Cellular neural networks with opposite‐sign templates for image thinning

This paper presents image thinning algorithms using cellular neural networks (CNNs) with one‐ or two‐dimensional opposite‐sign templates (OSTs) as well as non‐unity gain output functions. Two four‐layer CNN systems with one‐dimensional (1‐D) OSTs are proposed for image thinning with 4‐ or 8‐connectivity, respectively. A CNN system, which consists of an eight‐layer CNN with two‐dimensional (2‐D) OSTs followed by another four‐layer CNN with 2‐D OSTs, is constructed for image thinning with 8‐connectivity, in which designs of B‐ and I‐templates are simpler than in CNNs with 1‐D OSTs. In the aforementioned designs, parameter values of 1‐D OSTs are chosen to make CNNs operate with thinning‐like property 1 (TL‐1), and those of 2‐D OSTs with 2‐D thinning‐like property (2‐DTL). Simulation studies show that these CNN systems have a good image thinning performance. Copyright © 1999 John Wiley & Sons, Ltd.     

Watermarking on CNN‐UM for image and video authentication

In this paper a new approach to fragile watermarking technique is introduced. This problem is particularly interesting in the field of modern multimedia applications, when image and video authentication are required. The approach exploits the cellular automata suitability to work as pseudorandom pattern generators and extends the related algorithms under the framework of the cellular non‐linear networks (CNNs). The result is a novel way to perform watermarking generation in real time, using the presently available CNN‐universal chip prototypes. In this paper, both the CNN algorithms for fragile watermarking as well as on‐chip experimental results are reported, confirming the suitability of CNNs to successfully act as real‐time watermarking generators. The availability of CNN‐based visual microprocessors allows to have powerful algorithms to watermark in real time images or videos for efficient smart camera applications. Copyright © 2004 John Wiley & Sons, Ltd.     

Guiding a mobile robot with cellular neural networks

We show how cellular neural networks (CNNs) are capable of providing the necessary signal processing needed for visual navigation of an autonomous mobile robot. In this way, even complex feature detection and object recognition can be obtained in real time by analogue hardware, making fully autonomous real‐time operation feasible. An autonomous robot was first simulated and then implemented by simulating the CNN with a DSP. The robot is capable of navigating in a maze following lines painted on the floor. Images are processed entirely by a CNN‐based algorithm, and navigation is controlled by a fuzzy‐rule‐based algorithm. Copyright © 2002 John Wiley & Sons, Ltd.     

A rigorous design method for binary cellular neural networks

In order to be able to take full advantage of the great application potential that lies in cellular neural networks (CNNs) we need to have successful design and learning techniques as well. In almost any analogic CNN algorithm that performs an image processing task, binary CNNs play an important role. We observed that all binary CNNs reported in the literature, except for a connected component detector, exhibit monotonic dynamics. In the paper we show that the local stability of a monotonic binary CNN represents sufficient condition for its functionality, i.e. convergence of all initial states to the prescribed global stable equilibria. Based on this finding, we propose a rigorous design method, which results in a set of design constraints in the form of linear inequalities. These are obtained from simple local rules similar to that in elementary cellular automata without having to worry about continuous dynamics of a CNN. In the end we utilize our method to design a new CNN template for detecting holes in a 2D object. © 1998 John Wiley Sons, Ltd.     

基于DSP的石油管道焊缝检测机器人系统

随着DSP处理能力的不断增强以及图像处理算法的日益完善,开发基于机器视觉的嵌入式实时系统成为目前图像处理领域一项重要分支.本文提出了一种基于DSP(TMS320DM642)的石油管道焊缝检测机器人系统,用于完成高性能的石油管道焊缝的实时自动定位和检测任务;介绍了机器人系统的工作原理,硬件系统原理;阐述了系统的焊缝识别算法和基于RF5参考架构的软件框架设计方案.经验证,该识别算法可靠、稳定、实时性好,能满足石油管道焊缝检测机器人系统对焊缝快速准确定位的要求.     

A programmable VLSI architecture based on multilayer CNN paradigms for real-time visual processing

A new digital VLSI architecture has been presented for the implementation of discrete-time multilayer CNNs. At functional level, the architecture is organized as 12 layers of 64 × 64 cells which interact as specified by a set of 3D generalized templates. At structural level the application of cloning templates occurs in a set of processing units programmed by instruction masks, generated on the basis of the algorithm to be emulated. It is demonstrated that this architecture is applicable to multilayer algorithms for visual processing and also to standard CNNs, including those that use sequences of templates or that work in parallel. Simulations evidence the high efficiency of this implementation.     

Uncalibrated Workpiece Positioning Method for Peg-in-hole Assembly Using an Industrial Robot

This paper proposes an uncalibrated workpiece positioning method for peg-in-hole assembly of a device using an industrial robot. Depth images are used to identify and locate the workpieces when a peg-in-hole assembly task is carried out by an industrial robot in a flexible production system. First, the depth image is thresholded according to the depth data of the workpiece surface so as to filter out the background interference. Second, a series of image processing and the feature recognition algorithms are executed to extract the outer contour features and locate the center point position. This image information, fed by the vision system, will drive the robot to achieve the positioning, approximately. Finally, the Hough circle detection algorithm is used to extract the features and the relevant parameters of the circular hole where the assembly would be done, on the color image, for accurate positioning. The experimental result shows that the positioning accuracy of this method is between 0.6-1.2 mm, in the used experimental system. The entire positioning process need not require complicated calibration, and the method is highly flexible. It is suitable for the automatic assembly tasks with multi-specification or in small batches, in a flexible production system.     

Cellular non‐linear networks for minimization of functionals. Part 2: Examples

A method for the definition of cellular non‐linear networks able to find approximate minima of rather a large class of continuous functionals is illustrated through three examples. The method, based on the spatial discretization of continuous functionals and on the theory of potential functions for resistive circuits, has been presented in Part 1 of this paper. The first example (related to electromagnetic‐field theory) has the main purpose to show some aspects of the application procedure. The other two examples concern, respectively, a possible image‐processing application of the method (where a parallel processing is highly desirable) and a comparison with another method proposed in the literature on CNNs. Copyright © 2001 John Wiley & Sons, Ltd.     

A method for the approximate synthesis of cellular non‐linear networks—Part 2: Circuit reduction

In this paper, we face the problem of model reduction in piecewise‐linear (PWL) approximations of non‐linear functions. The reduction procedure presented here is based on the PWL approximation method proposed in a companion paper and resorts to a strategy that exploits the orthonormality of basis functions in terms of a proper inner product. Such a procedure can be favourably applied to the synthesis of the resistive parts of cellular non‐linear networks (CNNs) to reduce the complexity of the resulting circuits. As an example, the method is applied to a case study concerning a CNN for image processing. Copyright © 2003 John Wiley & Sons, Ltd.     

Genetic Matrix Algorithm; Simultaneous Optimization of Structure and Numerical Parameters

Genetic Algorithm is often used to optimize numerical parameters, and Genetic Programming is used to optimize structure. However, optimizing both structure and numerical parameters simultaneously is quite difficult. Many different algorithms have been developed with the goal of optimizing both structure and numerical parameters simultaneously. However, those algorithms are not satisfactory in the sight of simultaneous optimization. We developed a new algorithm named Genetic Matrix Algorithm (GMA), which can evolve structure and numerical parameters simultaneously. The new algorithm, GMA, can evolve tree‐structured programs, which include numerical parameters in each of the nonterminal nodes. In this paper, we apply GMA to evolve image processing algorithms. Experimental results show that we can construct new useful image processing algorithms, which cannot be constructed using only fixed thresholds. Copyright © 2007 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Wavelets for contrast enhancement of digital mammography

Multiresolution representations provided an adaptive mechanism for the local emphasis of features of importance to mammography. In general, improvements in image contrast for multiscale image processing algorithms were superior to those obtained using existing competitive algorithms. These initial results are encouraging and suggest that wavelet based image processing algorithms could play an important role in improving the imaging performance of digital mammography. In part 2, features blended into the mammograms were "idealized" representations of the types of objects that are of primary interest to mammographers. The resultant mammographic images were appropriate for the purpose of demonstrating improved image contrast made possible by wavelet based image processing algorithms. These images were also useful for comparing multiscale wavelet based algorithms with existing image processing algorithms. The test results obtained in this study, however, cannot be directly extrapolated to clinical mammography. In addition, it is also important to study possible image artifacts introduced by new wavelet filters, which may increase the false positive rate     

Bio-Microfluidics Real-Time Monitoring Using CNN Technology

A new non-invasive real-time system for the monitoring and control of microfluidodynamic phenomena involving transport of particles and two phase fluids is proposed. The general purpose design of such system is suitable for in vitro and in vivo experimental setup and, therefore, for microfluidic applications in the biomedical field, such as lab-on-chip and for research studies in the field of microcirculation. The system consists of an ad hoc optical setup for image magnification providing images suitable for acquisition and processing. The main feature of the optical system is the accessibility of the information at any point of the optical path. It was designed and developed using discrete opto-mechanic components mounted on a breadboard. The optical sensing, acquisition, and processing were all performed using an integrated vision system based on cellular nonlinear networks (CNNs) analogic (analog plus logic) technology called Focal Plane Processor (FPP, Eye-RIS, Anafocus) that was inserted in the optical path. Ad hoc algorithms were implemented for the real-time analysis and extraction of fluidodynamic parameters in micro-channels. They were firstly tested on sequences of images recorded during in vivo microcirculation experiments on hamsters and then applied on images acquired and processed in real-time during in vitro experiments on two-phase fluid flow in a continuous microfluidic device (serpentine mixer, ThinXXS).      

Neurofuzzy prediction for gaze control

Real-time gaze control is a complicated task because of the different dynamics of the elements involved in the process. On the one hand, the algorithms for image processing are usually very time-consuming. On the other hand, the motors and mechanisms used to control camera movements are very slow. This work describes the use of an adaptive network-based fuzzy inference system (ANFIS) model to reduce the delay effects in gaze control and also explains how the delay problem is resolved through prediction of the target movement using a neurofuzzy approach. The approach has been successfully tested in the vision system of a humanoid robot. The predictions improve the velocity and accuracy of object tracking.     

An efficient paradigm for wavelet‐based image processing using cellular neural networks

We propose a novel paradigm for cellular neural networks (CNNs), which enables the user to simultaneously calculate up to four subband images and to implement the integrated wavelet decomposition and a subsequent function into a single CNN. Two sets of experiments were designated to test the performance of the paradigm. In the first set of experiments, the effects of seven different wavelet filters and five feature extractors were studied in the extraction of critical features from the down‐sampled low‐low subband image using the paradigm. Among them, the combination of DB53 wavelet filter and the r=2 halftoning processor was determined to be most appropriate for low‐resolution applications. The second set of experiments demonstrated the capacity of the paradigm in the extraction of features from multi‐subband images. CNN edge detectors were embedded in a two‐subband digital wavelet transformation processor to extract the horizontal and vertical line features from the LH and HL subband images, respectively. A CNN logic OR operator proceeds to combine the results from the two subband line‐edge detectors. The proposed edge detector is capable of delineating more subtle details than using typical CNN edge detector alone, and is more robust in dealing with low‐contrast images than traditional edge detectors. The results demonstrate the proposed paradigm as a powerful and efficient scheme for image processing using CNN. Copyright © 2008 John Wiley & Sons, Ltd.     

Design of high-speed,high-density CNNS in cmos technology

An analogue VLSI circuit architecture for the CMOS implementation of cellular neural networks (CNNs) is presented. It is based exclusively on the use of small capacitors and operational transconductance amplifiers operating in continuous time. Integrated circuit implementations of this architecture are very well suited for processing applications requiring large array size and high speed. We describe a systematic design approach for those circuits and present the design, fabrication and testing of two chips. These chips are used for connected component detection applications and are the first working integrated circuit implementation of a CNN. They contain 2000 transistors and have been fabricated using 2 μm CMOS technology. the density is 32 cells per square millimetre of silicon and the time constant of the processing is of the order of 10^?7 s. Experimental results of static and dynamic tests are given, including a complete image-processing example.     

基于Retinex图像增强的搜救机器人设计

在地震、矿难等突发灾难发生时的恶劣现场环境下,抢险搜救任务的紧迫性及危险性突显了对智能搜救机器人的迫切需求。针对搜救机器人在废墟狭窄空间中行走困难,且在低照度环境下,图像处理时间长、细节丢失的情况。首先基于仿生学设计了机器人的三维模型,并对机器人的运动进行控制;其次为提高搜救工作中图像的光照一致性,加入了一种基于Retinex视网膜的结构感知平滑模型,为搜救机器人提供了高可见输出,建立图像评价模型剔除低质量图像;最后通过算法加速求解器减少图像处理时间以满足在树莓派上实时输出优质图像的需求。实验结果表明,当六足机器人工作在微光环境下,树莓派图像处理时间仅需0.23秒大大减小了输出延迟,峰值信噪比为14.752dB显示的细节更饱满,证明提高了机器人的性能,在未来地质调研,地震搜查,艰难地形的侦查方面有很大的应用前景。     

Two different views on collision detection

In this article, we present two algorithms for precise collision detection between two potentially colliding objects. The first one uses axis-aligned bounding boxes (AABB) and is a typical representative of a computational geometry algorithm. The second one uses spherical distance fields originating in image processing. Both approaches addresses the following challenges of collision detection algorithms: just in time, little resources, inclusive etc. Thus both approaches are scalable in the information they give in collision determination and the analysis up to a fixed refinement level, the collision time depends on the granularity of the bounding volumes and it is also possible to estimate the time bounds for the collision test tightly     

A study on WTA cellular neural networks

This paper addresses a number of basic issues concerning the dynamics of a class of winner‐take‐all cellular neural networks (WTA CNNs) proposed by Seiler and Nossek. The main result is an analytical estimate for the settling time, which shows from a theoretical point of view that such CNNs are well suited for on‐line applications requiring a large number of units, fast processing speed and a relatively high resolution. Other results are the determination of the largest parameter set that guarantee a correct WTA functionality for all initial conditions and the solution of a conjecture made by Seiler and Nossek. These results are proved by means of a new Lyapunov function to analyse the global dynamical behaviour of the WTA CNNs. Copyright © 2001 John Wiley & Sons, Ltd.     

基于深度信息的巡逻机器人避障系统实现

针对巡逻机器人的避障导航,基于Realsense深度摄像头获取环境深度信息,在使用机载计算机对深度图像进行分层处理的基础上,设计了巡逻机器人避障导航系统,同时对巡逻机器人通信协议以及决策流程等进行了改进设计,最后在ROS机器人开源操作系统上对其进行实验及验证。实验结果表明,在相同环境下,该方法能使巡逻机器人快速、安全、有效地避开静态障碍物而到达目标点。该方法不仅能够提高避障的成功率,获得实时避障效果,而且能够降低巡逻机器人的数据处理量,有利于巡逻机器人的移植。     

3D Scan matching for mobile robot localization over rough terrain

In order to enable an autonomous mobile robot to travel over rough terrain, it necessitates the capability to detect self‐position accurately even when the odometry errors are increased in traveling. The conventional method can keep high speed and precise localization using iterative closest point algorithms or feature matching techniques. However, effects of steep changes of a mobile robot position are not considered when it travels over rough terrain. In this article, we propose the method for efficient real‐time 6D pose tracking using a rotating 2D laser scanner in traveling over rough terrain. For adaptation to steep changes of the position, weighted point clouds are generated based on the angular and the linear velocity measured by sensors mounted on the robot. And the position and posture of the robot are sequentially optimized by the scan matching in increments of 10 scans. In indoor experiments, we evaluated accuracy of our method when the robot passes on rugged floor. As a result, our method was performed with less than 0.078 m RMS positional error in real time.