Global feature space neural network for active computer vision

We advance new active computer vision algorithms based on the Feature space Trajectory (FST) representations of objects and a neural network processor for computation of distances in global feature space. Our algorithms classify rigid objects and estimate their pose from intensity images. They also indicate how to automatically reposition the sensor if the class or pose of an object is ambiguous from a given viewpoint and they incorporate data from multiple object views in the final object classification. An FST in a global eigenfeature space is used to represent 3D distorted views of an object. Assuming that an observed feature vector consists of Gaussian noise added to a point on the FST, we derive a probability density function for the observation conditioned on the class and pose of the object. Bayesian estimation and hypothesis testing theory are then used to derive approximations to the maximum a posterioriprobability pose estimate and the minimum probability of error classifier. Confidence measures for the class and pose estimates, derived using Bayes theory, determine when additional observations are required, as well as where the sensor should be positioned to provide the most useful information.     

Gesture recognition for control of rehabilitation robots

This paper describes the development of a control user interface for a wheelchair-mounted manipulator for use by severely disabled persons. It explains the construction of the interface using tasks to define the user interface architecture. The prototype robot used several gesture recognition systems to achieve a level of usability better than other robots used for rehabilitation at the time. The use of neural networks and other procedures is evaluated. It outlines the experiments used to evaluate the user responses and draws conclusions about the effectiveness of the whole system. It demonstrates the possibility of control using a head mouse.

First and second order dynamics in a hierarchical SOM system for action recognition

Human recognition of the actions of other humans is very efficient and is based on patterns of movements. Our theoretical starting point is that the dynamics of the joint movements is important to action categorization. On the basis of this theory, we present a novel action recognition system that employs a hierarchy of Self-Organizing Maps together with a custom supervised neural network that learns to categorize actions. The system preprocesses the input from a Kinect like 3D camera to exploit the information not only about joint positions, but also their first and second order dynamics. We evaluate our system in two experiments with publicly available datasets, and compare its performance to the performance with less sophisticated preprocessing of the input. The results show that including the dynamics of the actions improves the performance. We also apply an attention mechanism that focuses on the parts of the body that are the most involved in performing the actions.     

A hybrid approach for autonomous navigation of mobile robots in partially-known environments

We propose a hybrid approach specifically adapted to deal with the autonomous-navigation problem of a mobile robot which is subjected to perform an emergency task in a partially-known environment. Such a navigation problem requires a method that is able to yield a fast execution time, under constraints on the capacity of the robot and on known/unknown obstacles, and that is sufficiently flexible to deal with errors in the known parts of the environment (unexpected obstacles). Our proposal includes an off-line task-independent preprocessing phase, which is applied just once for a given robot in a given environment. Its purpose is to build, within the known zones, a roadmap of near-time-optimal reference trajectories. The actual execution of the task is an online process that combines reactive navigation with trajectory tracking and that includes smooth transitions between these two modes of navigation. Controllers used are fuzzy-inference systems. Both simulation and experimental results are presented to test the performance of the proposed hybrid approach. Obtained results demonstrate the ability of our proposal to handle unexpected obstacles and to accomplish navigation tasks in relatively complex environments. The results also show that, thanks to its time-optimal-trajectory planning, our proposal is well adapted to emergency tasks as it is able to achieve shorter execution times, compared to other waypoint-navigation methods that rely on optimal-path planning.     

An investigation of the modified direction feature for cursive character recognition

This paper describes and analyses the performance of a novel feature extraction technique for the recognition of segmented/cursive characters that may be used in the context of a segmentation-based handwritten word recognition system. The modified direction feature (MDF) extraction technique builds upon the direction feature (DF) technique proposed previously that extracts direction information from the structure of character contours. This principal was extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image.In order to improve on the DF extraction technique, a number of modifications were undertaken. With a view to describe the character contour more effectively, a re-design of the direction number determination technique was performed. Also, an additional global feature was introduced to improve the recognition accuracy for those characters that were most frequently confused with patterns of similar appearance. MDF was tested using a neural network-based classifier and compared to the DF and transition feature (TF) extraction techniques. MDF outperformed both DF and TF techniques using a benchmark dataset and compared favourably with the top results in the literature. A recognition accuracy of above 89% is reported on characters from the CEDAR dataset.     

A novel fused neural network controller for lateral control of autonomous vehicles

We present a novel fused feed-forward neural network controller inspired by the notion of task decomposition principle. The controller is structurally simple and can be applied to a class of control systems that their control requires manipulation of two input variables. The benchmark problem of inverted pendulum is such example that its control requires availability of the angle as well as the displacement. We demonstrate that the lateral control of autonomous vehicles belongs to this class of systems and successfully apply the proposed controller to this problem. The parameters of the controller are encoded into real value chromosomes for genetic algorithm (GA) optimization. The neural network controller contains three neurons and six connection weights implying a small search space implying faster optimization time due to few controller parameters. The controller is also tested on two benchmark control problems of inverted pendulum and the ball-and-beam system. In particular, we apply the controller to lateral control of a prototype semi-autonomous vehicle. Simulation results suggest a good performance for all the tested systems. To demonstrate the robustness of the controller, we conduct Monte-Carlo evaluations when the system is subjected to random parameter uncertainty. Finally experimental studies on the lateral control of a prototype autonomous vehicle with different speed of operation are included. The simulation and experimental studies suggest the feasibility of this controller for numerous applications.     

Vision-based global localization for mobile robots with hybrid maps of objects and spatial layouts

This paper presents a novel vision-based global localization that uses hybrid maps of objects and spatial layouts. We model indoor environments with a stereo camera using the following visual cues: local invariant features for object recognition and their 3D positions for object pose estimation. We also use the depth information at the horizontal centerline of image where the optical axis passes through, which is similar to the data from a 2D laser range finder. This allows us to build our topological node that is composed of a horizontal depth map and an object location map. The horizontal depth map describes the explicit spatial layout of each local space and provides metric information to compute the spatial relationships between adjacent spaces, while the object location map contains the pose information of objects found in each local space and the visual features for object recognition. Based on this map representation, we suggest a coarse-to-fine strategy for global localization. The coarse pose is estimated by means of object recognition and SVD-based point cloud fitting, and then is refined by stochastic scan matching. Experimental results show that our approaches can be used for an effective vision-based map representation as well as for global localization methods.     

Multi-level cognitive machine-learning based concept for human-like “artificial” walking: Application to autonomous stroll of humanoid robots

We propose a machine-learning based multi-level cognitive model inspired from early-ages’ cognitive development of human’s locomotion skills for humanoid robot’s walking modeling. Contrary to the most of already introduced works dealing with biped robot’s walking modeling, which place the problem within the context of controlling specific kinds of biped robots, the proposed model attends to a global concept of biped walking ability’s construction independently from the robot to which the concept may be applied. The chief-benefit of the concept is that the issued machine-learning based structure takes advantage from “learning” capacity and “generalization” propensity of such models: allowing a precious potential to deal with high dimensionality, nonlinearity and empirical proprioceptive or exteroceptive information. Case studies and validation results are reported and discussed evaluating potential performances of the proposed approach.     

Learning and surface boundary feedbacks for colour natural scene perception

Boundary detection and segmentation are essential stages in object recognition and scene understanding. In this paper, we present a bio-inspired neural model of the ventral pathway for colour contour and surface perception, called LPREEN (Learning and Perceptual boundaRy rEcurrent dEtection Neural architecture). LPREEN models colour opponent processes and feedback interactions between cortical areas V1, V2, V4, and IT, which produce top-down and bottom-up information fusion. We suggest three feedback interactions that enhance and complete boundaries. Our proposed neural model contains a contour learning feedback that enhances the most probable contour positions in V1 according to a previous experience, and generates a surface perception in V4 through diffusion processes. We compared the proposed model with another bio-inspired model and two well-known contour extraction methods, using the Berkeley Segmentation Benchmark. LPREEN showed better performance than two methods and slightly worse performance than another one.     

Artificial neural networks for coordination and control: The portability of experiential representations

It is time to locate connectionist representation theory in the new wave of robotics research. The utility of representations developed in artificial neural networks (ANNs) during learning has been demonstrated in cognitive science research since the 1980s. The research reported here puts learned representations to work in a decentered control task, the disembodied arm problem, in which a mobile robot operates an arm fixed to a table to pick up objects. There is no physical linkage between the arm and the robot and so the robot's point of view must be decentered. This is done by developing a modular Artificial Neural Net system in three stages: (i) a classifier net is trained with laser scan data to output transformationally invariant position classes; (ii) an arm net is trained for picking up objects; (iii) an inter net is trained to communicate and coordinate the sensing and acting. The completed system is shown to create new nonsymbolic transformationally invariant representations in order to perform the effective generalization of decentered viewpoints.     

Optimal binarization of images by neural networks for morphological analysis of ductile cast iron

This work aims to characterize different objects on a scene by means of some of their morphological properties. The leading application consists in the analysis of ductile cast iron specimen pictures, in order to provide a quantitative evaluation of the graphite nodules shape; to this aim the material specimen pictures are binarized. Such a binarization process can be formulated as an optimal segmentation problem. The search for the optimal solution is solved efficiently by training a neural network on a suitable set of binary templates. A robust procedure is obtained, amenable for parallel or hardware implementation, so that real-time applications can be effectively dealt with. The method was developed as the core of an expert system aimed at the unsupervised analysis of ductile cast iron mechanical properties that are influenced by the microstructure and the peculiar morphology of graphite elements.

神经网络在机器人视觉图像命令识别中的应用

在智能机器人技术中,视觉识别是关键.在智能机器人视觉系统获得的图像中,由于图像倾斜而造成的识别错误是视觉识别难以解决的问题.针对机器人所要完成的具体任务,对机器人的视觉识别问题进行探讨,为实现机器人对图像命令的识别,首先对机器人视觉系统获得的倾斜图像,采用Hough变换进行倾斜度检测并进行校正,然后采用人工神经网络法进行识别,根据识别结果对机器人的下一步运动进行决策与控制,达到了预期的目的.实验结果表明,该方法具有较高的识别率.     

CYCLOPS: A mobile robotic platform for testing and validating image processing and autonomous navigation algorithms in support of artificial vision prostheses

While artificial vision prostheses are quickly becoming a reality, actual testing time with visual prosthesis carriers is at a premium. Moreover, it is helpful to have a more realistic functional approximation of a blind subject. Instead of a normal subject with a healthy retina looking at a low-resolution (pixelated) image on a computer monitor or head-mounted display, a more realistic approximation is achieved by employing a subject-independent mobile robotic platform that uses a pixelated view as its sole visual input for navigation purposes. We introduce CYCLOPS: an AWD, remote controllable, mobile robotic platform that serves as a testbed for real-time image processing and autonomous navigation systems for the purpose of enhancing the visual experience afforded by visual prosthesis carriers. Complete with wireless Internet connectivity and a fully articulated digital camera with wireless video link, CYCLOPS supports both interactive tele-commanding via joystick, and autonomous self-commanding. Due to its onboard computing capabilities and extended battery life, CYCLOPS can perform complex and numerically intensive calculations, such as image processing and autonomous navigation algorithms, in addition to interfacing to additional sensors. Its Internet connectivity renders CYCLOPS a worldwide accessible testbed for researchers in the field of artificial vision systems. CYCLOPS enables subject-independent evaluation and validation of image processing and autonomous navigation systems with respect to the utility and efficiency of supporting and enhancing visual prostheses, while potentially reducing to a necessary minimum the need for valuable testing time with actual visual prosthesis carriers.     

An artificial life approach for the animation of cognitive characters

This paper addresses the problem of cognitive character animation. We propose the use of finite state machines for the behavioral control of characters. Our approach rests on the idea that the cognitive character arises from the evolutionary computation embedded in the artificial life simulation, which in our case is implemented by the finite state machine. We present some of the results of the WOXBOT/ARENA research project. This project to build virtual worlds is aimed at the graphic simulation of an arena, where small mobile robots can perform requested tasks while behaving according to their own motivation and reasoning. Each robot is an intelligent agent that perceives the virtual environment through a simulated vision system and reacts by moving away from or approaching the object it sees. The conception and specification of the robots and environment are being done very carefully to create an open distributed object architecture that could serve as a test-bed freely available and ready to use for testing theories in some computational areas such as evolutionary computation, artificial life, pattern recognition, artificial intelligence, cognitive neurosciences and distributed objects architectures. Furthermore, it is a first step towards building a cognitive animated character.     

Intelligent sensor system for discrimination of material type using neural networks

Neural network based classification of material type even with the variation in the sensor parameter is investigated in this paper. The sensor is developed by means of a lightweight plunger probe and an optical mouse sensor. An experimental prototype was developed which involves bouncing or hopping of the plunger based impact probe freely on the plain surface of an object under test. The experiment is conducted to obtain the bouncing signals for plain surface of an objects kept at different distances from the probe. During the bouncing of the probe, time varying signals are generated from optical mouse that are recorded in data files on PC. Some dominant unique features are then extracted using signal processing tools to optimize neural network based classifier. The time and features of bouncing signal are related to the material type, and each material has a unique set of such properties. It is found that the sensor system is intelligent due to its ability to classify the material type even with the variation in the sensor parameter (distance between the sensor probe and plain objects). The classifiers are developed using two neural networks configurations, namely a well-known Multi-layer Perceptron Neural Networks (MLP NN), and Radial Basis Function Neural Networks (RBF NN). MLP NN and RBF NN models are designed to maximize accuracy under the constraints of minimum network dimension.The optimal parameters of MLP NN and RBF NN models based on various performance measures that include percentage classification accuracy (PCLA) on the testing data, and area under Receiver Operating Characteristics (ROC), and are determined. For the sensor data set, the PCLA of both the classifiers are found reasonable consistently in respect of rigorous testing using different data partitions. The areas under the ROC curves are close to unity. Performances of the two classifiers have been compared. It has been found that the RBF NN is more robust to noise, and epochs required for training are very less as compared to that for MLP NN.     

一种鲁棒的无线传感器网络覆盖空洞修补方法

在静态节点和少量移动节点构成的无线传感器混合网络中,针对部分静态节点失效会导致形成若干覆盖空洞的问题,提出了一种鲁棒的空洞修复算法。受鱼群运动模式的启发,该算法以网络覆盖率为目标函数,将移动节点的位置迁移过程抽象为人工鱼的生物行为,在传统鱼群觅食、追尾、聚群运动模式的基础上又定义鱼跃、优胜劣汰重生两个新的运动行为以提高寻优的收敛性;在人工鱼状态更新的过程中,采用自适应的视野和步长;最后以实际随机部署的移动节点距离目标点最近为原则,通过鱼群寻优完成空洞目标位置的修补。模拟实验结果表明,该算法无需修补前的地理位置信息和空洞探测,鲁棒性强,能够在使用较少移动节点的情况下快速完成空洞修复,显著地提高了网络覆盖率。     

Determination of vitality from a non-invasive biomedical measurement for use in fingerprint scanners

Fingerprints are the oldest and most widely used biometrics for personal identification. Unfortunately, it is usually possible to deceive automatic fingerprint identification systems by presenting a well-duplicated synthetic or dismembered finger. This paper introduces one method to provide fingerprint vitality authentication in order to solve this problem. Detection of a perspiration pattern over the fingertip skin identifies the vitality of a fingerprint. Mapping the two-dimensional fingerprint images into one-dimensional signals, two ensembles of measures, namely static and dynamic measures, are derived for classification. Static patterns as well as temporal changes in dielectric mosaic structure of the skin, caused by perspiration, demonstrate themselves in these signals. Using these measures, this algorithm quantifies the sweating pattern and makes a final decision about vitality of the fingerprint by a neural network trained by examples.