 3D Hand-based HCI, a novel platform is presented in this paper. Firstly, using cascade local coordinate systems and two direction vectors of hand, a new 3D hand model with a better design of thumb is developed. The presentation of articulated object is discussed in detail. Secondly, we demonstrate a method which synthetically utilizes the data glove and position tracker. According to the analysis of the rotating hand, we established the relationship between angles of position tracker and model parameters. Finally, the 3D Hand-based HCI platform using VC++ and OpenGL is presented. Experimental results show that, our 3D hand model can express a variety of gestures and the platform design is feasible and can meet our requirements. It also laid the foundation for free hand tracking.

In HCI (Human-Computer-Interaction), 3D hand-gesture tracking is a hot research topic. In this paper, the method of particle filter is used in 3D hand-gesture tracking; we also make some improvement based on this method. Our goal is to improve the precision of 3D hand-gesture tracking. In order to achieve the goal, we optimize the sampling method and the particles' weights. We also reduce the sampling error and obtain the proper number of sampling particles. The experimental results show that the improved algorithm is better than the traditional one in tracking effect, and the time consumption is lower. Compared with the traditional random sampling method, Gauss sampling method this paper used could improve the tracking precision. © 2010 Binary Information Press.

In order to satisfy the needs of 3D human hand tracking, a novel image features extraction algorithm with the purpose of improving precision is put forward in this paper. Firstly, the hand gesture contour is described with hand gesture polygons, which is divided into outer-polygons and inner-polygons in our study, and the algorithms for extracting outer-polygons and inner-polygons are presented respectively. Secondly, human gesture features are defined and the relationship between human gesture features and hand gesture polygons is explored. A great deal of experiments are completed. Our experimental results demonstrate that, compared with Lindeberg methods, our algorithm has capacity to extract more features, to obtain better accuracy and to use less time cost. Further more, our algorithm is effective for small size human hand images. © 2009 Binary Information Press.

3D hand gesture tracking is one of the key problems in human-computer interface design and has attracted increasing attention as an alternative way to traditional input devices, such as mouses and keyboards. Generally speaking, a human hand, as a typical articulated structure, has 15 joints and high dimensionality with 26DOFs, which makes it very difficult for real time tracking. A novel approach is presented in this paper. Firstly, a basic concept, sigma point, is defined, and the way to acquire the Sigma points of a state variable is presented and further proved in detail. Then, the global human hand tracking algorithm is put forward, which combine Sigma points and optimized selection based upon particle weights. In order to improve robustness to changing light conditions, a new skin model is proposed which is based on skin luminance. At last, our experimental results demonstrate that, compared with the classical particle filtering, our method has the capacity to use smaller number of particles for higher precision.

A novel sampling method is put forward in this paper. Firstly, under specific human-computer conditions, both cognitive psychology features of operators and motion features of the operators' hands are studied, upon which a basic assumption is made. Then, a sampling algorithm is put forward. Finally, in order to demonstrate validity and performance of our algorithm, a great deal of experiments is completed. By using fewer particles, compared with conventional particle filtering, the approach presented in this paper may achieve better tracking precision. In forms of both the theoretical analysis and a great deal of experimental results from real video data, just a few particles are needed to describe post probability distribution of state variables without reducing the tracking precision by our dimensionality reduction method.