A historical perspective of algorithmic lateral inhibition and accumulative computation in computer vision

Certainly, one of the prominent ideas of Professor José Mira was that it is absolutely mandatory to specify the mechanisms and/or processes underlying each task and inference mentioned in an architecture in order to make operational that architecture. The conjecture of the last fifteen years of joint research has been that any bottom-up organization may be made operational using two biologically inspired methods called “algorithmic lateral inhibition”, a generalization of lateral inhibition anatomical circuits, and “accumulative computation”, a working memory related to the temporal evolution of the membrane potential. This paper is dedicated to the computational formulation of both methods. Finally, all of the works of our group related to this methodological approximation are mentioned and summarized, showing that all of them support the validity of this approximation.     

Optimization of lateral interaction in accumulative computation on GPU-based platform

The Journal of Supercomputing - The lateral interaction in accumulative computation (LIAC) algorithm is a biologically inspired method that allows us to detect moving objects from image sequences...     

Accelerating bioinspired lateral interaction in accumulative computation for real-time moving object detection with graphics processing units

Biologically-inspired computer vision is a research area that offers prominent directions in a large variety of fields. Several processing algorithms inspired in natural vision enable detecting moving objects from video sequences so far. One example is lateral interaction in accumulative computation (LIAC), a classical bioinspired method that has been applied to numerous environments and applications. LIAC is the implementation for computer vision of two biologically-inspired methods denominated algorithmic lateral interaction and accumulative computation. The method has traditionally reached high precision but unfortunately requires high computing times. This paper introduces a proposal based on graphics processing units in order to speed up the original sequential code. This way not only excellent performance in terms of accuracy is maintained, but also real-time is obtained. A speed-up of 67× from the parallel over its sequential counterpart is achieved for several tested video sequences.

     

Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation

To be able to understand the motion of non-rigid objects, techniques in image processing and computer vision are essential for motion analysis. Lateral interaction in accumulative computation for extracting non-rigid shapes from an image sequence has recently been presented, as well as its application to segmentation from motion. In this paper, we introduce a modified version of the first multi-layer architecture. This version uses the basic parameters of the LIAC model to spatio-temporally build up to the desired extent the shapes of all moving objects present in a sequence of images. The influences of LIAC model parameters are explained in this paper, and we finally show some examples of the usefulness of the model proposed.     

基于自适应背景的实时运动物体检测

为了能够在监控系统中实时的检测出运动物体,提出了一种能够自适应获取并更新背景的运动检测方法。它是利用连续帧差分,当前帧与背景图像差分来获取运动信息,同时选择性的更新背景。实验证明该算法运算量小,鲁棒性好,算法中通过直方图分析来获取合适的阈值,提高了系统的自动化程度。     

基于颜色与运动特征的变电站实时烟雾检测

变电站的环境特殊性要求站内火灾检测准确、快速,烟雾检测是早期火灾检测中的常用方法.针对变电站特殊环境,提出一种快速烟雾检测算法.首先,利用改进的ViBe算法检测变电站实时监控视频中的运动区域,再通过颜色特征确定疑似烟雾区域,然后结合烟雾面积增长特性和移动特性识别烟雾区域.实验结果表明:这种算法能够检测到不同场景中的烟雾,对远距离、稀薄烟雾也能有效检测,满足变电站火灾检测实时性、准确性要求,能够应用于变电站场景烟雾检测.     

On the detection of motion and the computation of optical flow

A method for the detection of motion in image sequences is presented. In this method, the intensity history at each pixel is convolved with the second derivative in time of a temporal Gaussian smoothing function. The zero crossings in a single frame of the resulting function indicate the positions of moving edges. Intensity changes in time due to illumination effects do not produce zero crossings; thus, they are not interpreted as motion by the present method. It is also shown that the spatial and temporal derivatives of this function can be used to compute the component of the optical flow that is normal to the zero-crossing contours. This computation is also insensitive to nonconvective temporal and spatial variations in the image intensity that are caused by illumination effects     

Real-time crowd motion planning

Real-time crowd motion planning requires fast, realistic methods for path planning as well as obstacle avoidance. In a previous work (Morini et al. in Cyberworlds International Conference, pp. 144–151, 2007), we introduced a hybrid architecture to handle real-time motion planning of thousands of pedestrians. In this article, we present an extended version of our architecture, introducing two new features: an improved short-term collision avoidance algorithm, and simple efficient group behavior for crowds. Our approach allows the use of several motion planning algorithms of different precision for regions of varied interest. Pedestrian motion continuity is ensured when switching between such algorithms. To assess our architecture, several performance tests have been conducted, as well as a subjective test demonstrating the impact of using groups. Our results show that the architecture can plan motion in real time for several thousands of characters.

Real-time motion detection based on SW/HW-codesign for walking rescue robots

In a rescue operation walking robots offer a great deal of flexibility in traversing uneven terrain in an uncontrolled environment. For such a rescue robot, each motion is a potential vital sign and the robot should be sensitive enough to detect such motion, at the same time maintaining high accuracy to avoid false alarms. However, the existing techniques for motion detection have severe limitations in dealing with strong levels of ego-motion on walking robots. This paper proposes an optical flow-based method for the detection of moving objects using a single camera mounted on a hexapod robot. The proposed algorithm estimates and compensates ego-motion to allow for object detection from a continuously moving robot, using a first-order-flow motion model. Our algorithm can deal with strong rotation and translation in 3D, with four degrees of freedom. Two alternative object detection methods using a 2D-histogram based vector clustering and motion-compensated frame differencing, respectively, are examined for the detection of slow- and fast-moving objects. The FPGA implementation with optimized resource utilization using SW/HW codesign can process video frames in real-time at 31 fps. The new algorithm offers a significant improvement in performance over the state-of-the-art, under harsh environment and performs equally well under smooth motion.     

Real-time interactive visibility computation for quadratic surfaces

The display of a three-dimensional scene consisting of a collection of analytically defined surfaces is accomplished via a projection mapping into the viewing plane. Ray casting is a technique which accomplishes this mapping by firing a mapping ray through each pixel of the screen into the world space. The result is the intersection points of this ray with each of the surfaces. The intersection points so found are further tested in order to determine which one is visible.

Real-time interactive graphics requires that the image be updated fast enough so that the display seems to present fluid or real time motion to the viewer. Given that the refresh of the image takes place approximately every (1/30) of a second, the determination of the above mentioned intersections should take place in this interval of time.

In this paper we present a VSLI-oriented algorithm that determines the intersection points of the mapping rays with a quadratic surface as well as the visible points. A simple shading model is presented and a VSLI architecture is briefly discussed.     

Data errors in the computation of free motion

Input data in the computation of free motion (the inertia and stiffness matrices) contain some errors. These errors generate errors of output data (the natural frequency vector, the natural mode vectors). In this paper the relationships between errors of input and output data in the computation of free motion are derived. This analysis is applied to the finite element method. The paper presents program ERROR, which computes the errors of the natural frequencies created by the inertia matrix errors. An example of the influence of the errors of the mass and of the mass moment of inertia on the natural frequencies of a ship hull is presented.     

Real-time vandalism detection by monitoring object activities

This paper proposes a novel method for the detection of vandalism events in video sequences. The method is based on a proposed definition for common vandal behaviors recorded on surveillance video sequences. To do this, the method monitors changes inside a restricted site containing vandalism-prone objects such as a vending machine, a pay phone, or a street sign. When an object is detected as leaving such a site, the proposed method checks if the site contains temporally consistent and significant static changes, representing damage. If there are such changes and given that the site is normally unchanged after legal use, a vandalism event is declared and the vandals are tracked. The proposed method is tested on video sequences showing real and simulated vandal behaviors and it achieves a detection rate of 96%. It detects different forms of vandalism such as graffiti and theft, and can handle sudden illumination changes, occlusions, and segmentation errors. The proposed method operates at a frame rate of 13 frames per second.     

Real-time iris detection

A real-time algorithm to automatically detect human faces and irises from color images has been developed. A Haar cascade-based algorithm has been applied for simple and fast face detection. The face image is then converted into a gray-scale image. Three types of image processing techniques have been tested to study their effect on the performance of the iris detection algorithm. Then iris candidates are extracted from the valley of the face region. The iris candidates are paired up and the cost of each possible pairing is computed by a combination of mathematical models. The pairing with the lowest cost is considered to be a pair of irises. The algorithm has been tested by quality images from a Logitech camera and noisy images from a Voxx CCD camera. The proposed algorithm has achieved a success rate of 83.60% for iris detection in an open office environment.     

yoyo运动的实时轨迹生成

基于NTG（Nonlinear Trajectory Generation）软件包提出了一种机器人yoyo运动实时最优轨迹生成的通用方法,即数值解法,该方法也可以应用于其他类似周期性动态系统的轨迹规划问题。对于这类系统的实时最优控制来说,一个最为关键的问题就是如何实现快速求解最优轨迹,以满足实时性要求。而传统的数值求解方法都很费时。通过把最优问题映射一个较低维的空间进行求解,并且利用多线程编程技术,大大减少了计算所用的时间。仿真结果显示所求得的数值解与解析解完全相同,这也验证了该方法的正确性。单循环yoyo仿真的计算时间为10 ms左右,这表明该方法完全可以应用于实时控制。     

Real-time motion blur using extruded triangles

Several algorithms have been introduced to render motion blur in real time by solving the visibility problem in the spatial-temporal domains. However, some algorithms render at interactive frame rates but have artifacts or noise. Therefore, we propose a new algorithm that renders real-time motion blur using extruded triangles. Our method uses two triangles in the previous frame and the current frame to make an extruded triangle then send it to rasterization. By using the standard rasterization, visibility determination is performed efficiently. To solve the occlusion between extruded triangles for a given pixel, we introduce a combination solution using a sorting in front-to-back order and bitwise operations in the spatial-temporal dimensions. This solution ensures that only non-occluded extruded triangles are shaded. We further improve performance of our algorithm using a coverage map.     

Real-time Ethernet networks for motion control

Communication networks have been traditionally employed in motion control applications, especially within factory automation systems. While in the past they were merely used to exchange non time critical data (e.g. parameters and configuration data) nowadays they allow for much more powerful performance. In particular, the recently introduced Real-time Ethernet (RTE) networks, have been explicitly designed in order to cope with very tight timing constraints in terms of both determinism and real-time. In this paper we focus on two popular RTE networks, namely Ethernet POWERLINK and EtherCAT, and provide an example of their employment for a coordinated motion control application. In particular, we consider the tracking of a circular trajectory by the coordinated motion of two independent axes where the velocity set-points are transmitted to the electrical drives implementing the axis control by means of the RTE networks. After providing some essential features of the two networks, we describe the configurations adopted for the coordinated motion control application. Then we check the effectiveness of the solution proposed by means of numerical simulations which take into consideration possible error scenarios deriving from the adoption of the communication networks such as transmission errors, communication delays and cable breaks.     

Real-time detection of ventilatory maneuvers by a microcomputer

The SYTER software system was built around an Apple II microcomputer to automatically process the data yielded by three ventilatory tests: analysis of lung elasticity during an expiratory maneuver, plethysmographic measurement of airway resistance during a panting maneuver, and similar measurements of lung volumes. A volume signal is displayed to the operator throughout each test to help control the maneuver. The various stages of the test are recognized in real time by routines written in assembling language, so that significant data are displayed and stored during the maneuver. This paper describes the algorithms used to perform waveform analysis, and presents illustrative displays obtained in the Lung Function Laboratory.