Robust Vision Research Articles

SPATIOTEMPORAL CONTEXT INTEGRATION IN ROBOT VISION

Robust vision in dynamic environments using limited processing power is one of the main challenges in robot vision. This is especially true in the case of biped humanoids that use low-end computers. Techniques such as active vision, context-based vision, and multi-resolution are currently in use to deal with these highly demanding requirements. Thus, having as main motivation the development of robust and high performing robot vision systems, which can operate in dynamic environments, with limited computational resources, we propose a spatiotemporal context integration framework that improves the perceptual capabilities of a given robot vision system. Furthermore, we try to link the vision, tracking, and self-localization problems using a context filter to improve the performance of all these parts together more than to improve them separately. This framework computes: (i) an estimation of the poses of visible and nonvisible objects using Kalman filters; (ii) the spatial coherence of each current detection with all other simultaneous detections and with all tracked objects; and (iii) the spatial coherence of each tracked object with all current detections. Using a Bayesian approach, we calculate the a-posteriori probabilities for each detected and tracked object, which is used in a filtering stage. We choose as a first application of this framework, the detection of static objects in the RoboCup Standard Platform League domain, where Nao humanoid robots are employed. The proposed system is validated in simulations and using real video sequences. In noisy environments, the system is able to decrease largely the number of false detections and to improve effectively the self-localization of the robot.

Developing robust vision modules for microsystems applications

In this work, several robust vision modules are developed and implemented for fully automated micromanipulation. These are autofocusing, object and end-effector detection, real-time tracking and optical system calibration modules. An image based visual servoing architecture and a path planning algorithm are also proposed based on the developed vision modules. Experimental results are provided to assess the performance of the proposed visual servoing approach in positioning and trajectory tracking tasks. Proposed path planning algorithm in conjunction with visual servoing imply successful micromanipulation tasks.

Accurate and Robust Surface Measurement Using Optimal Structured Light Tracking Method

Structured light vision systems are based on the fact that the pixel location of light in an image has a unique association with the object depth. However, their applications are mainly limited to the properties of the object surface and the lighting conditions. This paper presents a robust vision system for accurate acquisition of 3-D surface data based on optimal structured light. To achieve depth measurement for a dynamic scene, the data acquisition must be performed with only a single image. Our special arrangement makes the image of the light stripe remaining sharp while the background becomes blurred. Moreover, a dynamic programming approach is proposed to track the optimal path while the laser beam is invisible or divergent under extreme condition. The principle and necessary mathematics for implementing the algorithm are presented. The robustness of the system against uncalibrated errors is demonstrated.

Vision and visual cortical maps in mice with a photoreceptor synaptopathy: Reduced but robust visual capabilities in the absence of synaptic ribbons

How little neurotransmission in the visual system is sufficient to promote decent visual capabilities? This question is of key importance for therapeutic approaches to restore vision in patients who suffer from degenerative retinal diseases. In the retinae of mice, mutant for the presynaptic scaffolding protein Bassoon (Bsn), signal transfer at photoreceptor ribbon synapses is severely disturbed due to impaired ribbon attachment to the active zone. We have used two different behavioural tasks and optical imaging of intrinsic signals to probe vision in young and adult Bsn−/− mice and their wild-type littermates. Here we show that while visual acuity was significantly reduced in mutants compared to controls, vision guided behavioural decisions and optical imaging revealed essentially unperturbed cortical signals and retinotopy in spite of the photoreceptor synaptopathy. In addition, both vision and visual cortical maps were adult-like at 4 weeks of age. These results show that (i) while Bassoon-dependent fast exocytosis is essential for normal vision surprisingly good visual performance can be achieved in the absence of synaptic ribbons, (ii) both the development and maintenance of visual cortical maps is independent of synaptic ribbons and (iii) visual development in the mutants is completed at 4 weeks of age indicating that later developing ectopic synapses do not affect vision. Thus, the central visual system can make use of slow and weak retinal signals to subserve surprisingly robust vision.

Towards a more inclusive vision of the medical sciences

Progress in the medical sciences is largely determined by two things: (i) the questions we ask, and (ii) how rigorously and vigorously we attempt to answer them. How do we know which questions are the right questions to ask, and thus the correct questions to spend our time and energies trying to answer? Such evaluative concerns bring into sharper focus the question--'What is medicine for?' The international study of rosuvastatin is important not simply because of the health benefits it may confer, but because it inspires a more robust and inclusive vision of the medical sciences. A vision which recognizes that the primary goal of medicine is to promote health, and that includes the health of 'normal' people as well as those with illness and disease. This inclusive vision of the medical sciences is a transformative one, it departs from the 'disease-model' approach which has dominated distinct areas of medical research for decades.

Medicine as Friendship with God: Anointing the Sick as a Theological Hermeneutic

A THEOLOGICAL BIOETHICS NEEDS, FIRST, A THEOLOGICAL POLITICS. THE thesis of this essay rests on the claim that the contours of a theological poli tics are found in the nature of sacramental practices. More specifically, a the ological politics of medicine is found in the sacramental practice of anointing of the sick. Anointing provides a radically theological hermeneutic—a theolog ically robust vision for interpreting medicine that, if enacted, can powerfully make real God's work in the world. Such a vision is embodied in one particu lar twentieth-century exemplar—the organization called Partners In Health (PIH) and its cofounder, Paul Farmer. Farmer and PIH, I argue, live the theologie and theological politics of medicine embodied in the practice of anointing. What is more, they show—against those who would accuse such an approach of be ing naively idealistic—that such a theological politics is possible, powerful, and can even change the world.

A fuzzy sensor for color matching vision system

This article presents the development of a vision system according to a fuzzy sensor concept with the aim to improve the wooden boards color matching. The main difficulty consists in the recognition of gradual color in an industrial context. This problem implies the use of a flexible and robust vision system. It must be focused on the techniques that are able to work with the imprecision of physical measurements and the subjective human definitions of colors. Indeed, the color classes are not often well separated and the different users can have different perceptions of the colors. So, the vision system must be easy to tune. To achieve such a system, the recognition step is done with a fuzzy reasoning classifier that is well-adapted for this application case. The proposed method is quite efficient with small learning data sets because of the generalisation capacity of both feature selection and recognition steps. This technique allows to keep the interpretability of the model. The obtained results are compared with more classical methods and show the efficiency of the proposed fuzzy sensor, especially for merging outputs of several sensors used together in multi-face application case.

Promoting inclusive practices in primary schools in Cyprus: empowering pupils to build supportive networks

Having ownership of a dream is a core element for school improvement and effectiveness. Believing in the effectiveness of a programme is the beginning of reviving a school’s internal capacities for improvement. Any improvement and development programme needs to be inviting and non‐threatening, a holistic process involving all stakeholders. In this way any educational organization, such as a school, will succeed in serving its core purpose to the maximum: that of offering quality, well‐rounded education to its pupils. Our study was founded on this philosophy. The challenge was to create the foundation base on which the school could develop alternative procedures and structures necessary for addressing educational inclusion. This meant having a robust vision, including everyone, starting from the pupils. Through this action research project and with the pupils’ empowerment and participation, we wanted to change current practice, to bring the pupils together and share understandings, in order to promote inclusive practices within a primary school setting. To this end, a group of 11‐year‐old pupils would act as pupil‐researchers and co‐educators. The group of pupils were trained in research methods, and together planned and designed the action to be taken during this project. The use of pupils as researchers was an innovation in Cyprus, the aim to address the difficult logistical problems of implementing inclusion in practical settings.

U.S. SPACE WEAPONS

Under the administration of President George W. Bush, Pentagon rhetoric has increasingly articulated a more robust vision of space as a future battlefield. This analysis details some of the ongoing spending for research and development programs identified in current U.S. Air Force, Missile Defense Agency (MDA), and Defense Advanced Research and Planning Agency (DARPA) planning and budget documents related to “space control” and “space force projection.” This analysis finds that current support for “space superiority” and “space control” systems remains largely rhetorical—with little actual budgetary support. Unclassified technology development programs included in the six-year Future Years Defense Plan are a decade or more away from deployment. Programs related to offensive counterspace, space-based missile defense interceptors, and space-based strike total slightly less than $300 million in FY 2006 funding. We conclude significantly higher expenditures in research and development would be required to develop and deploy killer micro satellites, space-based missile defense interceptors, and military space planes.

Long-term forecasting for Sustainable Development: air travel demand for 2050

Before implementing policy measures that may contribute to a sustainable development, one has to determine in one or other away in advance if these measures will have their intended effects. As sustainable development necessitates long-term perspectives, a robust vision of possible future states of the world is vital. This paper discusses two different approaches to gain insights into possible future states of the system of interest. One is the classical scenario approach, and the other is the empirical modelling approach. This paper considers possible future air travel demand as a case study, as in that system long-term visions of up to 50 years are necessary. This paper discusses a need for more sustainable development in the aviation sector and argues that changes in that system require long horizons for action. It explains the need for developing ideas about the possible future air travel demand for the period up to 2050. This paper presents a brief review of the literature on scenarios and exploratory modelling. It discusses both the scenario and empirical modelling approach to come up with plausible future states of the system and gives a convergent forecast of future growth in the year 2050.

Robust and efficient vision system for group of cooperating mobile robots with application to soccer robots

In this paper a global vision scheme for estimation of positions and orientations of mobile robots is presented. It is applied to robot soccer application which is a fast dynamic game and therefore needs an efficient and robust vision system implemented. General applicability of the vision system can be found in other robot applications such as mobile transport robots in production, warehouses, attendant robots, fast vision tracking of targets of interest and entertainment robotics. Basic operation of the vision system is divided into two steps. In the first, the incoming image is scanned and pixels are classified into a finite number of classes. At the same time, a segmentation algorithm is used to find corresponding regions belonging to one of the classes. In the second step, all the regions are examined. Selection of the ones that are a part of the observed object is made by means of simple logic procedures. The novelty is focused on optimization of the processing time needed to finish the estimation of possible object positions. Better results of the vision system are achieved by implementing camera calibration and shading correction algorithm. The former corrects camera lens distortion, while the latter increases robustness to irregular illumination conditions.

Introduction: Pragmatism and Deliberative Politics

In the past decade, democratic theory has taken an unmistakable turn toward deliberative models of democratic legitimacy and practice. This deliberative turn is in part due to the frustrations that emerged out of the disputes concerning liberalism often misleadingly characterized as the "liberal-communitarian debate." 1 Recall that the communitarian critique proposed that liberal political philosophy rested upon a viciously atomistic view of the individual and consequently could not countenance an adequately robust vision of democratic citizenship. That is, the critics of liberalism maintained that liberal politics could not eschew what Jane Mansbridge fittingly characterized as "adversary democracy" (Mansbridge, 1983). Explaining this style of democratic politics, Jürgen Habermas writes:

A 128 x 128 pixel 120-db dynamic-range vision-sensor chip for image contrast and orientation extraction

A vision sensor for low-cost, fast, and robust vision systems is described. The sensor includes an on-chip analog computation of contrast magnitude and direction of image features. A temporal ordering of this information according to the contrast magnitude is used to reduce the amount of data delivered. This sensor, realized in a 0.5-μm two-poly three-metal technology, features a contrast sensitivity of 2%, a contrast direction precision of ±3°, and an illumination dynamic range of 120 dB. Applications with uncontrolled lighting conditions are ideal for this sensor.

LOW GAIN ROBUST VISUAL SERVOING WITH BOUNDED TRACKING ERRORS

This paper focuses on the design of robust vision based control of a 2-DOF planar manipulator. The controller is expressed in the image space, where the system can be modeled as a pure integrator with a nonlinear matrix gain. It involves a simple proportional controller with a feedforward velocity input. Robustness is provided by the guarantee of a bounded tracking error, thanks to the online computation on the desired velocity along the trajectory. The approach is both formally proven and experimentally validated on a lab apparatus.

Organizational Health and Robust School Vision

This article reports a significant positive relationship between teachers’ perceptions of organizational health and the relative robustness of their school vision. Subsequent regression analysis indicated that academic emphasis and institutional integrity were the school health themes that characterized the overall association with robust school vision.

Competitive Learning and its Application in Adaptive Vision for Autonomous Mobile Robots

The task of providing robust vision for autonomous mobile robots is a complex signal processing problem which cannot be solved using traditional deterministic computing techniques. In this article we investigate four unsupervised neural learning algorithms, known collectively as competitive learning, in order to assess both their theoretical operation and their ability to learn to represent a basic robotic vision task. This task involves the ability of a modest robotic system to identify the components of basic motion and to generalize upon that learned knowledge to classify correctly novel visual experiences. This investigation shows that standard competitive learning and the DeSieno version of frequency-sensitive competitive learning (FSCL) are unsuitable for solving this problem. Soft competitive learning, while capable of producing an appropriate solution, is too computationally expensive in its present form to be used under the constraints of this application. However, the Krishnamurthy version of FSCL is found to be both computationally efficient and capable of reliably learning a suitable solution to the motion identification problem both in simulated tests and in actual hardware-based experiments.

Computational Vision at Yale

We present a brief introduction to the five articles that make up this special issue: Shock Graphs and Shape Matching, The Bas-Relief Ambiguity, Incremental Focus of Attention for Robust Vision Based Tracking, What Tasks can be Performed with an Uncalibrated Stereo Vision System, and Volumetric Deformation Analysis Using Mechanics-Based Data Fusion: Application in Cardiac Motion Recovery. Tjis introduction and accompanying articles provide a by no means exhaustive, but hopefully representative sampling of the computational vision at Yale University.

A vision sensor having an expanded dynamic range for autonomous vehicles

Insufficiency of dynamic range of conventional video cameras is an important problem in realizing a robust vision system for autonomous vehicles because road scenes have a very wide dynamic range of brightness. To solve the problem, a method for expanding the dynamic range of video cameras by combining the images taken under different exposure conditions has been developed. Using this method, an experimental vision sensor with a wide dynamic range has been manufactured. The developed sensor has a dynamic range of 10 000, which is approximately 30 times as wide as that of a conventional video camera. The effectiveness of the developed vision sensor in comparison with a conventional video camera was confirmed from the experiments on a highway under various lighting conditions.

Robot vision robust to changes of lighting conditions using a wide-dynamic-range visual sensor

We have developed a robust vision system for 2D positioning of industrial parts stable to changes of lighting conditions. A wide dynamic range vision sensor that we had developed previously was used to avoid the saturation of object images. Additionally, a gray scale pattern matching technique was employed for robust image processing. Performance of the system with a wide dynamic range vision sensor was investigated experimentally in comparison with that of a system with a conventional video camera. The probability of correct positioning of an object under changing lighting conditions, simulating those in a factory, was 100% for the wide dynamic range vision sensor and 83% for the conventional video camera. The experimental results confirm the effectiveness of the developed system, revealing that dynamic range expansion of the video cameras is very effective for realizing robust robot vision systems. © 1997 Scripta Technica, Inc. Electr Eng Jpn, 120(2): 34–40, 1997

照明変動にロバストな部品位置決め用ロボット視覚システム

A robust vision system against the change of lighting condition for industrial parts positioning has been developed. A wide dynamic range vision sensor, we had developed previously, was employed to avoid the saturation of images of the objects. Performance of the developed system with the wide dynamic range vision sensor was investigated experimentally in comparison with that of the system with a conventional video camera. The experimental result has confirmed the effectiveness of the developed system, revealing that the dynamic range expansion of the video cameras is very effective for realizing robust robot vision systems.