共查询到20条相似文献,搜索用时 15 毫秒
1.
2.
3.
A hand posture recognition system using 3D data is described. The system relies on a novel 3D sensor that generates a dense range image of the scene. The main advantage of the proposed system, compared to other gesture recognition techniques, is the capability for robust unconstrained recognition of complex hand postures such as those encountered in sign language alphabets. This is achieved by explicitly utilizing 3D hand geometry. Moreover, the proposed approach does not rely on color information, and guarantees robust segmentation of the hand under varying illumination conditions, and scene content. Several novel 3D image analysis algorithms are presented, covering the complete processing chain: 3D image acquisition, arm segmentation, hand–forearm segmentation, hand pose estimation, 3D feature extraction, and gesture classification. The proposed system is extensively evaluated. 相似文献
4.
5.
FD216是智原科技公司出品的一款结构与ADI公司的ADSP-2181相类似且指令集相兼容的高性价比16位定点DSP芯片。利用智原科技公司提供的开发工具包,可以方便地将C算法移植到FD216中。详细介绍了在FD216评估板上用嵌入式C语言和汇编语言混合编程的方法设计并实现基于定点DSP的MP3实时解码器的整个流程。 相似文献
6.
Chang-Beom ParkSeong-Whan Lee 《Image and vision computing》2011,29(1):51-63
In this paper, we present a real-time 3D pointing gesture recognition algorithm for mobile robots, based on a cascade hidden Markov model (HMM) and a particle filter. Among the various human gestures, the pointing gesture is very useful to human-robot interaction (HRI). In fact, it is highly intuitive, does not involve a-priori assumptions, and has no substitute in other modes of interaction. A major issue in pointing gesture recognition is the difficultly of accurate estimation of the pointing direction, caused by the difficulty of hand tracking and the unreliability of the direction estimation.The proposed method involves the use of a stereo camera and 3D particle filters for reliable hand tracking, and a cascade of two HMMs for a robust estimate of the pointing direction. When a subject enters the field of view of the camera, his or her face and two hands are located and tracked using particle filters. The first stage HMM takes the hand position estimate and maps it to a more accurate position by modeling the kinematic characteristics of finger pointing. The resulting 3D coordinates are used as input into the second stage HMM that discriminates pointing gestures from other types. Finally, the pointing direction is estimated for the pointing state.The proposed method can deal with both large and small pointing gestures. The experimental results show gesture recognition and target selection rates of better than 89% and 99% respectively, during human-robot interaction. 相似文献
7.
8.
介绍了一种应用在TI TMSB20C64xx系列DSP上的实时调度模块,该模块任务调度机制使用传统的前后台模式。具有运行效率高、占用资源少的特点,很适合作为任务控制不是特别复杂的实时应用软件的底层调度平台。提供了一种使用DSP/BIOS之外的选择。 相似文献
9.
10.
11.
指势行为识别作为一种理想的人机交互模式,而指势手指有效分割与指尖提取是关键。采用基于背景差分方法提取前景运动目标并消除背景影响,运用肤色分割方法,提取运动目标脸部、手部区域。在确定指势手与人脸位置关系的基础上,基于指势行为中指尖位于指势手的边沿轮廓,从指势手的外界矩形框与轮廓的交接点中定位指尖点。经实验证明该算法快速有效、提取精度高,且有一定的鲁棒性。 相似文献
12.
针对Ethernet通信响应的不确定性这个缺点,对实现CAN总线网络与Ethernet数据实时通信做了深入的研究,提出了CAN总线网络与Ethernet数据实时通信方案。采用当今最先进的DSP技术,从硬件和软件设计两个方面提出了可行策略,保证网络高速率通信及实时性。 相似文献
13.
提出了基于定点DSP的人工混响算法实时处理系统.讨论了DSP芯片TMS320VC5509与音频编解码芯片TLV320A-IC23的硬件接口和软件设计.并在此基础上论述人工混响算法实时播放的设计方法和工作原理,最后提出系统实时性实现的 相似文献
14.
15.
高性能DSP与高速实时信号处理 总被引:1,自引:0,他引:1
吴楚舒 《计算机与数字工程》2004,32(4):48-50,81
简要概述了DSP的性能和特点,然后详细介绍了DSP应用软件结构,并对DSP应用的未来趋势——DSP和RTOS的结合进行了初步分析。 相似文献
16.
17.
Yaw-Huei Hwang Ching-Hsyang Wang Huey-Wen Liang Jer-Junn Luh 《International Journal of Industrial Ergonomics》2009,39(5):681-688
This study reports on the development of the pointing device activity monitoring software, Mlog, which is used to assess elements of computer use such as pointing device use time. The Mlog monitoring program was written with Virtual C++ and is 1.59 MB in size. It is applicable for computers equipped with computer processing units (CPUs) of 1 GHz or faster, and records pointing device activity at the millisecond level. The accuracy, precision, and reliability of the Mlog monitoring program were tested by comparing Mlog-recorded activity time intervals, for example, the time interval between pressing and releasing the pointing device key, against oscilloscope-recorded pointing device electric signals. For most tested time intervals, the Mlog monitoring program's margin of error for accuracy was within ±0.50%, and it boasted precision error rate of less than 1.00%. Correlation coefficients between the Mlog recordings and the references were all greater than 0.99905, with the highest values observed for dragging actions. For most tested time intervals, the results of the reliability test showed that their intraclass correlation coefficients were higher than 0.95, with few less than 0.90 for those with relatively longer tested time intervals. Linear regression analyses indicated that the pointing device clicking action time intervals recorded by the Mlog monitoring program were very close to the reference values and not affected by CPU speed and memory capacity, computer system loadings of software programs in operation, or types of pointing device key action. In conclusion, the Mlog monitoring program was validated as an accurate tool for monitoring pointing device activity during computer work. Future study is warranted to examine the influences of idle time threshold for electronic activity monitoring, passive computer tasks, and job type on the performance of the program in field studies.
Relevance to industry
The Mlog monitoring program was validated as accurate in measuring pointing device activity during computer work, providing an indirect and supplemental exposure indices for those traditional ergonomic measurements for physical loading assessment. 相似文献18.
19.
一种基于FPGA和DSP的视频处理系统 总被引:3,自引:1,他引:3
该文介绍了一种基于现场可编程门阵列(FPGA)和数字信号处理器(DSP)的实时视频处理系统,此系统以FPGA为数据缓冲和逻辑控制单元,DSP为图像数据处理单元.该文介绍了此视频处理系统的整体结构,详细讨论了从色空间RGB到YCbCr的转换,并给出了转换前后的图像对照.同时也介绍了视频数据流的缓冲处理,以及DSP和FPGA轮流对双口RAM的控制,最后介绍了用DSP实现图像压缩的过程.通过此系统的实现可以看出,使用FPGA实现视频处理系统的控制,可以提高系统的性能,同时使得系统的适应性和灵活性强,设计调试方便. 相似文献
20.
在研究视频图像实时处理系统的基础上,以TI公司的DSP芯片(TMS320C5000)为硬件开发平台,以Code Composer Studio为软件开发环境,通过硬件设计和软件编程实现视频图像中动态目标的获取、边缘检测;针对传统实现方法的长延时实时处理性差等不足,文章利用CCS对程序中的关键代码进行了优化,并在仿真系统的实验平台上进行了调试;结果证明系统的软件的运行效率得到了提高,达到了实时性的要求;该系统结合了软件算法的灵活性和硬件DSP的高速度,能够对视频图像进行真正意义上的实时处理。 相似文献