Dr. Nathan Mundhenk Profile

Dr. Nathan Mundhenk

Machine Learning Group Leader at Lawrence Livermore National Lab

SPIE Involvement:

Conference Program Committee | Author

Area of Expertise:

Computer Vision , Image Processing , Machine Learning , Biologically Inspired Methods

Websites:

Personal Website | Company Website

Publications (22)

Proceedings Article | 1 August 2021 Presentation

Explaining neural network predictions of material strength

Nathan Mundhenk, Ian Palmer, Brian Gallagher, T. Yong Han

Proceedings Volume 11843, 1184302 (2021) https://doi.org/10.1117/12.2594295

KEYWORDS: Scanning electron microscopy, Neural networks, Crystals, Volume rendering, Photography, Machine vision, Electron microscopes, Computer vision technology, Artificial intelligence

Read Abstract +

Proceedings Article | 4 March 2019 Presentation + Paper

Using convolutional neural networks to classify static x-ray imager diagnostic data at the National Ignition Facility

William Leach, James Henrikson, Robert Hatarik, Judy Liebman, Nathan Mundhenk, Nathan Palmer, Matt Rever

Proceedings Volume 10898, 108980I (2019) https://doi.org/10.1117/12.2512605

KEYWORDS: National Ignition Facility, Diagnostics, X-ray imaging, X-rays, Convolutional neural networks, Image processing, Image filtering, Image quality, Databases

Read Abstract +

Proceedings Article | 14 May 2017 Paper

Deep learning for evaluating difficult-to-detect incomplete repairs of high fluence laser optics at the National Ignition Facility

T. Nathan Mundhenk, Laura Kegelmeyer, Scott Trummer

Proceedings Volume 10338, 103380H (2017) https://doi.org/10.1117/12.2264000

KEYWORDS: Laser optics, National Ignition Facility, Process control, Neural networks, Visualization, RGB color model, Image classification, Fusion energy, Inspection, Machine learning, Video, Image processing

Read Abstract +

Proceedings Article | 8 February 2015 Paper

PanDAR: a wide-area, frame-rate, and full color lidar with foveated region using backfilling interpolation upsampling

T. Nathan Mundhenk, Kyungnam Kim, Yuri Owechko

Proceedings Volume 9406, 94060K (2015) https://doi.org/10.1117/12.2078348

KEYWORDS: Clouds, LIDAR, Cameras, Image fusion, Sensors, Image processing, Head, Panoramic photography, Calibration, Resolution enhancement technologies

Read Abstract +

Proceedings Article | 3 February 2014 Paper

Classification and segmentation of orbital space based objects against terrestrial distractors for the purpose of finding holes in shape from motion 3D reconstruction

T. Nathan Mundhenk, Arturo Flores, Heiko Hoffman

Proceedings Volume 9025, 90250K (2014) https://doi.org/10.1117/12.2047338

KEYWORDS: Image segmentation, 3D modeling, Space operations, System on a chip, Image classification, Atomic force microscopy, Cameras, Associative arrays, Visualization, Space telescopes

Read Abstract +

3D reconstruction of objects via Shape from Motion (SFM) has made great strides recently. Utilizing images from a variety of poses, objects can be reconstructed in 3D without knowing a priori the camera pose. These feature points can then be bundled together to create large scale scene reconstructions automatically. A shortcoming of current methods of SFM reconstruction is in dealing with specular or flat low feature surfaces. The inability of SFM to handle these places creates holes in a 3D reconstruction. This can cause problems when the 3D reconstruction is used for proximity detection and collision avoidance by a space vehicle working around another space vehicle. As such, we would like the automatic ability to recognize when a hole in a 3D reconstruction is in fact not a hole, but is a place where reconstruction has failed. Once we know about such a location, methods can be used to try to either more vigorously fill in that region or to instruct a space vehicle to proceed with more caution around that area. Detecting such areas in earth orbiting objects is non-trivial since we need to parse out complex vehicle features from complex earth features, particularly when the observing vehicle is overhead the target vehicle. To do this, we have created a Space Object Classifier and Segmenter (SOCS) hole finder. The general principle we use is to classify image features into three categories (earth, man-made, space). Classified regions are then clustered into probabilistic regions which can then be segmented out. Our categorization method uses an augmentation of a state of the art bag of visual words method for object categorization. This method works by first extracting PHOW (dense SIFT like) features which are computed over an image and then quantized via KD Tree. The quantization results are then binned into histograms and results classified by the PEGASOS support vector machine solver. This gives a probability that a patch in the image corresponds to one of three categories: Earth, Man-Made or Space. Here man-made refers to artificial objects in space. To categorize a whole image, a common sliding window protocol is used. Here we utilized 90 high resolution images from space shuttle servicing missions of the international space station. We extracted 9000 128x128 patches from the images, then we hand sorted them into one of three categories. We then trained our categorizer on a subset of 6000 patches. Testing on 3000 testing patches yielded 96.8% accuracy. This is basically good enough because detection returns a probabilistic score (e.g. p of man-made). Detections can then be spatially pooled to smooth out statistical blips. Spatial pooling can be done by creating a three channel (dimension) image where each channel is the probability of each of the three classes at that location in the image. The probability image can then be segmented or co-segmented with the visible image using a classical segmentation method such as Mean Shift. This yields contiguous regions of classified image. Holes can be detected when SFM does not fill in a region segmented as man-made. Results are shown of the SOCS implementation finding and segmenting man-made objects in pictures containing space vehicles very different from the training set such as Skylab, the Hubble space telescope or the Death Star.

SPIE Journal Paper | 11 June 2012

Methods for efficient correction of complex noise in outdoor video rate passive millimeter wavelength imagery

Terrell Mundhenk, Josh Baron, Roy Matic

OE, Vol. 51, Issue 9, 091608, (June 2012) https://doi.org/10.1117/12.10.1117/1.OE.51.9.091608

KEYWORDS: Video, Nonuniformity corrections, Passive millimeter wave sensors, Image filtering, Image processing, Signal to noise ratio, Motion estimation, Imaging systems, Deconvolution, Wavelets

Read Abstract +

Proceedings Article | 23 January 2012 Paper

Detection of unknown targets from aerial camera and extraction of simple object fingerprints for the purpose of target reacquisition

T. Nathan Mundhenk, Kang-Yu Ni, Yang Chen, Kyungnam Kim, Yuri Owechko

Proceedings Volume 8301, 83010H (2012) https://doi.org/10.1117/12.906491

KEYWORDS: Video, Cameras, Image segmentation, Target acquisition, Target detection, Data modeling, Imaging systems, Computer simulations, Performance modeling, Light sources and illumination

Read Abstract +

An aerial multiple camera tracking paradigm needs to not only spot unknown targets and track them, but also needs to know how to handle target reacquisition as well as target handoff to other cameras in the operating theater. Here we discuss such a system which is designed to spot unknown targets, track them, segment the useful features and then create a signature fingerprint for the object so that it can be reacquired or handed off to another camera. The tracking system spots unknown objects by subtracting background motion from observed motion allowing it to find targets in motion, even if the camera platform itself is moving. The area of motion is then matched to segmented regions returned by the EDISON mean shift segmentation tool. Whole segments which have common motion and which are contiguous to each other are grouped into a master object. Once master objects are formed, we have a tight bound on which to extract features for the purpose of forming a fingerprint. This is done using color and simple entropy features. These can be placed into a myriad of different fingerprints. To keep data transmission and storage size low for camera handoff of targets, we try several different simple techniques. These include Histogram, Spatiogram and Single Gaussian Model. These are tested by simulating a very large number of target losses in six videos over an interval of 1000 frames each from the DARPA VIVID video set. Since the fingerprints are very simple, they are not expected to be valid for long periods of time. As such, we test the shelf life of fingerprints. This is how long a fingerprint is good for when stored away between target appearances. Shelf life gives us a second metric of goodness and tells us if a fingerprint method has better accuracy over longer periods. In videos which contain multiple vehicle occlusions and vehicles of highly similar appearance we obtain a reacquisition rate for automobiles of over 80% using the simple single Gaussian model compared with the null hypothesis of <20%. Additionally, the performance for fingerprints stays well above the null hypothesis for as much as 800 frames. Thus, a simple and highly compact single Gaussian model is useful for target reacquisition. Since the model is agnostic to view point and object size, it is expected to perform as well on a test of target handoff. Since some of the performance degradation is due to problems with the initial target acquisition and tracking, the simple Gaussian model may perform even better with an improved initial acquisition technique. Also, since the model makes no assumption about the object to be tracked, it should be possible to use it to fingerprint a multitude of objects, not just cars. Further accuracy may be obtained by creating manifolds of objects from multiple samples.

Proceedings Article | 1 June 2011 Paper

Efficient reduction of complex noise in passive millimeter-wavelength video utilizing Bayesian surprise

T. Nathan Mundhenk, Josh Baron, Roy Matic

Proceedings Volume 8042, 804210 (2011) https://doi.org/10.1117/12.887672

KEYWORDS: Video, Nonuniformity corrections, Image filtering, Passive millimeter wave sensors, Imaging systems, Image processing, Discrete wavelet transforms, Image enhancement, Fourier transforms, Motion estimation

Read Abstract +

Proceedings Article | 24 January 2011 Paper

High precision object segmentation and tracking for use in super resolution video reconstruction

T. Nathan Mundhenk, Rashmi Sundareswara, David Gerwe, Yang Chen

Proceedings Volume 7878, 78780G (2011) https://doi.org/10.1117/12.871605

KEYWORDS: Image segmentation, Super resolution, Video, Image restoration, Image enhancement, Motion estimation, Cameras, Motion detection, Motion models, Visualization

Read Abstract +

Proceedings Article | 25 October 2005 Paper

Task-selection and task-merging for directional and vision-based sensors

Jacob Everist, T. Nathan Mundhenk, Chris Landauer, Kirstie Bellman

Proceedings Volume 6006, 600609 (2005) https://doi.org/10.1117/12.630957

KEYWORDS: Cameras, Sensors, Surveillance, Servomechanisms, Calibration, Detection and tracking algorithms, Imaging systems, Image processing, Switches, Filtering (signal processing)

Read Abstract +

Proceedings Article | 25 October 2005 Paper

Distributed biologically-based real-time tracking in the absence of prior target information

T. Nathan Mundhenk, Jacob Everist, Chris Landauer, Laurent Itti, Kirstie Bellman

Proceedings Volume 6006, 60060D (2005) https://doi.org/10.1117/12.631076

KEYWORDS: RGB color model, Visualization, Cameras, Video, Feature extraction, Optical tracking, Automatic tracking, Target acquisition, Algorithm development, Distributed computing

Read Abstract +

Proceedings Article | 25 October 2005 Paper

Visual surveillance coverage: strategies and metrics

Jacob Everist, T. Nathan Mundhenk, Chris Landauer, Kirstie Bellman

Proceedings Volume 6006, 600608 (2005) https://doi.org/10.1117/12.630943

KEYWORDS: Cameras, Target detection, Sensors, Servomechanisms, Surveillance, Imaging systems, Machine vision, Computer vision technology, Video surveillance, Satellites

Read Abstract +

Proceedings Article | 25 October 2004 Paper

Teaching the computer subjective notions of feature connectedness in a visual scene for real-time vision

Terrell Mundhenk, Chris Landauer, Kirstie Bellman, Michael Arbib, Laurent Itti

Proceedings Volume 5608, (2004) https://doi.org/10.1117/12.571768

KEYWORDS: Visualization, Independent component analysis, Image processing, Principal component analysis, Monte Carlo methods, Image filtering, Visual analytics, Feature selection, Feature extraction, Aerospace engineering

Read Abstract +

We discus a tool kit for usage in scene understanding where prior information about targets is not necessarily understood. As such, we give it a notion of connectivity such that it can classify features in an image for the purpose of tracking and identification. The tool VFAT (Visual Feature Analysis Tool) is designed to work in real time in an intelligent multi agent room. It is built around a modular design and includes several fast vision processes. The first components discussed are for feature selection using visual saliency and Monte Carlo selection. Then features that have been selected from an image are mixed into useful and more complex features. All the features are then reduced in dimension and contrasted using a combination of Independent Component Analysis and Principle Component Analysis (ICA/PCA). Once this has been done, we classify features using a custom non-parametric classifier (NPclassify) that does not require hard parameters such as class size or number of classes so that VFAT can create classes without stringent priors about class structure. These classes are then generalized using Gaussian regions which allows easier storage of class properties and computation of probability for class matching. To speed up to creation of Gaussian regions we use a system of rotations instead of the traditional Psuedo-inverse method. In addtion to discussing the structure of VFAT we discuss training of the current system which is relatively easy to perform. ICA/PCA is trained by giving VFAT a large number of random images. The ICA/PCA matrix is computed by features extracted by VFAT. The non-parametric classifier NPclasify it trained by presenting it with images of objects having it decide how many objects it thinks it sees. The difference between what it sees and what it is supposed to see in terms of the number of objects is used as the error term and allows VFAT to learn to classify based upon the experimenters subjective idea of good classification.

Proceedings Article | 25 October 2004 Paper

Camera localization methods for intelligent room systems using RF techniques

Pradeep Natarajan, Terrell Mundhenk, Kirstie Bellman, Laurent Itti, Michael Arbib

Proceedings Volume 5608, (2004) https://doi.org/10.1117/12.571793

KEYWORDS: Cameras, Error analysis, Algorithm development, Imaging systems, Intelligence systems, Receivers, Signal attenuation, Received signal strength, Sensors, Telecommunications

Read Abstract +

Proceedings Article | 7 June 2004 Paper

Biologically inspired feature-based categorization of objects

T. Nathan Mundhenk, Vidhya Navalpakkam, Hendrik Makaliwe, Shrihari Vasudevan, Laurent Itti

Proceedings Volume 5292, (2004) https://doi.org/10.1117/12.527321

KEYWORDS: Algorithm development, Image segmentation, Independent component analysis, Visualization, Feature extraction, Detection and tracking algorithms, Navigation systems, Cameras, Expectation maximization algorithms, Object recognition

Read Abstract +

Proceedings Article | 30 September 2003 Paper

Low-cost high-performance mobile robot design utilizing off-the-shelf parts and the Beowulf concept: the Beobot project

Terrell Mundhenk, Christopher Ackerman, Daesu Chung, Nitin Dhavale, Brian Hudson, Ried Hirata, Eric Pichon, Zhan Shi, April Tsui, Laurent Itti

Proceedings Volume 5267, (2003) https://doi.org/10.1117/12.515180

KEYWORDS: Robotics, RGB color model, Detection and tracking algorithms, Image segmentation, Servomechanisms, Video, Computing systems, Cameras, Operating systems, Mobile robots

Read Abstract +

Proceedings Article | 30 September 2003 Paper

Utilization and viability of biologically inspired algorithms in a dynamic multiagent camera surveillance system

Terrell Mundhenk, Nitin Dhavale, Salvador Marmol, Elizabeth Calleja, Vidhya Navalpakkam, Kirstie Bellman, Chris Landauer, Michael Arbib, Laurent Itti

Proceedings Volume 5267, (2003) https://doi.org/10.1117/12.515176

KEYWORDS: Cameras, Visualization, Brain, Calibration, Iron, Surveillance systems, Imaging systems, Video, Detection and tracking algorithms, Brain mapping

Read Abstract +

In view of the growing complexity of computational tasks and their design, we propose that certain interactive systems may be better designed by utilizing computational strategies based on the study of the human brain. Compared with current engineering paradigms, brain theory offers the promise of improved self-organization and adaptation to the current environment, freeing the programmer from having to address those issues in a procedural manner when designing and implementing large-scale complex systems. To advance this hypothesis, we discus a multi-agent surveillance system where 12 agent CPUs each with its own camera, compete and cooperate to monitor a large room. To cope with the overload of image data streaming from 12 cameras, we take inspiration from the primate’s visual system, which allows the animal to operate a real-time selection of the few most conspicuous locations in visual input. This is accomplished by having each camera agent utilize the bottom-up, saliency-based visual attention algorithm of Itti and Koch (Vision Research 2000;40(10-12):1489-1506) to scan the scene for objects of interest. Real time operation is achieved using a distributed version that runs on a 16-CPU Beowulf cluster composed of the agent computers. The algorithm guides cameras to track and monitor salient objects based on maps of color, orientation, intensity, and motion. To spread camera view points or create cooperation in monitoring highly salient targets, camera agents bias each other by increasing or decreasing the weight of different feature vectors in other cameras, using mechanisms similar to excitation and suppression that have been documented in electrophysiology, psychophysics and imaging studies of low-level visual processing. In addition, if cameras need to compete for computing resources, allocation of computational time is weighed based upon the history of each camera. A camera agent that has a history of seeing more salient targets is more likely to obtain computational resources. The system demonstrates the viability of biologically inspired systems in a real time tracking. In future work we plan on implementing additional biological mechanisms for cooperative management of both the sensor and processing resources in this system that include top down biasing for target specificity as well as novelty and the activity of the tracked object in relation to sensitive features of the environment.

Proceedings Article | 11 October 2000 Paper

Simple obstacle detection to prevent miscalculation of line location and orientation in line following using statistically calculated expected values

Terrell Mundhenk, Michael Rivett, Ernest Hall

Proceedings Volume 4197, (2000) https://doi.org/10.1117/12.403789

KEYWORDS: Cameras, Robotics, Switches, Fourier transforms, Video, Imaging systems, Switching, Visualization, Mobile robots, Education and training

Read Abstract +

Proceedings Article | 11 October 2000 Paper

Techniques for fisheye lens calibration using a minimal number of measurements

Terrell Mundhenk, Michael Rivett, Xiaoqun Liao, Ernest Hall

Proceedings Volume 4197, (2000) https://doi.org/10.1117/12.403762

KEYWORDS: Distortion, Calibration, Cameras, Spherical lenses, Error analysis, Robot vision, Robotics, Video, C++, Manufacturing

Read Abstract +

Proceedings Article | 26 August 1999 Paper

Intelligent robot trends and predictions for the new millennium

Ernest Hall, Terrell Mundhenk

Proceedings Volume 3837, (1999) https://doi.org/10.1117/12.360303

KEYWORDS: Control systems, Robotics, Mechatronics, Sensors, Robot vision, Manufacturing, Intelligent sensors, Kinematics, Safety, Defense and security

Read Abstract +

Proceedings Article | 6 October 1998 Paper

Range detection for AGV using a rotating sonar sensor

Wen-chuan Chiang, Dhyana Chandra Ramamurthy, Terrell Mundhenk, Ernest Hall

Proceedings Volume 3522, (1998) https://doi.org/10.1117/12.325788

KEYWORDS: Computer programming, Transducers, Sensors, Motion controllers, Robot vision, Ultrasonics, Mobile robots, Computing systems, Ranging, Control systems design

Read Abstract +

Proceedings Article | 6 October 1998 Paper

Path planning for mobile robot using sonar map and neural network

Jin Cao, Wen-chuan Chiang, Terrell Mundhenk, Ernest Hall

Proceedings Volume 3522, (1998) https://doi.org/10.1117/12.325771

KEYWORDS: Neural networks, Mobile robots, Control systems, Sensors, Robot vision, Space robots, Evolutionary algorithms, Detection and tracking algorithms, Environmental sensing, Computing systems

Read Abstract +