Signal Processing

SRI’s Center for Systems and Signals Technology (CSST) is an industry leader in providing high-performance signals processing solutions, open source intelligence, and analytics.

Signals Intelligence (SIGINT)

CSST's signals processing team provides outstanding support to the Department of Defense and Intelligence Community as the lead on a major signals processing subsystem for National Programs. Expertise includes signal detection, characterization, and geo-location in dense signal environments including the system architecture to provide rapid processing. CSST is expanding this capability into the tactical signals processing arena.

Open Source Intelligence (OSINT)

CSST has a proven capability to automatically collect and normalize large quantities of open source data. Our contribution to OSINT programs has combined open source maritime data with national sources’ data to produce the most comprehensive collection of openly available maritime information. We provide context to the content, a much needed capability in today’s large data environment. Our exploitation system implements a generalized platform for non-attributable discovery, collection, ingestion, normalization and storage of disparate data from open source repositories.

Analytics

CSST has recently added analytics to its capabilities list, particularly in the areas of decision optimization, predictive analysis, forecasting, and statistical modeling. CSST’s expertise enhances the increasing requirement for data transformation to knowledge. Virtual Personal Assistance (VPA) is transitioning the artificial intelligence created in DARPA projects into analytic processing. VPA enables ‘just ask for it’ user interaction, allowing for multi-source data exploitation while reducing mundane tasks enabling more time for true analysis. 

Publications

In this paper published in the Proceedings of the 2013 International Technical Meeting of The Institute of Navigation, we present a general method for online sensor calibration using factor graphs, which can be applied to a wide range of sensors and parameter types.

This paper, published in the Interservice/Industry Training, Simulation & Education Journal, addresses the need within the military to enhance its training capability to provide more realistic and timely training, but without incurring excessive costs in time and infrastructure.

In this paper, published in IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2012. Camera tracking system for augmented reality applications that can operate both indoors and outdoors is described.

In this paper, published in IEEE Visual Communications and Image Processing, we introduce Vision Guided Compression (VGC), as a pre-processing technology that can be coupled with standards-based video coding, to provide FMV at low-bit rates.

In this paper, published in Intelligent Robots and Systems (IROS), 2012. We present a system for detecting pedestrians at long ranges using a combination of stereo-based detection, classification using deep learning, and a cascade of specialized classifiers.

In this paper, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 . We present an augmented reality system based on Kinect for on-line handbag shopping.

In this paper, published in IEEE Computer Society Conference on Stereo Vision Vision and Pattern Recognition Workshops (CVPRW), 2012. Processing is a critical component of Augmented Reality systems that rely on the precise depth map of a scene.

High-performance dense stereo is a critical component of computer vision applications like 3D reconstruction, robot navigation, and augmented reality. In this paper, we present a low-power, high performance FPGA implementation of a stereo algorithm suitable for embedded real-time platforms.

In this paper published in IEEE International Conference on Technologies for Practical Robot Applications (TePRA), 2012. This paper presents an on-the-move pedestrian detection system that utilizes multiple sensor modalities to improve detection rates at deployable computational loads.