Automated sensor planning for robotic vision tasks (original) (raw)
Related papers
The MVP sensor planning system for robotic vision tasks
IEEE Transactions on Robotics and Automation, 1995
The MVP model-based sensor planning system for robotic vision is presented. MVP automatically synthesizes desirable camera views of a scene based on geometric models of the environment, optical models of the vision sensors, and models of the task to be achieved. The generic task of feature detectability has been chosen since it is applicable to many robot-controlled vision systems. For such a task, features of interest in the environment are required to simultaneously be visible, inside the field of view, in focus, and magnified as required. In companion papers we analytically characterize the domain of admissible camera locations, orientations, and optical settings for which each of the above feature detectability requirements is satisfied separately. In this paper, we present a technique that poses the vision sensor planning problem in an optimization setting and determines viewpoints that satisfy all previous requirements simultaneously and with a margin. In addition, we present experimental results of this technique when applied to a robotic vision system that consists of a camera mounted on a robot manipulator in a hand-eye configuration. The camera is positioned and the lens is focused according to the results generated by MVP. Camera views taken from the computed viewpoints verify that all feature detectability constraints are indeed satisfied.
Automated senor planning for robotic vision tasks
1991
In this paper, we present a method to determine viewpoints for a robotic vision system for which object features of interest will simultaneously be visible, inside the field-of-view, in-focus and magnified as required. As part of our previous work, we had analytically characterized the domain of admissible camera locations, orientations and optical settings for which each of the above feature detectability requirements is satisfied separately. In this paper, we present a technique that poses the problem in an optimization setting in order to determine viewpoints that satisfy all requirements simultaneously and with a margin. The formulation and results of the optimization are shown, as well as, experimental results in which a robot vision system is positioned and its lens is set according to this method. Camera views are taken from the computed viewpoints in order to verify that all feature detectability requirements are indeed satisfied.
A survey of sensor planning in computer vision
IEEE Transactions on Robotics and Automation, 1995
A survey of research in the area of vision sensor planning is presented. The problem can be summarized as follows: Given information about the environment (e.g., the object under observation, the available sensors) as well as information about the task that the vision system is to accomplish (i.e., detection of certain object features, object recognition, scene reconstruction, object manipulation), develop strategies to automatically determine sensor parameter values that achieve this task with a certain degree of satisfaction. With such strategies, sensor parameters values can be selected and can be purposefully changed in order to effectively perform the task at hand. Sensory systems are then able to operate more flexibly, autonomously, and reliably. This problem has recently become an active area of study with a number of researchers addressing various aspects of the problem. The focus here is on vision sensor planning for the task of robustly detecting object features. For this task, camera and illumination parameters such as position, orientation, and optical settings are determined so that object features are, for example, visible, in focus, within the sensor field of view, magnified as required, and imaged with sufficient contrast. References to, and a brief description of, representative sensing strategies for the tasks of object recognition and scene reconstruction are also presented. For these tasks, sensor configurations are sought that will prove most useful when trying to identify an object or reconstruct a scene.
Automatic camera placement for robot vision tasks
1995
Remote sensors such as CCD cameras can be used for a variety of robot sensing tasks, but given restrictions on camera location and imaging geometry, task constraints, and visual occlusion it can be difficult to find viewing positions from which the task can be completed. The complexity of these constraints suggests that automated, quantitative methods of sensor placement are likely to be useful, particularly when the workspace is cluttered and a mobile robot-mounted sensor is being used to increase the sensible region, circumvent occlusions, and so forth.
Automatic Task Planning for Robot Vision
Robotics Research, 1996
This paper describes an automated planner for visual inspection and monitoring tasks using a robot mounted CCD camera. It is capable of finding heuristically near-optimal viewing positions for a series of visual tasks, and of ordering them and planning robot paths between them to produce a near minimal cost overall task plan for the sequence. It has been optimized for intervention-style tasks with relatively large, cluttered workspaces, where it is difficult for a human operator to take account of all the constraints involved. The guiding principle of the work has been to aim for reliability by using quantitative, physically-based measures of quality wherever possible, and by using global search to ensure that possible solutions are not overlooked. We discuss a novel global function optimization technique based on decision theory and subjective models of function behaviour, that allows global viewpoint searches to run in the time usually required for local ones.
Robotics, 2018
The task of robot vision is to recognize the geometry of the robot workspace from a digital image. It is our aim to find the relation between the coordinates of a point in the two-dimensional (2D) image and the coordinates of the point in the real threedimensional (3D) robot environment. 8.1 System Configuration The robot vision system is based on the use of one, two or more cameras. If several cameras are used to observe the same object, information about the depth of the object can be derived. In such case, we talk about 3D or stereo vision. Of course, the 3D view can also be achieved with a single camera if two images of the object are available, captured from different poses. If only one image is available, the depth can be estimated based on some previously known geometric properties of the object. When analyzing the configuration of the robotic vision system, it is necessary to distinguish between possible placements of the cameras. The cameras can be placed in a fixed configuration, where they are rigidly mounted in the workcell, or in a mobile configuration, where the camera is attached to a robot. In the first configuration, the camera observes objects from a fixed position with respect to the robot base coordinate frame. The field of view of the camera does not change during the execution of the task, which means that basically the accuracy of the measurement is constant. In some tasks, it is difficult to prevent the manipulator from reaching into the field of view of the camera and thereby occluding the objects. Therefore, in such case, it is necessary to put a camera on a robot (in a mobile configuration). The camera can be attached before or after the robot wrist. In the first case, the camera observes the situation from a favorable position and the manipulator generally does not occlude its field of view. In the second case, the camera is attached to the robot end-effector and typically only observes the object that is being manip
Scale Invariant Features for Camera-Planning in a Mobile Trinocular Active Vision System
In this paper, we present a camera-planning approach for a mobile trinocular active vision system. At a stationary version of this system, the sensor planning module calculates the generalized cameras' parameters (i.e., translation distance from the center, zoom, focus and vergence) using deterministic geometric specifications of both the sensors and the objects in their field of view. Some of these geometric parameters are difficult to be predetermined for the mobile system operation. In this paper, a new camera-planning approach, based on processing the content of the captured images, is proposed. The approach uses a combination of a closed-form solution for the translation between the three cameras, the vergence angle of the cameras as well as zoom and focus setting with the results of the correspondences between the acquired images and a predefined target object(s) obtained using the SIFT algorithm. We demonstrate the accuracy of the new approach using practical experiments. according to following formulas: .0m t = 0.005622d 2 + 0.04068d+ 0.04125 [m] Case 2: 0.3m< R d 0.5m, 1.925m d d d 7.0m t = 0.005812d 2 + 0.04702d-0.01307 [m] Case 3: 0.5m< R d 0.7m, 2.650m d d d 7.0 m t = 0.006205d 2 + 0.05530d-0.09068 [m] Case 4: 0.7m< R d 0.9m, 3.375m d d d 7.0m t = 0.006882d 2 + 0.06668d-0.20372 [m] Case 5: 0.9m< R d 1.0m, 4.100m d d d 7.0m t = 0.007990d 2 + 0.08380d-0.37802 [m]
Auto-preview camera orientation for environment perception on a mobile robot
Intelligent Robots and Computer Vision XXVII: Algorithms and Techniques, 2010
Using wide-angle or omnidirectional camera lenses to increase a mobile robot's field of view introduces nonlinearity in the image due to the 'fish-eye' effect. This complicates distance perception, and increases image processing overhead. Using multiple cameras avoids the fish-eye complications, but involves using more electrical and processing power to interface them to a computer. Being able to control the orientation of a single camera, both of these disadvantages are minimized while still allowing the robot to preview a wider area. In addition, controlling the orientation allows the robot to optimize its environment perception by only looking where the most useful information can be discovered. In this paper, a technique is presented that creates a two dimensional map of objects of interest surrounding a mobile robot equipped with a panning camera on a telescoping shaft. Before attempting to negotiate a difficult path planning situation, the robot takes snapshots at different camera heights and pan angles and then produces a single map of the surrounding area. Distance perception is performed by making calibration measurements of the camera and applying coordinate transformations to project the camera's findings into the vehicle's coordinate frame. To test the system, obstacles and lines were placed to form a chicane. Several snapshots were taken with different camera orientations, and the information from each were stitched together to yield a very useful map of the surrounding area for the robot to use to plan a path through the chicane.