Computer vision publications
-
The F Region and Topside Ionosphere Response to a Strong Geomagnetic Storm at Arecibo
We analyze the data derived from the Arecibo incoherent scatter radar measurements to investigate the response of the F region and topside ionosphere to a strong geomagnetic storm that occurred during the…
-
3D Optic Disc Reconstruction Via a Global Fundus Stereo Algorithm
This paper presents a novel method to recover 3D structure of the optic disc in the retina from two uncalibrated fundus images.
-
Affect Analysis in Natural Human Interaction Using Joint Hidden Conditional Random Fields
We present a novel approach for multi-modal affect analysis in human interactions that is capable of integrating data from multiple modalities while also taking into account temporal dynamics.
-
Recognizing Activities Via Bag of Words for Attribute Dynamics
In this work, we propose a novel video representation for activity recognition that models video dynamics with attributes of activities. A video sequence is decomposed into short-term segments, which are…
-
An Embedded Vision Services Framework for Heterogeneous Accelerators
This paper describes an architecture framework using heterogeneous hardware accelerators for embedded vision applications.
-
Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions
In this paper, we propose a novel approach to extract primary object segments in videos in the ‘object proposal’ domain. The extracted primary object regions are then used to build…
-
Low-Light NV-CMOS Image Sensors for Day/Night Imaging
SRI’s new NV-CMOS™ image sensor technology is designed to capture images over the full range of illumination from bright sunlight to overcast starlight.
-
3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image
We present a unified framework for detecting and classifying people interactions in unconstrained user generated images.
-
Motion Adaptive Signal Integration-High Dynamic Range (MASI-HDR) Video Processing for Dynamic Platforms
SRI’s MASI-HDR (Motion Adaptive Signal Integration-High Dynamic Range) is a novel technique for generating blur-reduced video using multiple captures for each displayed frame while increasing the effective camera dynamic range…
-
On the Applicability of Speaker Diarization to Audio Indexing of Non-Speech and Mixed Non-Speech/Speech Video
This paper explores how unsupervised audio segmentation systems like speaker diarization can be adapted to automatically identify low-level sound concepts similar to annotator defined concepts and how these concepts can…
-
Synthesis and Thermoluminescence Characteristics of Gamma and Proton Irradiated Nanocrystalline MgB4o7: Dy, Na
This paper investigates the use of nanocrystalline MgB4O7: Dy, Na thermoluminescent (TL) dosimeter synthesized by the combustion method for the assessment of proton beam and gamma radiation doses, primarily on…
-
Domain Adaptive Object Detection
We study the use of domain adaptation and transfer learning techniques as part of a framework for adaptive object detection.