APL-UW Home

Jobs
About
Campus Map
Contact
Privacy
Intranet

James Pitton

Senior Principal Engineer

Affiliate Associate Professor, Electrical Engineering

Email

pitton@apl.washington.edu

Phone

206-685-1843

Research Interests

Statistical Signal Processing, Digital Communications, Auditory Science, Psychoacoustics

Biosketch

James Pitton is a Senior Principal Engineer at APL-UW and Affiliate Associate Professor of Electrical Engineering at the University of Washington. From 2007 until 2010, he was the Associate Director for Ocean and Undersea Science at the US Office of Naval Research Global (ONR Global) in London, UK. Prior to joining ONR Global, Dr. Pitton joined APL-UW in 1999, and was the Head of the Environmental and Information Systems Department there from 2002 until 2007. Dr. Pitton received his Ph.D. in Electrical Engineering from the University of Washington in Seattle in 1994, and has also held research positions at AT&T Bell Laboratories in Murray Hill, NJ, and the Statistical Sciences Division of MathSoft in Seattle, WA. He has served on the organizing committee of numerous workshops and conferences, including the "Workshop on Machine Intelligence for Autonomous Operations" organized jointly between ONR Global, UK DSTL, and NURC. His ongoing research interests are focused on algorithms for information processing and autonomous systems, with an emphasis on sonar, automatic classification, nonstationary signal processing, and array processing.

Education

B.S. Electrical Engineering, University of Michigan, 1985

M.S. Electrical Engineering, University of Michigan, 1986

Ph.D. Electrical Engineering, University of Washington, 1994

Publications

2000-present and while at APL-UW

Building recurrent networks by unfolding iterative thresholding for equential sparse recovery

Wisdom, S., T. Powers, J. Pitton, and L. Atlas, "Building recurrent networks by unfolding iterative thresholding for equential sparse recovery," Proc., IEEE International Conference on Acoustics, Speech and Signal Processing, 5-9 March, New Orleans, LA, 4346-4350, doi:10.1109/ICASSP.2017.7952977 (IEEE, 2017).

More Info

19 Jun 2017

Historically, sparse methods and neural networks, particularly modern deep learning methods, have been relatively disparate areas. Sparse methods are typically used for signal enhancement, compression, and recovery, usually in an unsupervised framework, while neural networks commonly rely on a supervised training set. In this paper, we use the specific problem of sequential sparse recovery, which models a sequence of observations over time using a sequence of sparse coefficients, to show how algorithms for sparse modeling can be combined with supervised deep learning to improve sparse recovery. Specifically, we show that the iterative soft-thresholding algorithm (ISTA) for sequential sparse recovery corresponds to a stacked recurrent neural network (RNN) under specific architecture and parameter constraints. Then we demonstrate the benefit of training this RNN with backpropagation using supervised data for the task of column-wise compressive sensing of images. This training corresponds to adaptation of the original iterative thresholding algorithm and its parameters. Thus, we show by example that sparse modeling can provide a rich source of principled and structured deep network architectures that can be trained to improve performance on specific tasks.

Robust human tracking based on DPM constrained multiple-kernel from a moving camera

Hou, L., W. Wan, K.-H. Lee, J.-N. Hwang, G. Okopal, and J. Pitton, "Robust human tracking based on DPM constrained multiple-kernel from a moving camera," J. Sign. Process. Syst., 86, 27-39, doi:10.1007/s11265-015-1097-y, 2017

More Info

1 Jan 2017

In this paper, we attempt to solve the challenging task of precise and robust human tracking from a moving camera. We propose an innovative human tracking approach, which efficiently integrates the deformable part model (DPM) into multiple-kernel tracking from a moving camera. The proposed approach consists of a two-stage tracking procedure. For each frame, we first iteratively mean-shift several spatially weighted color histograms, called kernels, from the current frame to the next frame. Each kernel corresponds to a part model of a DPM-detected human. In the second step, conditioned on the tracking results of these kernels on the later frame, we then iteratively mean-shift the part models on that frame. The part models are represented by histogram of gradient (HOG) features, and the deformation cost of each part model provided by the trained DPM detector is used to constrain the movement of each detected body part from the first step. The proposed approach takes advantage of not only low computation owing to the kernel-based tracking, but also robustness of the DPM detector without the need of laborious human detection for each frame. Experimental results have shown that the proposed approach makes it possible to successfully track humans robustly with high accuracy under different scenarios from a moving camera.

Ground-moving-platform-based human tracking using visual SLAM and constrained multiple kernels

Lee, K.-H., J.-N. Hwang, G. Okopal, and J. Pitton, "Ground-moving-platform-based human tracking using visual SLAM and constrained multiple kernels," IEEE Trans. Intell. Transp. Syst., 17, 3602-3612, doi:10.1109/TITS.2016.2557763, 2016.

More Info

1 Dec 2016

This paper proposes a robust ground-moving-platform-based human tracking system, which effectively integrates visual simultaneous localization and mapping (V-SLAM), human detection, ground plane estimation, and kernel-based tracking techniques. The proposed system systematically detects humans from recorded video frames of a moving camera and tracks the humans in the V-SLAM-inferred 3-D space via a tracking-by-detection scheme. To efficiently associate the detected human frame by frame, we propose a novel human tracking framework, combining the constrained-multiple-kernel tracking and the estimated 3-D information (depth), to globally optimize the data association between consecutive frames. By taking advantage of the appearance model and 3-D information, the proposed system not only achieves high effectiveness but also well handles occlusion in the tracking. Experimental results show the favorable performance of the proposed system, which efficiently tracks humans in a camera equipped on a ground-moving platform such as a dash camera and an unmanned ground vehicle.

More Publications

Inventions

3D Reconstruction of Dental Caries Using the Scanning-fiber Endoscope

Record of Invention Number: 47625

Eric Seibel, Matthew Carson, Yuanzheng Gong, James Pitton

Disclosure

16 Feb 2016

Multi-perspective Infrared Interrogation of Teeth

Record of Invention Number: 47417

James Pitton, Eric Seibel

Disclosure

27 Jul 2015

Enhancement of Noisy and Reverberant Speech Using Beamforming and Suppression

Record of Invention Number: 46870

James Pitton

Disclosure

6 Mar 2014

Acoustics Air-Sea Interaction & Remote Sensing Center for Environmental & Information Systems Center for Industrial & Medical Ultrasound Electronic & Photonic Systems Ocean Engineering Ocean Physics Polar Science Center
Close

 

Close