Real-time directional stylization of images and videos

This paper describes a real-time non-photorealistic rendering system that automatically produces stylistic effects from photos and videos. The algorithm includes the capture of salient shapes in the image using a smooth direction field and the abstraction of both colors and shapes along the direction field. In addition to the directional stylization, the proposed algorithm has many good properties. First, the temporal coherence is preserved without any extra processing. Second, the level of abstraction can be controlled within constant time complexity. Last but not least, the parallel GPU implementation allows the real-time stylization of online videos. A variety of experimental results demonstrate the effectiveness of the system in producing high-quality abstract illustrations.     

A class of adaptive directional image smoothing filters

The gray level distribution around a pixel of an image usually tends to be more coherent in some directions compared to other directions. The idea of adaptive directional filtering is to estimate the direction of higher coherence around each pixel location and then to employ a window which approximates a line segment in that direction. Hence, the details of the image may be preserved while maintaining a satisfactory level of noise suppression performance. In this paper we describe a class of adaptive directional image smoothing filters based on generalized Gaussian distributions. We propose a measure of spread for the pixel values based on the maximum likelihood estimate of a scale parameter involved in the generalized Gaussian distribution. Several experimental results indicate a significant improvement compared to some standard filters.     

Real-time implementation of airborne inertial-SLAM

This paper addresses some challenges to the real-time implementation of Simultaneous Localisation and Mapping (SLAM) on a UAV platform. When compared to the implementation of SLAM in 2D environments, airborne implementation imposes several difficulties in terms of computational complexity and loop closure, with high nonlinearity in both vehicle dynamics and observations. An implementation of airborne SLAM is formulated to relieve this computational complexity in both direct and indirect ways. Our implementation is based on an Extended Kalman Filter (EKF), which fuses data from an Inertial Measurement Unit (IMU) with data from a passive vision system. Real-time results from flight trials are provided.     

Parallel implementation of sequential morphological filters

Many useful morphological filters are built as more or less long concatenations of erosions and dilations: openings, closings, size distributions, sequential filters, etc. An efficient implementation of these concatenations would allow all the sequentially concatenated operators run simultaneously, on the time-delayed data. A recent algorithm (see below) for the morphological dilation/erosion allows such inter-operator parallelism. This paper introduces an additional, intra-operator level of parallelism in this dilation/erosion algorithm. Realized in a dedicated hardware, for rectangular structuring elements with programmable size, such an implementation allows obtaining previously unachievable, real-time performances for these traditionally costly operators. Low latency and memory requirements are the main benefits when the performance is not deteriorated even for long concatenations or high-resolution images.     

Real-time Java simulations of multiple interference dielectric filters

An interactive Java applet for real-time simulation and visualization of the transmittance properties of multiple interference dielectric filters is presented. The most commonly used interference filters as well as the state-of-the-art ones are embedded in this platform-independent applet which can serve research and education purposes. The Transmittance applet can be freely downloaded from the site http://cpc.cs.qub.ac.uk.

Program summary

Program title: TransmittanceCatalogue identifier: AEBQ_v1_0Program summary URL:http://cpc.cs.qub.ac.uk/summaries/AEBQ_v1_0.htmlProgram obtainable from: CPC Program Library, Queen's University, Belfast, N. IrelandLicensing provisions: Standard CPC licence, http://cpc.cs.qub.ac.uk/licence/licence.htmlNo. of lines in distributed program, including test data, etc.: 5778No. of bytes in distributed program, including test data, etc.: 90 474Distribution format: tar.gzProgramming language: JavaComputer: Developed on PC-Pentium platformOperating system: Any Java-enabled OS. Applet was tested on Windows ME, XP, Sun Solaris, Mac OSRAM: VariableClassification: 18Nature of problem: Sophisticated wavelength selective multiple interference filters can include some tens or even hundreds of dielectric layers. The spectral response of such a stack is not obvious. On the other hand, there is a strong demand from application designers and students to get a quick insight into the properties of a given filter.Solution method: A Java applet was developed for the computation and the visualization of the transmittance of multilayer interference filters. It is simple to use and the embedded filter library can serve educational purposes. Also, its ability to handle complex structures will be appreciated as a useful research and development tool.Running time: Real-time simulations     

Finite difference implementation of distributed parameter filters

The numerical problems associated with the full three-dimensional (spatial) distributed parameter filters demand a novel technique that maintains accuracy and efficiency for the complex partial differential Riccati equation governing the filter variance. The filters can be successfully implemented by using numerical operators that can, in various ways, be factored. Use of the finite difference method having this property increases the accuracy and efficiency of the implementation.

This paper outlines a time-splitting technique for the numerical implementation of distributed parameter filters. The paper provides rationales to the square root and U-D factorizations of the distributed parameter filter by means of the time-splitting finite difference method.     

Periodic stabilization of look-ahead filters in VLSI implementation

A linear look-ahead filter is a model of digital dynamical systems and infinite impulse response filters for fast pipeline processing in very large scale integration (VLSI) implementation of the digital systems. Two essential problems to be dealt with in the design of look-ahead filters are stability and computational complexity of the filter. In this paper, a new periodic scheme is proposed to stabilize the d-step look-ahead filter and provide minimum amount of computation in digital implementation of the filter.     

OSNet: a neural network implementation of order statistic filters

A dedicated neural network model called OSNet which finds the kth largest element in an array of real numbers is proposed. Its overall processing time is constant irrespective of the number of elements in the array and is four times the processing time of a single neuron. Networks of this kind may be used as building blocks for hardware implementation of order statistic filters. Examples of using OSNet for implementing various order statistic filters and for sorting are shown.     

实时动态信息发布系统实现及发展

实时动态信息发布系统正是在这种背景环境下诞生的一种新型的媒体发布应用系统。实时动态信息发布系统是一种通过数字化音、视频多媒体处理,通过网络实现远程多点分布式播放和集中管理控制的系统,播放的信息是实时动态系统;一个操作员可以集中建立、编辑和分配内容给网络环境中的数量庞大的显示终端,即实现一台服务器集中管理,向多个不同场所地点的显示终端发布实时动态的多媒体信息。     

Real-time automatic recognition of omnidirectional multiple barcodes and DSP implementation

Barcodes have been extensively adopted in daily life, such as in merchandise labels, inventory control, storage/retrieval systems and inspection. Computer-vision-based barcode recognition can definitely facilitate barcode reading, especially for multiple barcodes and free orientation and in complex scenarios. This work, presents an automatic barcode detection and recognition algorithm for multiple and rotation invariant barcode decoding. The proposed system comprises three stages. First, the barcode is extracted by coarse-to-fine segmentation in four steps: background small clutter reduction, candidate barcode segmentation, barcode verification and barcode rotation and regularization. To enhance the barcode region, thin and small background noise clusters are eliminated using Max–Min Differencing. The approach combines several image-processing schemes, namely Gaussian smoothing filtering, connected component analysis, orientation homogeneity, moment analysis and iterative thresholding. The second stage decodes the barcode by scanning multiple traversal lines, thus preventing decoding errors due to minor barcode defects. Finally, the proposed system is implemented and optimized on a DM6437 DSP EVM board. Experimental results indicate that the proposed approach can locate multiple and omnidirectional barcodes, even with a complex background and minor distortion. The recognition rates for 10,395 lottery barcodes and 388 merchandise barcodes are 99.74 and 90.7%, respectively. The proposed system is promising and has been successfully adopted in commercial applications of lottery reading and verification of winning numbers.     

AVS全I帧视频编码器的FPGA实时实现

AVS视频编码标准是我国自主知识产权的信源编码标准。完成了AVS视频编码器在FPGA平台上的设计与实现。考虑硬件平台的结构特点,采用可重用设计和流水线设计对编码器进行优化,保证了流水线的高效运行以及硬件资源的最优利用。通过ISE软件仿真和Xilinx公司Vritex-4 pro平台验证,最高工作频率可达110 MHz,满足CIF分辨率下I帧在FPGA硬件平台的实时编码要求。     

Design and implementation of embedded computer vision systems based on particle filters

Particle filtering methods are gradually attaining significant importance in a variety of embedded computer vision applications. For example, in smart camera systems, object tracking is a very important application and particle filter based tracking algorithms have shown promising results with robust tracking performance. However, most particle filters involve vast amount of computational complexity, thereby intensifying the challenges faced in their real-time, embedded implementation. Many of these applications share common characteristics, and the same system design can be reused by identifying and varying key system parameters and varying them appropriately. In this paper, we present a System-on-Chip (SoC) architecture involving both hardware and software components for a class of particle filters. The framework uses parameterization to enable fast and efficient reuse of the architecture with minimal re-design effort for a wide range of particle filtering applications as well as implementation platforms.     

The design and implementation of multiplierless nonrecursive linear phase discrete time filters

This paper develops techniques for the design and implementation of linear phase discrete time filters that are implemented using only delays, adds and subtracts. Sometimes called discrete time linear phase transport processors, these filters have finite length integer valued impulse responses. The design technique developed in this paper determines an optimal integer valued impulse response that minimizes the mean square error in the filter's passband and stopband while bounding the impulse response values to a specified value. The implementation technique developed in this paper generates a structure that can realize integer valued impulse responses using only delays, adds and substracts.     

基于定点DSP的MP3实时解码器的设计与实现

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。     

Real-time detection of changes in network with OpenFlow based on NetFPGA implementation

Sketch-based algorithms are extensively applied in a wide range of networking applications. This work develops the compact implementation of a system for detecting changes in traffic in real time with OpenFlow on a NetFPGA 1G (4 × 1G) platform. The system can monitor network traffic at a line rate of up to 4 Gbps with the required detection accuracy needed with limited memory on-board. The system utilizes a one-pass method to determine when the flow exceeds a predefined threshold. Based on the flow IDs identified, actions are issued immediately to switches to respond properly according to the OpenFlow protocol.     

前视声纳实时成像算法与DSP实现

前视声纳通道数目多、采样频率高,获取方位和距离信息的运算量大,对原始回波图像显示质量和速度提出非常高的要求.通过分析坐标变换和像素亮度填充法对成像质量的影响,根据系统指标设计了前视声纳视域范围内回波数据的显示算法,解决了声纳原始图像的显示质量问题;利用DSP丰富接口资源和EDMA动态调表技术,设计了声纳原始图像实时显示方案,很大程度上突破了实时显示的瓶颈.通过水池拉距实验验证了高质量实时显示方案的有效性.     

Real-time implementation of a dynamic fuzzy neural networks controller for a SCARA

This paper presents the design, development and implementation of a Dynamic Fuzzy Neural Networks (D-FNNs) Controller suitable for real-time industrial applications. The unique feature of the D-FNNs controller is that it has dynamic self-organising structure, fast learning speed, good generalisation and flexibility in learning. The approach of rapid prototyping is employed to implement the D-FNNs controller with a view of controlling a Selectively Compliance Assembly Robot Arm (SCARA) in real time. Simulink, an iterative software for simulating dynamic systems, is used for modelling, simulation and analysis of the dynamic system. The D-FNNs controller was implemented through Real-Time Workshop (RTW). RTW generates C-codes from the Simulink block diagrams and in turn, the generated codes (object codes) are downloaded to the dSPACE DS1102 floating-point processor, together with the supporting files, for execution. The performance of the D-FNNs controller was found to be superior and it matches favourably with the simulation results.     

On the implementation and effectiveness of morphological close-open and open-close filters for topology optimization

The design of physical (plant) and control aspects of a dynamic system have traditionally been treated as two separate problems, often solved in sequence. Optimizing plant and control design disciplines separately results in sub-optimal system designs that do not capitalize on the synergistic coupling between these disciplines. This coupling is inherent in most actively controlled dynamic systems, including wind turbines. In this case structural and control design both affect energy production and loads on the turbine. This article presents an integrated approach to achieve system-optimal wind turbine designs using co-design, a design methodology that accounts directly for the synergistic coupling between physical and control system design. A case study, based on multidisciplinary simulation, is presented here that demonstrates a promising increase (up to 8%) in annualized wind turbine energy production compared to the results of a conventional sequential design strategy. The case study also revealed specific synergistic mechanisms that enable performance improvements, which are accessible via co-design but not sequential design.