Zobrazeno 1 - 10
of 74
pro vyhledávání: '"A.M. Waxman"'
Autor:
M. Seibert, A.M. Waxman
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 14:107-124
The authors address the problem of generating representations of 3-D objects automatically from exploratory view sequences of unoccluded objects. In building the models, processed frames of a video sequence are clustered into view categories called a
Autor:
A.M. Waxman, I.A. Bachelder
Publikováno v:
Proceedings of PerAc '94. From Perception to Action.
We describe a real-time, view-based neural system for unsupervised exploration, adaptive map-making, and navigation within 3D environments defined by a spatially distributed set of visual landmarks inspired by on analogy to learning aspect graphs of
Publikováno v:
IGARSS
Although the processing of electro-optical imagery from Earth observation satellites has been effectively used for classification of many types of land cover, forest classification has been generally limited to broad categories such as deciduous or c
Publikováno v:
[1989] Proceedings. Workshop on Visual Motion.
Theoretical approaches to the study of perceptual phenomena of short-range and long-range apparent motion are discussed. Short-range motion is estimated by real-time receptive fields sensitive to velocities of image features. The design of these rece
Publikováno v:
CVPR
A method is developed for the measurement of short-range visual motion in image sequences, making use of the motion of image features such as edges and points. Each feature generates a Gaussian activation profile in a spatiotemporal neighborhood of s
Publikováno v:
Proceedings. Computers in Cardiology 1988.
The authors describe initial experience in echocardiographic image processing utilizing PIPE, a high-speed eight-stage array processor capable of performing multiple sequential algorithms at the real-time video field rate. The algorithms implemented
Autor:
A.M. Waxman, D.A. Fay
Publikováno v:
IJCNN-91-Seattle International Joint Conference on Neural Networks.
Summarizes recent work on real-time implementations of early vision neural computations on the PIPE video-rate parallel computer. PIPE is an eight-stage machine for real-time image processing, performing nearly one billion 8-bit operations per second
Autor:
R. Cunningham, A.M. Waxman
Publikováno v:
IJCNN-91-Seattle International Joint Conference on Neural Networks.
Summary form only given, as follows. Spatiotemporal grouping phenomena were examined in the context of static and time-varying imagery. The dynamics of a biologically plausible diffusion-enhancement bilayer was developed that exhibits grouping of sta
Autor:
A.M. Waxman, R.K. Cunningham
Publikováno v:
Proceedings of 1995 IEEE Workshop on Neural Networks for Signal Processing.
The method of convected activation profiles was developed to measure short-range visual motion of edge and point features in time-varying imagery. Each feature is assumed to generate a spatiotemporal Gaussian activation profile that results in a shap
Publikováno v:
IEEE Photonics Technology Letters. 3:761-763
Through-wafer optical communication has been demonstrated in experiments employing two vertically stacked Si wafers, the upper one with In/sub 0.15/Ga/sub 0.85/As-In/sub 0.15/Al/sub 0.85/As double-heterostructure LEDs (light-emitting diodes) grown by