Our recent experience working as part of a large team has enabled us to identify the role that terminology development plays in team coordination, idea generation, and software development. This paper provides a summary of our findings.
The interpretation of thermal imagery can be augmented with information derived from human thermal modeling to better infer human activity during, or prior to, data capture. This additional insight into human activity could prove useful in security and surveillance applications. We have implemented Tanabe’s 65 NM thermocomfort model to predict skin surface temperature under a wide variety of environmental, activity and body parameters. Here, humans are modeled as sixteen segments (head, chest, upper leg, etc.), wherein spherical geometry is assumed for the head and cylindrical geometry is assumed for all other segments. Each segment is comprised of four layers: core, muscle, fat, and skin. Clothing is modeled as an additional layer (or layers) of resistance. Users supply input parameters via our custom MATLAB graphical user interface that includes a robust clothing database based on McCullough’s A Database for Determining the Evaporative Resistance of Clothing, and then Tanabe’s bioheat equations are solved to predict skin temperatures of each body segment. As an initial step of model validation, we compared our computed thermal resistances with literature values. Our evaporative and dry resistance on a per segment basis agreed with literature values. The dry resistance of each segment varied no more than .03 [m2°C/W]. Model validation will be extended to compare the results of our human subject trials (known body parameters, clothing, environmental factors and activity levels) to model outputs. Agreement would further substantiate the propagation of model- predicted skin temperatures through the thermal imager’s transfer function to predict human heat signatures in thermal imagery.
Real-time, stand-off sensing of human subjects to detect emotional state would be valuable in many defense, security and medical scenarios. We are developing a multimodal sensor platform that incorporates high-resolution electro-optical and mid-wave infrared (MWIR) cameras and a millimeter-wave radar system to identify individuals who are psychologically stressed. Recent experiments have aimed to: 1) assess responses to physical versus psychological stressors; 2) examine the impact of topical skin products on thermal signatures; and 3) evaluate the fidelity of vital signs extracted from thermal imagery and radar signatures. Registered image and sensor data were collected as subjects (n=32) performed mental and physical tasks. In each image, the face was segmented into 29 non-overlapping segments based on fiducial points automatically output by our facial feature tracker. Image features were defined that facilitated discrimination between psychological and physical stress states. To test the ability to intentionally mask thermal responses indicative of anxiety or fear, subjects applied one of four topical skin products to one half of their face before performing tasks. Finally, we evaluated the performance of two non-contact techniques to detect respiration and heart rate: chest displacement extracted from the radar signal and temperature fluctuations at the nose tip and regions near superficial arteries to detect respiration and heart rates, respectively, extracted from the MWIR imagery. Our results are very satisfactory: classification of physical versus psychological stressors is repeatedly greater than 90%, thermal masking was almost always ineffective, and accurate heart and respiration rates are detectable in both thermal and radar signatures.
We aim to identify humans in multimodal imagery by predicting the human long-wave infrared (LWIR) signature in a
variety of scenarios. By adapting Tanabe's thermocomfort model, we simulate human body heat flow both between
tissue layers (core, muscle, fat and skin) and between body segments (head, chest, upper arm, etc.). To assess the validity
of our implementation, we simulated the conditions described in actual human subject studies, and compared our results
to values reported in the literature. Inputs to the model include age, height, weight, clothing, physical activity and
ambient conditions, including temperature, humidity and wind velocity. Iteration of heat transport equations and a
thermoregulatory component yields temporal data of segment surface temperature. Our model was found to be in close
agreement with experimentally collected data, with a maximum deviation from literature values of approximately 0.80%.
By comparing the predicted human thermal signature to deblurred LWIR images and then fusing this information at the
feature level with high-resolution electro-optical image data, we can facilitate identity detection of objects in a scene
acquired under different conditions. Ultimately, our goal is to differentiate humans from their surroundings and label
non-human objects as thermal clutter.
Receiver operator characteristic (ROC) analysis is an emerging automated target recognition system performance assessment tool. The ROC metric, area under the curve (AUC), is a universally accepted measure of classifying accuracy. In the presented approach, the detection algorithm output, i.e., a response plane (RP), must consist of grayscale values wherein a maximum value (e.g. 255) corresponds to highest probability of target locations. AUC computation involves the comparison of the RP and the ground truth to classify RP pixels as true positives (TP), true negatives (TN), false positives (FP), or false negatives (FN). Ideally, the background and all objects other than targets are TN. Historically, evaluation methods have excluded the background, and only a few spoof objects likely to be considered as a hit by detection algorithms were a priori demarcated as TN. This can potentially exaggerate the algorithm's performance. Here, a new ROC approach has been developed that divides the entire image into mutually exclusive target (TP) and background (TN) grid squares with adjustable size. Based on the overlap of the thresholded RP with the TP and TN grids, the FN and FP fractions are computed. Variation of the grid square size can bias the ROC results by artificially altering specificity, so an assessment of relative performance under a constant grid square size is adopted in our approach. A pilot study was performed to assess the method's ability to capture RP changes under three different detection algorithm parameter settings on ten images with different backgrounds and target orientations. An ANOVA-based comparison of the AUCs for the three settings showed a significant difference (p<0.001) at 95% confidence interval.
Most man-made objects provide characteristic straight line edges and, therefore, edge extraction is a commonly used target detection tool. However, noisy images often yield broken edges that lead to missed detections, and extraneous edges that may contribute to false target detections. We present a sliding-block approach for target detection using weighted power spectral analysis. In general, straight line edges appearing at a given frequency are represented as a peak in the Fourier domain at a radius corresponding to that frequency, and a direction corresponding to the orientation of the edges in the spatial domain. Knowing the edge width and spacing between the edges, a band-pass filter is designed to extract the Fourier peaks corresponding to the target edges and suppress image noise. These peaks are then detected by amplitude thresholding. The frequency band width and the subsequent spatial filter mask size are variable parameters to facilitate detection of target objects of different sizes under known imaging geometries. Many military objects, such as trucks, tanks and missile launchers, produce definite signatures with parallel lines and the algorithm proves to be ideal for detecting such objects. Moreover, shadow-casting objects generally provide sharp edges and are readily detected. The block operation procedure offers advantages of significant reduction in noise influence, improved edge detection, faster processing speed and versatility to detect diverse objects of different sizes in the image. With Scud missile launcher replicas as target objects, the method has been successfully tested on terrain board test images under different backgrounds, illumination and imaging geometries with cameras of differing spatial resolution and bit-depth.
KEYWORDS: Object recognition, Information theory, Signal to noise ratio, Monte Carlo methods, Detection and tracking algorithms, Image transmission, Associative arrays, Image analysis, Image processing, Calibration
Discrimination of friendly or hostile objects is investigated using information-theory measures/metric in an image
which has been compromised by a number of factors. In aerial military images, objects with different orientations can
be reasonably approximated by a single identification signature consisting of the average histogram of the object under
rotations. Three different information-theoretic measures/metrics are studied as possible criteria to help classify the
objects. The first measure is the standard mutual information (MI) between the sampled object and the library object
signatures. A second measure is based on information efficiency, which differs from MI. Finally an information
distance metric is employed which determines the distance, in an information sense, between the sampled object and the
library object. It is shown that the three (parsimonious) information-theoretic variables introduced here form an
independent basis in the sense that any variable in the information channel can be uniquely expressed in terms of the
three parameters introduced here. The methodology discussed is tested on a sample set of standardized images to
evaluate their efficacy. A performance standardization methodology is presented which is based on manipulation of
contrast, brightness, and size attributes of the sample objects of interest.
KEYWORDS: Signal to noise ratio, Detection and tracking algorithms, Stochastic processes, Interference (communication), Nonlinear filtering, Signal detection, Electronic filtering, Filtering (signal processing), Physics, Monte Carlo methods
Object detection in images was conducted using a nonlinear means of improving signal to noise ratio termed "stochastic
resonance" (SR). In a recent United States patent application, it was shown that arbitrarily large signal to noise ratio
gains could be realized when a signal detection problem is cast within the context of a SR filter. Signal-to-noise ratio
measures were investigated. For a binary object recognition task (friendly versus hostile), the method was implemented
by perturbing the recognition algorithm and subsequently thresholding via a computer simulation. To fairly test the
efficacy of the proposed algorithm, a unique database of images has been constructed by modifying two sample library
objects by adjusting their brightness, contrast and relative size via commercial software to gradually compromise their
saliency to identification. The key to the use of the SR method is to produce a small perturbation in the identification
algorithm and then to threshold the results, thus improving the overall system's ability to discern objects. A background
discussion of the SR method is presented. A standard test is proposed in which object identification algorithms could be
fairly compared against each other with respect to their relative performance.
Our challenge was to develop a semi-automatic target detection algorithm to aid human operators in
locating potential targets within images. In contrast to currently available methods, our approach is
relatively insensitive to image brightness, image contrast and object orientation. Working on overlapping
image blocks, we used a sliding difference method of histogram matching. Incrementally sliding the
histograms of the known object template and the image region of interest (ROI) together, the sum of
absolute histogram differences was calculated. The minimum of the resultant array was stored in the
corresponding spatial position of response surface matrix. Local minima of the response surface suggest
possible target locations. Because the template contrast will rarely perfectly match the contrast of the actual
image contrast, which can be compromised by illumination conditions, background features, cloud cover,
etc., we perform a random contrast manipulation, which we term 'wobble', on the template histogram. Our
results have shown increased object detection with the combination of the sliding histogram difference and
wobble.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.