Abstract

The popularity of hyperspectral imaging (HSI) in remote sensing continues to lead to it being adapted in novel ways to overcome challenging imaging problems. This paper reports on research efforts exploring the phenomenology of using HSI as an aid in detecting and tracking human pedestrians. An assessment of the likelihood of distinguishing between pedestrians based on the measured spectral reflectance of observable materials and the presence of noise is presented. The assessments included looking at the spectral separation between pedestrian material subregions using different spectral-reflectance regions within the full range (450–2500 nm), as well as when the spectral content of the pedestrian subregions are combined. In addition to the pedestrian spectral-reflectance data analysis, the separability of pedestrian subregions in remotely sensed hyperspectral images was assessed using a unique data set garnered as part of this work. Results indicated that skin was the least distinguishable material between pedestrians using the spectral Euclidean distance metric. The clothing, especially the shirt, offered the most salient feature for distinguishing the pedestrian. Additionally, significant spectral separability performance is realized when combining the reflectance information of two or more subregions.

© 2013 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. J. R. Schott, Remote Sensing, 2nd ed. (Oxford University, 2007).
  2. J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
    [CrossRef]
  3. A. Rice, J. Vasquez, M. Mendenhall, and J. Kerekes, “Feature-aided tracking via synthetic hyperspectral imagery,” in First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2009 (IEEE, 2009), pp. 1–4.
  4. A. S. Nunez, “A physical model of human skin and its application for search and rescue,” Ph.D. dissertation, Air Force Institute of Technology, Wright–Patterson Air Force Base, OH (2010).
  5. J. D. Clark, M. J. Mendenhall, and G. L. Peterson, “Stochastic feature selection with distributed feature spacing for hyperspectral data,” in 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) 2010 (IEEE, 2010), pp. 1–4.
  6. J. A. Herweg, J. P. Kerekes, and M. Eismann, “Hyperspectral imaging of natural signatures for pedestrians,” Proc. SPIE 8390, 83901C (2012).
    [CrossRef]
  7. C. M. Jengo and J. LaVeigne, “Sensor performance comparison of HyperSpecTIR instruments 1 and 2,” in Aerospace Conference 2004 Proceedings (IEEE, 2004), Vol. 3, pp. 1799–1805.
  8. Analytical Spectral Devices, Inc., “FieldSpec Pro User’s Guide,” 2002, retrieved, 15 October 2010, http://www.asdi.com .
  9. D. Simmons, “Performance characterization of an innovative illumination source for the analytical spectral device spectroradiometer, FieldSpec Pro FR,” Rochester Institute of Technology Digital Imaging and Remote Sensing Laboratory Probe Development Status Report (2006).
  10. I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
    [CrossRef]
  11. T. L. Haran, “Short-wave infrared diffuse reflectance of textile materials,” Masters’ thesis (Georgia State University, 2008).
  12. P. Bajorski, Statistics for Imaging, Optics, and Photonics (Wiley, 2011).
  13. A. Webb, Statistical Pattern Recognition, 2nd ed. (Wiley, 2005).
  14. J. A. Herweg, “Pedestrian detection phenomenology in a cluttered urban environment using hyperspectral imaging,” Ph.D. dissertation (Rochester Institute of Technology, 2012).
  15. R. S. Berns, Billmeyer and Saltzman’s Principles of Color Technology, 3rd ed. (Wiley, 2000).
  16. E. J. Ientilucci and P. Bajorski, “Stochastic modeling of physically derived signature spaces,” J. Appl. Remote Sens. 2, 1–10 (2008).
    [CrossRef]

2012 (1)

J. A. Herweg, J. P. Kerekes, and M. Eismann, “Hyperspectral imaging of natural signatures for pedestrians,” Proc. SPIE 8390, 83901C (2012).
[CrossRef]

2008 (1)

E. J. Ientilucci and P. Bajorski, “Stochastic modeling of physically derived signature spaces,” J. Appl. Remote Sens. 2, 1–10 (2008).
[CrossRef]

2007 (1)

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

2000 (1)

I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
[CrossRef]

Bajorski, P.

E. J. Ientilucci and P. Bajorski, “Stochastic modeling of physically derived signature spaces,” J. Appl. Remote Sens. 2, 1–10 (2008).
[CrossRef]

P. Bajorski, Statistics for Imaging, Optics, and Photonics (Wiley, 2011).

Bazakos, M.

I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
[CrossRef]

Berns, R. S.

R. S. Berns, Billmeyer and Saltzman’s Principles of Color Technology, 3rd ed. (Wiley, 2000).

Blackburn, J.

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

Clark, J. D.

J. D. Clark, M. J. Mendenhall, and G. L. Peterson, “Stochastic feature selection with distributed feature spacing for hyperspectral data,” in 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) 2010 (IEEE, 2010), pp. 1–4.

Eismann, M.

J. A. Herweg, J. P. Kerekes, and M. Eismann, “Hyperspectral imaging of natural signatures for pedestrians,” Proc. SPIE 8390, 83901C (2012).
[CrossRef]

Fritz, B.

I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
[CrossRef]

Haran, T. L.

T. L. Haran, “Short-wave infrared diffuse reflectance of textile materials,” Masters’ thesis (Georgia State University, 2008).

Herweg, J. A.

J. A. Herweg, J. P. Kerekes, and M. Eismann, “Hyperspectral imaging of natural signatures for pedestrians,” Proc. SPIE 8390, 83901C (2012).
[CrossRef]

J. A. Herweg, “Pedestrian detection phenomenology in a cluttered urban environment using hyperspectral imaging,” Ph.D. dissertation (Rochester Institute of Technology, 2012).

Ientilucci, E. J.

E. J. Ientilucci and P. Bajorski, “Stochastic modeling of physically derived signature spaces,” J. Appl. Remote Sens. 2, 1–10 (2008).
[CrossRef]

Jengo, C. M.

C. M. Jengo and J. LaVeigne, “Sensor performance comparison of HyperSpecTIR instruments 1 and 2,” in Aerospace Conference 2004 Proceedings (IEEE, 2004), Vol. 3, pp. 1799–1805.

Kerekes, J.

A. Rice, J. Vasquez, M. Mendenhall, and J. Kerekes, “Feature-aided tracking via synthetic hyperspectral imagery,” in First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2009 (IEEE, 2009), pp. 1–4.

Kerekes, J. P.

J. A. Herweg, J. P. Kerekes, and M. Eismann, “Hyperspectral imaging of natural signatures for pedestrians,” Proc. SPIE 8390, 83901C (2012).
[CrossRef]

LaVeigne, J.

C. M. Jengo and J. LaVeigne, “Sensor performance comparison of HyperSpecTIR instruments 1 and 2,” in Aerospace Conference 2004 Proceedings (IEEE, 2004), Vol. 3, pp. 1799–1805.

Mendenhall, M.

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

A. Rice, J. Vasquez, M. Mendenhall, and J. Kerekes, “Feature-aided tracking via synthetic hyperspectral imagery,” in First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2009 (IEEE, 2009), pp. 1–4.

Mendenhall, M. J.

J. D. Clark, M. J. Mendenhall, and G. L. Peterson, “Stochastic feature selection with distributed feature spacing for hyperspectral data,” in 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) 2010 (IEEE, 2010), pp. 1–4.

Nunez, A. S.

A. S. Nunez, “A physical model of human skin and its application for search and rescue,” Ph.D. dissertation, Air Force Institute of Technology, Wright–Patterson Air Force Base, OH (2010).

Papanikolopoulos, N.

I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
[CrossRef]

Pavlidis, I.

I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
[CrossRef]

Peterson, G. L.

J. D. Clark, M. J. Mendenhall, and G. L. Peterson, “Stochastic feature selection with distributed feature spacing for hyperspectral data,” in 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) 2010 (IEEE, 2010), pp. 1–4.

Rice, A.

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

A. Rice, J. Vasquez, M. Mendenhall, and J. Kerekes, “Feature-aided tracking via synthetic hyperspectral imagery,” in First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2009 (IEEE, 2009), pp. 1–4.

Schott, J. R.

J. R. Schott, Remote Sensing, 2nd ed. (Oxford University, 2007).

Shelnutt, P.

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

Simmons, D.

D. Simmons, “Performance characterization of an innovative illumination source for the analytical spectral device spectroradiometer, FieldSpec Pro FR,” Rochester Institute of Technology Digital Imaging and Remote Sensing Laboratory Probe Development Status Report (2006).

Soliman, N.

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

Symosek, P.

I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
[CrossRef]

Vasquez, J.

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

A. Rice, J. Vasquez, M. Mendenhall, and J. Kerekes, “Feature-aided tracking via synthetic hyperspectral imagery,” in First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2009 (IEEE, 2009), pp. 1–4.

Webb, A.

A. Webb, Statistical Pattern Recognition, 2nd ed. (Wiley, 2005).

J. Appl. Remote Sens. (1)

E. J. Ientilucci and P. Bajorski, “Stochastic modeling of physically derived signature spaces,” J. Appl. Remote Sens. 2, 1–10 (2008).
[CrossRef]

Machine Vis. Appl. (1)

I. Pavlidis, P. Symosek, B. Fritz, M. Bazakos, and N. Papanikolopoulos, “Automatic detection of vehicle occupants: the imaging problem and its solution,” Machine Vis. Appl. 11, 313–320 (2000).
[CrossRef]

Proc. SPIE (2)

J. Blackburn, M. Mendenhall, A. Rice, P. Shelnutt, N. Soliman, and J. Vasquez, “Feature aided tracking with hyperspectral imagery,” Proc. SPIE 6699, 1–12 (2007).
[CrossRef]

J. A. Herweg, J. P. Kerekes, and M. Eismann, “Hyperspectral imaging of natural signatures for pedestrians,” Proc. SPIE 8390, 83901C (2012).
[CrossRef]

Other (12)

C. M. Jengo and J. LaVeigne, “Sensor performance comparison of HyperSpecTIR instruments 1 and 2,” in Aerospace Conference 2004 Proceedings (IEEE, 2004), Vol. 3, pp. 1799–1805.

Analytical Spectral Devices, Inc., “FieldSpec Pro User’s Guide,” 2002, retrieved, 15 October 2010, http://www.asdi.com .

D. Simmons, “Performance characterization of an innovative illumination source for the analytical spectral device spectroradiometer, FieldSpec Pro FR,” Rochester Institute of Technology Digital Imaging and Remote Sensing Laboratory Probe Development Status Report (2006).

A. Rice, J. Vasquez, M. Mendenhall, and J. Kerekes, “Feature-aided tracking via synthetic hyperspectral imagery,” in First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2009 (IEEE, 2009), pp. 1–4.

A. S. Nunez, “A physical model of human skin and its application for search and rescue,” Ph.D. dissertation, Air Force Institute of Technology, Wright–Patterson Air Force Base, OH (2010).

J. D. Clark, M. J. Mendenhall, and G. L. Peterson, “Stochastic feature selection with distributed feature spacing for hyperspectral data,” in 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) 2010 (IEEE, 2010), pp. 1–4.

T. L. Haran, “Short-wave infrared diffuse reflectance of textile materials,” Masters’ thesis (Georgia State University, 2008).

P. Bajorski, Statistics for Imaging, Optics, and Photonics (Wiley, 2011).

A. Webb, Statistical Pattern Recognition, 2nd ed. (Wiley, 2005).

J. A. Herweg, “Pedestrian detection phenomenology in a cluttered urban environment using hyperspectral imaging,” Ph.D. dissertation (Rochester Institute of Technology, 2012).

R. S. Berns, Billmeyer and Saltzman’s Principles of Color Technology, 3rd ed. (Wiley, 2000).

J. R. Schott, Remote Sensing, 2nd ed. (Oxford University, 2007).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (13)

Fig. 1.
Fig. 1.

True-color radiance image of the HYMNS-P scene with pedestrians present. Several variations of this static scene were used for this research effort.

Fig. 2.
Fig. 2.

Collection setup of a skin spectral-reflectance measurement on the forearm of a pedestrian using the custom field contact probe.

Fig. 3.
Fig. 3.

Spectral profiles for the several relative spectral-reflectance measurements of pedestrians’ hair.

Fig. 4.
Fig. 4.

Spectral profiles for the several relative spectral-reflectance measurements of pedestrians’ facial skin.

Fig. 5.
Fig. 5.

Spectral profiles for the several relative spectral-reflectance measurements of pedestrians’ clothing fabric on the torso.

Fig. 6.
Fig. 6.

Spectral profiles for the several relative spectral reflectance measurements of pedestrian’s trousers or shorts.

Fig. 7.
Fig. 7.

Textile reflectance spectra taken from pedestrian clothing in the HYMNS-P data set. The spectral differences between the three material types are apparent.

Fig. 8.
Fig. 8.

Example of the two class distance distributions for a pedestrian’s face–skin reflectance sample. The probability of the POI class distribution, denoted by the solid curve, is seen on the left while the probability density function of the non-POI class distribution, denoted by the dashed curve, is seen on the right. The SNR level for these two distributions was 8.

Fig. 9.
Fig. 9.

POI and non-POI class distributions for a pedestrian’s torso subregion pixels.

Fig. 10.
Fig. 10.

Plot of the probability of error for the POI class versus SNR for each of the subregions. Note that fairly low probabilities of error were achieved with relatively low SNR, but in typical imagery there are very few pixels on each subregion.

Fig. 11.
Fig. 11.

Plot of the probability of error for the POI class versus SNR when two of the considered subregions are combined.

Fig. 12.
Fig. 12.

Plot of the probability of error for the POI class versus SNR when three of the considered subregions are combined.

Fig. 13.
Fig. 13.

Plot of the probability of error for the POI class versus SNR when all four of the considered subregions are combined.

Tables (3)

Tables Icon

Table 1. Summary Table of P ( error | ω POI ) for Pedestrian Subregion Spectral–Reflectance Combinations at SNR = 5

Tables Icon

Table 2. Summary Table of the Subregion Probability of Error for Subregions in Image A

Tables Icon

Table 3. Summary Table of the Subregion Probability of Error When Using Spectral Information from Image A to Classify POI Subregions from Image B

Equations (3)

Equations on this page are rendered with MathJax. Learn more.

x ˜ = x⃗ + x⃗ SNR * ( 0 , 1 ) ,
d e ( x⃗ , y⃗ ) = 1 p i = 1 p ( x i y i ) 2 ,
x⃗ a , b = [ x⃗ a x⃗ b ] ,

Metrics