I. A. Essa. Computers seeing people. AI Magazine, 20(1):69--82, 1999. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Conceptual Spaces for Computer Vision Representations - Chella, Frixione, Gaglio (Correct)
.... camera) and gives as its output highly structured data (suitable symbolic descriptions of the scene) Such data are crucial for the e#ective autonomy of a moving robot [2] for sensing actions in planning [22] for teleautonomy and telepresence [8] and also for advanced man machine interfaces [11]. The schema of a general architecture for computer vision is shown in Fig. 1. The first block is the camera. The data in this block are strictly related to the signals coming from the sensors, and they are generally structured as a matrix of pixels. The information in the camera block is ....
I.A. Essa. Computers seeing people. AI Magazine, 20(2):69--82, 1999.
Sensory-Motor Primitives as a Basis for Imitation: Linking.. - Mataric (2000) (12 citations) (Correct)
....problem, and the tools that have been explored to deal with it are varied. They include color, models, and features, often used in combination, and usually at a high computational cost. A detailed survey of movement perception is beyond the scope of this chapter; for more information see Essa (1999). X.4.1 Eye Tracking Studies and Results Johansson (1977) demonstrated the human capability to recognize biological motion from a small number of structured visual cues such as light dots in key locations on the limbs. This well known and subsequently often replicated experiment points toward a ....
Essa, I. A. (1999), `Computers Seeing People', AI Magazine 20(2), 69--82.
Vision-Based Recognition of Actions using Context - Moore (2000) (2 citations) Self-citation (Essa) (Correct)
No context found.
I. Essa, \Computers Seeing People," AI Magazine,Vol. 20, No. 1, pp. 69-82, Summer 1999.
Detecting and Tracking Eyes By Using Their Physiological.. - Haro, Flickner, Essa (2000) (10 citations) Self-citation (Essa) (Correct)
....robust detection and tracking. Once we know which regions are likely to be eyes, we undertake higher level processing on these regions. We observe pairs of regions and probabilistically determine which regions are most likely to be faces when paired together. Prior Work There is much prior work [2] on finding faces and facial features in complex scenes. Some approaches, like Kothari, et al. 4] find eyes in images without finding faces. They observed that image gradient intersection points were good candidate locations for eyes. Most false positives were removed by ensuring similar numbers ....
I. Essa. Computers seeing people. AI Magazine, 20(1):69--82, Summer 1999.
Scale-Based Human Motion Representation for Action.. - Pers, Vuckovic, Dezman.. (2003) (Correct)
No context found.
I. A. Essa. Computers seeing people. AI Magazine, 20(1):69--82, 1999.
15 Seconds of Fame - Solina (2003) (Correct)
No context found.
I. A. Essa, "Computers seeing people", AI Magazine,Vol. 20, No. 2, 69--82 (1999).
A 3D Object Extraction and Recognition Method. - Antonio Carlos Zimmermann (Correct)
No context found.
Irfan A. Essa, "Computers Seeing People", American Association for Artificial Intelligence, AI Magazine, Summer 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC