基于立体视觉的非穿戴指势识别方法

基于彩色图像中红、绿、蓝3分量强度在阴影区域存在差异,根据小波变换在时域和空域均具有优异的局部化特征,结合背景差分,进行小波多尺度变换,提取视频指势对象,所提方法不需场景学习与训练、手工校正及先验假设等信息,可克服动态场景变化、阴影、噪声干扰等影响,具有强的鲁棒性.基于人类生物结构特征,采用不易遮挡和不受人脸朝向、姿态、光照变化等影响的头项特征代替人眼特征,保证了人机交互活动的自由性和自然性,且提高了人机交互的时效性.融合手指尖特征和手臂中心轴线及其外极线的多几何约束策略,采用求解反对应方法.确保手指特征匹配对应的正确性.通过实验验证,证实了上述方法有效、可行,可应用于实时、非穿戴的自然指势视觉3维人机交互中.     

LHMM熵的聚众事件实时检测

提出一种结合分层隐马尔科夫模型(LHMM)与熵值的聚众事件实时检测方法。使用长宽比消除前景中其他物体的影响,以区域中的人数和总速度为观察值,分2层训练出聚众事件的LHMM。当观察值序列与模型的相似度大于设定阈值时,利用光流法计算该帧熵值,若熵值大于设定阈值,则表示发生聚众事件;否则,为非聚众事件,继续下一帧的处理。实验结果表明,该方法具有较高的识别率和较好的鲁棒性。     

Real-time robust vision-based hand gesture recognition using stereo images

This paper presents a real-time and robust approach to recognize two types of gestures consisting of seven motional gestures and six finger spelling gestures. This approach utilizes stereo images captured by a stereo webcam to achieve robust recognition under realistic lighting conditions and in various backgrounds. It incorporates several existing computationally efficient techniques and introduces a rule-based approach to merge the information from a pair of stereo images leading to an improved hand detection compared to using single images. The results obtained indicate that high recognition rates under realistic conditions are obtained in real-time on PC platforms at the rate of 30 frames per second. It is shown that its outcome is comparable to two existing approaches while it is computationally more efficient than these approaches.     

基于小波域的视频压缩编码MRME算法的研究

小波变换将视频帧分解为一系列的不同频带的子图像,在该方法中,高分辨率的运动矢量由低分辨率的运动矢量预测,并且在每一步都要进行矢量修正.为了进一步提高运动补偿的效率,提出了一种只对运动区域进行运动补偿的多分辨率运动补偿(MRME)算法,根据当前帧和参考帧小波系数,运动区域由自适应的运动检测算法得到,实验结果表明,这种方法在运算时间、信噪比和码长度方面都得到了令人满意的结果.     

基于低比特率视频序列的运动对象分割算法

在兼顾运动图像分割效果和实时性的原则上,针对视频会议、新闻播报等低比特率视频序列,提出了一种简单高效的运动对象分割算法。首先利用累积帧差求出图像帧的运动区域,然后对其进行二值化和形态学处理得到帧差模板,最后利用二次扫描的方法得到运动对象掩模,对其进行填充就可以提取出运动对象。实验证明得到了较好的分割效果并且在实时性的应用中具有一定的优势。     

An enhanced algorithm for improving real-time video transmission for tele-training education

Tele-training in surgical education has not been effectively implemented. There is a stringent need for a high transmission rate, reliability, throughput, and reduced distortion for high-quality video transmission in the real-time network. This work aims to propose a system that improves video quality during real-time surgical tele-training. The proposed approach aims to minimise the video frame’s total distortion, ensuring better flow rate allocation and enhancing the video frames’ reliability. The proposed system consists of a proposed algorithm for Enhancing Video Quality, Distorting Minimization, Bandwidth efficiency, and Reliability Maximization called (EVQDMBRM) algorithm. The proposed algorithm reduces the video frame’s total distortion. In addition, it enhances the video quality in a real-time network by dynamically allocating the flow rate at the video source and maximizing the transmission reliability of the video frames. The result shows that the proposed EVQDMBRM algorithm improves the video quality with the minimized total distortion. Therefore, it improves the Peak Signal to Noise Ratio (PSNR) average by 51.13 dB against 47.28 dB in the existing systems. Furthermore, it reduces the video frames processing time average by 58.2 milliseconds (ms) against 76.1, and the end-to-end delay average by 114.57 ms against 133.58 ms comparing to the traditional methods. The proposed system concentrates on minimizing video distortion and improving the surgical video transmission quality by using an EVQDMBRM algorithm. It provides the mechanism to allocate the video rate at the source dynamically. Besides that, it minimizes the packet loss ratio and probing status, which estimates the available bandwidth.

     

基于帧缓冲队列的边缘视频处理加速方法

由于边缘设备的计算能力有限,处理高分辨率、高帧率的视频时极易造成帧堆积。同时,视频参数的多样性也会影响视频处理的效果,需要自适应调整系统参数以保证视频处理性能。针对视频处理的帧堆积问题提出了在帧接收和帧处理间加入缓冲区即帧缓冲队列的方法,来并行处理缓冲帧,以解决帧接收时延问题,加速视频处理。实验结果表明,帧缓冲队列解决了边缘视频处理系统丢帧问题,满足帧实时处理的同时,降低了系统功耗,提高了实时处理边缘视频数据的能力。     

Real-time gesture recognition by learning and selective control of visual interest points

For the real-time recognition of unspecified gestures by an arbitrary person, a comprehensive framework is presented that addresses two important problems in gesture recognition systems: selective attention and processing frame rate. To address the first problem, we propose the Quadruple Visual Interest Point Strategy. No assumptions are made with regard to scale or rotation of visual features, which are computed from dynamically changing regions of interest in a given image sequence. In this paper, each of the visual features is referred to as a visual interest point, to which a probability density function is assigned, and the selection is carried out. To address the second problem, we developed a selective control method to equip the recognition system with self-load monitoring and controlling functionality. Through evaluation experiments, we show that our approach provides robust recognition with respect to such factors as type of clothing, type of gesture, extent of motion trajectories, and individual differences in motion characteristics. In order to indicate the real-time performance and utility aspects of our approach, a gesture video system is developed that demonstrates full video-rate interaction with displayed image objects.     

基于深度学习的SAR目标识别DSP设计

SAR图像目标识别主要针对桥梁、机场等战略军事目标以及飞机、坦克、汽车等战术目标,进行精确的识别分类及定位,是SAR图像解译的重要一环。首先,构建C6678的卷积神经网络主要处理层,然后结合C6678的处理及存储特性,对卷积层和网络调度进行优化设计,完成了YOLOv3-TINY目标识别网络在C6678上的设计实现方法。该方法能够对常用卷积神经网络模型进行重构及修改,解决了C6678等多核DSP处理平台运行深度学习网络的难题。实验结果表明,该方法在检测性能上与GPU一致,考虑到机载SAR的实时图像帧率,虽然该方法在C6678的实时性能相对GPU还有较大差距,但其能够满足机载SAR实时处理需求。     

Fast buffering for FPGA implementation of vision-based object recognition systems

Real-time frame rate is an important factor for practical deployment of computer vision systems. Field programmable gate array (FPGA) technology has been considered for many applications due to its parallel computing capability. FPGA implementations of computer vision algorithms normally involve buffering data on external memory devices, which could slow down the whole system. This paper proposes a buffering scheme suitable for implementing real-time vision-based systems on an FPGA that does not require external memory to buffer data. A stop sign detection system implemented on an FPGA employing the proposed buffering scheme is presented as an example system. This system is capable of processing over 200?fps at the frame size of 480?×?752 pixels.     

基于主体的自适应视频传输系统

为及时评估网络的状况，动态调整发送帧率，保证视频传输的最佳服务质量，该文以反应型主体模型为指导，应用基于消息的行为组织方法维护主体行为模型的消息一行为准则，并考虑了多主体并行以及协调与协作等特点，设计了基于主体的具适应性视频传输系统。此系统中采用了实时传输协议，根据客户主体的反馈信息预测网络状况并据此实现对发送帧率的动态调整。     

Calibration-free augmented reality

Camera calibration and the acquisition of Euclidean 3D measurements have so far been considered necessary requirements for overlaying three-dimensional graphical objects with live video. We describe a new approach to video-based augmented reality that avoids both requirements: it does not use any metric information about the calibration parameters of the camera or the 3D locations and dimensions of the environment's objects. The only requirement is the ability to track across frames at least four fiducial points that are specified by the user during system initialization and whose world coordinates are unknown. Our approach is based on the following observation: given a set of four or more noncoplanar 3D points, the projection of all points in the set can be computed as a linear combination of the projections of just four of the points. We exploit this observation by: tracking regions and color fiducial points at frame rate; and representing virtual objects in a non-Euclidean, affine frame of reference that allows their projection to be computed as a linear combination of the projection of the fiducial points. Experimental results on two augmented reality systems, one monitor-based and one head-mounted, demonstrate that the approach is readily implementable, imposes minimal computational and hardware requirements, and generates real-time and accurate video overlays even when the camera parameters vary dynamically     

实时文本分类系统的研究与实现

分析文本分类过程中影响实时性的因素,即分词处理高耗时和特征空间维数过高问题。结合网页过滤的实时应用提出一种实时文本分类方法,弱化分词处理过程,降低特征空间维数,以提高分类速度。通过优化特征项选取维持分类效果,基于贝叶斯理论实现实时文本分类系统。实验结果表明,该方法在维持精确率和召回率分别为85%, 94%的情况下,显著提高了分类速度。     

Video-rate digital image analysis equipment

In parallel cellular arrays the same instruction may be executed on many pixels in parallel. Some commercially available systems use an alternative approach in which the same instruction is executed on many pixels serially, at approximately 10⁷ pixels s⁻¹: this is known as video-rate processing. Besides table look-up and arithmetical operations, ambitious connectivity-based image analysis is performed at video rates in commercially available equipment. For example, a histogram showing how many separate connected regions have what area can be obtained in one video frame time. This paper reviews various video-rate techniques, and proposes a microprocessor technique for video-rate connectivity-based analysis. Graphics capabilities such as roam and movie are not reviewed.     

Fusion of Band Limited Phase Only Correlation and Width Centroid Contour Distance for finger based biometrics

In this paper, a new approach of multimodal finger biometrics based on the fusion of finger vein and finger geometry recognition is presented. In the proposed method, Band Limited Phase Only Correlation (BLPOC) is utilized to measure the similarity of finger vein images. Unlike previous methods, BLPOC is resilient to noise, occlusions and rescaling factors; thus can enhance the performance of finger vein recognition. As for finger geometry recognition, a new type of geometrical features called Width-Centroid Contour Distance (WCCD) is proposed. This WCCD combines the finger width with Centroid Contour Distance (CCD). As compared with the single type of feature, the fusion of W and CCD can improve the accuracy of finger geometry recognition. Finally, we integrate the finger vein and finger geometry recognitions by a score-level fusion method based on the weighted SUM rule. Experimental evaluation using our own database which was collected from 123 volunteers resulted in an efficient recognition performance where the equal error rate (EER) was 1.78% with a total processing time of 24.22 ms.     

适用于临床实时出图的准静态弹性成像系统设计

为了在临床中能够获得实时稳定出图且分辨率高的准静态弹性成像,在弹性成像系统设计中加入了帧对构造模块、帧对筛选模块、弹性计算模块以及弹性帧相关处理模块;在帧对构造和帧对筛选模块中设计了帧对预筛选方案及评估方法,能够以较少的计算量实现对错误帧对数据的自动剔除,一方面减少了对操作手法的依赖,另一方面促进为了弹性图像输出稳定;弹性计算模块中采用二维自相关算法进行弹性应变值的计算,可以实现高分辨率弹性成像;弹性帧相关处理模块对多帧弹性图像做帧相关处理,进一步确保弹性图像输出稳定;临床乳腺及甲状腺病变检测结果表明,该系统设计方案可以实现帧率达18帧每秒的实时稳定、高分辨率(1.5 mm)弹性成像输出,且能够为临床医生提供有价值的辅助诊断信息。     

基于模型切换的自适应背景建模方法

提出了一种基于模型切换的背景建模方法 (MSBM). 该方法以熵图像为纽带, 实现了不同精细程度的背景模型在空间上的自适应选取和在时间上的自适应切换. 对于亮度分布复杂度高的背景区域采用精细的模型以保证运动目标检测的精度, 反之采用简单的模型以降低计算量. 通过模型结构自适应结合参数自适应, 很好地兼顾了检测精度和计算代价. 基于高斯混合模型和时间平均模型的双模型切换式运动目标检测算法被用于实验研究, 结果表明这种算法的检测效果和单独采用高斯混合模型的检测效果相当, 而计算速度却比后者提高很多.     

Estimation of pointing poses for visually instructing mobile robots under real world conditions

In this paper, we present an approach for directing a mobile robot under real-world conditions into a target position by means of pointing poses only. Because one important objective of our work is the development of a low-cost platform, only monocular vision at web-cam level should be employed. Our previous approach presented in Gross et al. (2006) [1], Richarz et al. (2007) [2] has been improved by several additional processing steps. Finally, a background subtraction technique and a histogram equalization have been integrated in the preprocessing stage to be able to work in environments with structured backgrounds and under variable lighting conditions. Furthermore, a discriminant analysis was used to find the most relevant input features for the pointing pose estimator. The contribution of this paper is, however, not only the presentation of an approach to estimating pointing poses in a demanding real-world scenario on a mobile robot, but also the detailed and evaluative comparison between different image-preprocessing techniques, alternative feature extraction methods, and several function approximators with the same set of test- and training data. Reasonable combinations of the different methods are tested, and for each component on the processing chain the effect on the accuracy of the target estimation is quantized. The approach presented in this paper has been implemented on the mobile interaction robot Horos to determine the performance and estimation accuracy under real-world conditions. Furthermore, we compared the accuracy of our approach with that of humans performing the same estimation task, and achieved very comparable results for the best estimator.     

Sparse Bayesian learning for efficient visual tracking

This paper extends the use of statistical learning algorithms for object localization. It has been shown that object recognizers using kernel-SVMs can be elegantly adapted to localization by means of spatial perturbation of the SVM. While this SVM applies to each frame of a video independently of other frames, the benefits of temporal fusion of data are well-known. This is addressed here by using a fully probabilistic relevance vector machine (RVM) to generate observations with Gaussian distributions that can be fused over time. Rather than adapting a recognizer, we build a displacement expert which directly estimates displacement from the target region. An object detector is used in tandem, for object verification, providing the capability for automatic initialization and recovery. This approach is demonstrated in real-time tracking systems where the sparsity of the RVM means that only a fraction of CPU time is required to track at frame rate. An experimental evaluation compares this approach to the state of the art showing it to be a viable method for long-term region tracking.     

投票表决算法在高帧频图像处理中的应用

针对目前高帧频图像处理方法中软件速度慢、实时性差、专用硬件开发周期长、灵活性差等缺陷,开发完成了基于FPGA的高帧频图像硬件实时处理系统。该系统采用投票表决算法,压缩了存储和处理的数据量,充分发挥FPGA器件的并行特性,使图像采集与图像处理并行完成,提高了图像处理速度。系统已成功应用于高速轨道检测车的钢轨断面图像实时动态处理和分析。