An assessment of a 360-degree profiling sensor for object classification

Brown, Jeremy B.; Chari, Srikant; Jacobs, Eddie L.

doi:10.1117/12.884219

Cited by 3 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 360° profiling sensor is a non-sparse detector that uses a long wave infrared camera focused on a conical mirror to achieve a 360° field of view [28]. The conic mirror provides continuous field of view coverage in the horizontal regions but its size and shape constrains coverage in the vertical direction, though the cones are interchangeable.…”

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

“…Figure 18 shows how the projection angles α and β can be calculated by using Equations (11) and (12), where FOV m is the minimum field of view of the camera covered by the concentric conic mirror [28]. Equation (13) computes the internal angle of the cone base, ϕ , where h c and r b are the height of the cone and the radius of the base of the cone, respectively.…”

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

“…However, different designs may distort the image further, thus making the segmentation, feature extraction, and classification algorithms less successful. Figure 19 shows the 360° profiling sensor model designed and built in the laboratory at the University of Memphis [28]. …”

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

“…For an object present in the field of view of the 360° profiling sensor, several sample frames are taken and statistical analysis is used to separate the targeted object from its background. Brown et al [28] explain the different statistical methods used to separate the image into the segment of interest in addition to feature extraction and classification methods.…”

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

See 3 more Smart Citations

Advancing Profiling Sensors with a Wireless Approach

Galvis

Russomanno

2012

Sensors

View full text Add to dashboard Cite

The notion of a profiling sensor was first realized by a Near-Infrared (N-IR) retro-reflective prototype consisting of a vertical column of wired sparse detectors. This paper extends that prior work and presents a wireless version of a profiling sensor as a collection of sensor nodes. The sensor incorporates wireless sensing elements, a distributed data collection and aggregation scheme, and an enhanced classification technique. In this novel approach, a base station pre-processes the data collected from the sensor nodes and performs data re-alignment. A back-propagation neural network was also developed for the wireless version of the N-IR profiling sensor that classifies objects into the broad categories of human, animal or vehicle with an accuracy of approximately 94%. These enhancements improve deployment options as compared with the first generation of wired profiling sensors, possibly increasing the application scenarios for such sensors, including intelligent fence applications.

show abstract

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

Section: Alternative Profiling Sensor Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Advancing Profiling Sensors with a Wireless Approach

Galvis

Russomanno

2012

Sensors

View full text Add to dashboard Cite

show abstract

“…Chari et al 7 and Brown et al 8 used height-to-width ratio as a feature to classify human against animal. In general, humans have a higher height-to-width ratio than animals.…”

Section: Introductionmentioning

confidence: 99%

Real-time classification of humans versus animals using profiling sensors and hidden Markov tree model

Hossen

Jacobs

Chari³

2015

Opt. Eng

Self Cite

View full text Add to dashboard Cite

Linear pyroelectric array sensors have enabled useful classifications of objects such as humans and animals to be performed with relatively low-cost hardware in border and perimeter security applications. Ongoing research has sought to improve the performance of these sensors through signal processing algorithms. In the research presented here, we introduce the use of hidden Markov tree (HMT) models for object recognition in images generated by linear pyroelectric sensors. HMTs are trained to statistically model the wavelet features of individual objects through an expectation-maximization learning process. Human versus animal classification for a test object is made by evaluating its wavelet features against the trained HMTs using the maximum-likelihood criterion. The classification performance of this approach is compared to two other techniques; a texture, shape, and spectral component features (TSSF) based classifier and a speeded-up robust feature (SURF) classifier. The evaluation indicates that among the three techniques, the wavelet-based HMT model works well, is robust, and has improved classification performance compared to a SURF-based algorithm in equivalent computation time. When compared to the TSSF-based classifier, the HMT model has a slightly degraded performance but almost an order of magnitude improvement in computation time enabling real-time implementation. Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073102-2 July 2015 • Vol. 54(7) Hossen, Jacobs, and Chari: Real-time classification of humans versus animals. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073102-3 July 2015 • Vol. 54(7) Hossen, Jacobs, and Chari: Real-time classification of humans versus animals. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx Optical Engineering 073102-15 July 2015 • Vol. 54(7) Hossen, Jacobs, and Chari: Real-time classification of humans versus animals. . . Downloaded From: http://opticalengineering.spiedigitallibrary.org/ on 08/17/2015 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspx

show abstract