DOC PREVIEW
Berkeley COMPSCI 294 - Active Perception

This preview shows page 1-2-3 out of 10 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 10 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Active Perception RUZENA BAJCSY, MEMBER, IEEE Invited Paper Active Perception (Active Vision specifically) is defined as a study of Modeling and Control strategies for perception. By modeling we mean models of sensors, processing modules and their interac- tion. We distinguish local models from global models by their extent of application in space and time. The local models repre- sent procedures and parameters such as optical distortions of the lens, focal lens, spatial resolution, band-pass filter, etc. The global models on the other hand characterize the overall performance and make predictions on how the individual modules interact. The control strategies are formulated as a search of such sequence of steps that would minimize a loss function while one is seeking the most information. Examples are shown as the existence proof of the proposed theory on obtaining range from focus and sterolver- gence on 2-0 segmentation of an image and 3-0 shape parametri- za tion. I. INTRODUCTION Most past and present work in machine perception has involved extensive static analysis of passively sampled data. However, it should be axiomatic that perception is not pas- sive, but active. Perceptual activity is exploratory, probing, searching; percepts do not simply fall onto sensors as rain falls onto ground. We do not just see, we look. And in the course, our pupils adjust to the level of illumination, our eyes bring the world into sharp focus, our eyes converge or diverge, we move our heads or change our position to get a better view of something, and sometimes we even put on spectacles. This adaptiveness is crucial for survival in an uncertain and generally unfriendly world, as millenia of experiments with different perceptual organizations have clearly demonstrated. Yet no adequate account or theory or example of active perception has been presented by machine perception research. This lack is the motivation for this paper. Manuscript received November23,1987; revised March21,1988. This work was supported in part by NSF Grant DCR-8410771, Air Force Grant AFOSR F49620-85-K-0018, Army/DAAG-29-84-K-O061, NSF-CERIDCR82-19196 A02, DARPMONR NIH Grant NS-10939-11 as part of Cerebo Vascular Research Center, NIH l-ROl-NS-23636- NATO Grant 0224/85, and by DEC Corporation, IBM Corporation, and LORD Corporation. The author is with the Computer and Information Science Department, University of Pennsylvania, Philadelphia, PA 19104, USA. 01, NSF INT85-14199, NSF DMC85-17315, ARPA N0014-85-K-0807, IEEE Log Number 8822793. 996 II. WHAT IS ACTIVE SENSING? In the robotics and computer vision literature, the term “active sensor” generally refers to a sensor that transmits (generally electromagnetic radiation, e.g., radar, sonar, ultrasound, microwaves and collimated light) into the envi- ronment and receives and measures the reflected signals. We believe that the use of active sensors is not a necessary condition on active sensing, and that sensing can be per- formed with passive sensors (that only receive, and do not emit, information), employed actively. Here we use the term active not to denote a time-of-flight sensor, but to denote a passive sensor employed in an active fashion, purpose- fully changing the sensor’s state parameters according to sensing strategies. Hence the problem of Active Sensing can be stated as a problem of controlling strategies applied to the data acqui- sition process which will depend on the current state of the data interpretation and the goal or the task of the process. The question may be asked, “Is Active Sensing only an application of Control Theory?” Our answer is: “No, at least not in its simple version.” Here is why: 1) The feedback is performed not only on sensory data but on complex processed sensory data, i.e., various extracted features, including relational features. 2) The feedback is dependent on a priori knowledge- models that are a mixture of numeric/parametric and symbolic information. But one can say that Active Sensing is an application of intelligent control theory which includes reasoning, deci- sion making, and control. This approach has been elo- quently stated by Teoenbaum [I]: “Because of the inherent limitation of a single image, the acquisition of information should be treated asan integral part of the perceptual pro- cess . . . Accommodation attacks the fundamental limita- tion of image inadequacy rather than the secondary prob- lems caused by it.” Although he uses the term accommodation rather than active sensing the message is the same. The implications of the active sensing approach are the following: 1) The necessityof models of sensors. This is to say, first, the model of the physics of sensors as well as the noise of the sensors. Second, the model of the signal processingand 0018-9219/88/0800-0996$0~.00 0 1988 IEEE PROCEEDINGS OF THF IFFF Vnl 7fi Nn I( AIICIICT 1000data reduction mechanisms that are applied on the mea- sured data. These processes produce parameterswith adef- inite range of expected values plus some measure of uncer- tainties. These models shall be called Local Models. 2) The system (which mirrors the theory) is modular as dictated by good computer science practices and inter- active, that is, it acquires data as needed. In order to be able to make predictions on the whole outcome, we need, in addition to models of each module (as described in 1) above), models for the whole process, including feedback. We shall refer to these as Global Models. 3) Explicit specification of the initial and final statelgoal. If the Active Vision theory is a theory, what is its predic- tive power? There are two components to our theory, each with certain predictions: 1) Local models. At each processing level, local models are characterized by certain internal parameters. Examples of local modelscan be: region growing algorithm with inter- nal parameters, the local similarity and size of the local neighborhood. Another example is an edge detection algo- rithm with parameter of the width of the bandpass filter in which one is detecting the edge effect. These parameters predict a) the definite range of plausible values, and b) the noise and uncertainty which will determine the expected resolution, sensitivitylrobustness of the output results from each module. Following the edge detection example, from the width of the bandpass filter, we can predict how close two


View Full Document

Berkeley COMPSCI 294 - Active Perception

Documents in this Course
"Woo" MAC

"Woo" MAC

11 pages

Pangaea

Pangaea

14 pages

Load more
Download Active Perception
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Active Perception and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Active Perception 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?