Thermal spatio-temporal data for stress recognition

Nandita Sharma, Abhinav DHALL, Tamas Gedeon, Roland GOECKE

    Research output: Contribution to journalArticle

    8 Citations (Scopus)
    2 Downloads (Pure)

    Abstract

    Stress is a serious concern facing our world today, motivating the development of a better objective understanding through the use of non-intrusive means for stress recognition by reducing restrictions to natural human behavior. As an initial step in computer vision-based stress detection, this paper proposes a temporal thermal spectrum (TS) and visible spectrum (VS) video database ANUStressDB - a major contribution to stress research. The database contains videos of 35 subjects watching stressed and not-stressed film clips validated by the subjects. We present the experiment and the process conducted to acquire videos of subjects' faces while they watched the films for the ANUStressDB. Further, a baseline model based on computing local binary patterns on three orthogonal planes (LBP-TOP) descriptor on VS and TS videos for stress detection is presented. A LBP-TOP-inspired descriptor was used to capture dynamic thermal patterns in histograms (HDTP) which exploited spatio-temporal characteristics in TS videos. Support vector machines were used for our stress detection model. A genetic algorithm was used to select salient facial block divisions for stress classification and to determine whether certain regions of the face of subjects showed better stress patterns. Results showed that a fusion of facial patterns from VS and TS videos produced statistically significantly better stress recognition rates than patterns from VS or TS videos used in isolation. Moreover, the genetic algorithm selection method led to statistically significantly better stress detection rates than classifiers that used all the facial block divisions. In addition, the best stress recognition rate was obtained from HDTP features fused with LBP-TOP features for TS and VS videos using a hybrid of a genetic algorithm and a support vector machine stress detection model. The model produced an accuracy of 86%.
    Original languageEnglish
    Pages (from-to)1-7
    Number of pages7
    JournalEurasip Journal on Image and Video Processing
    Volume28
    DOIs
    Publication statusPublished - 2014

    Fingerprint

    Genetic algorithms
    Support vector machines
    Hot Temperature
    Computer vision
    Classifiers
    Fusion reactions
    Experiments

    Cite this

    Sharma, Nandita ; DHALL, Abhinav ; Gedeon, Tamas ; GOECKE, Roland. / Thermal spatio-temporal data for stress recognition. In: Eurasip Journal on Image and Video Processing. 2014 ; Vol. 28. pp. 1-7.
    @article{b8ba26fdd7fe4643895d4241a61dd831,
    title = "Thermal spatio-temporal data for stress recognition",
    abstract = "Stress is a serious concern facing our world today, motivating the development of a better objective understanding through the use of non-intrusive means for stress recognition by reducing restrictions to natural human behavior. As an initial step in computer vision-based stress detection, this paper proposes a temporal thermal spectrum (TS) and visible spectrum (VS) video database ANUStressDB - a major contribution to stress research. The database contains videos of 35 subjects watching stressed and not-stressed film clips validated by the subjects. We present the experiment and the process conducted to acquire videos of subjects' faces while they watched the films for the ANUStressDB. Further, a baseline model based on computing local binary patterns on three orthogonal planes (LBP-TOP) descriptor on VS and TS videos for stress detection is presented. A LBP-TOP-inspired descriptor was used to capture dynamic thermal patterns in histograms (HDTP) which exploited spatio-temporal characteristics in TS videos. Support vector machines were used for our stress detection model. A genetic algorithm was used to select salient facial block divisions for stress classification and to determine whether certain regions of the face of subjects showed better stress patterns. Results showed that a fusion of facial patterns from VS and TS videos produced statistically significantly better stress recognition rates than patterns from VS or TS videos used in isolation. Moreover, the genetic algorithm selection method led to statistically significantly better stress detection rates than classifiers that used all the facial block divisions. In addition, the best stress recognition rate was obtained from HDTP features fused with LBP-TOP features for TS and VS videos using a hybrid of a genetic algorithm and a support vector machine stress detection model. The model produced an accuracy of 86{\%}.",
    keywords = "stress recognition, thermal images, spatio-temporal data",
    author = "Nandita Sharma and Abhinav DHALL and Tamas Gedeon and Roland GOECKE",
    year = "2014",
    doi = "10.1186/1687-5281-2014-28",
    language = "English",
    volume = "28",
    pages = "1--7",
    journal = "Eurasip Journal on Image and Video Processing",
    issn = "1687-5176",
    publisher = "Springer Publishing Company",

    }

    Thermal spatio-temporal data for stress recognition. / Sharma, Nandita; DHALL, Abhinav; Gedeon, Tamas; GOECKE, Roland.

    In: Eurasip Journal on Image and Video Processing, Vol. 28, 2014, p. 1-7.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Thermal spatio-temporal data for stress recognition

    AU - Sharma, Nandita

    AU - DHALL, Abhinav

    AU - Gedeon, Tamas

    AU - GOECKE, Roland

    PY - 2014

    Y1 - 2014

    N2 - Stress is a serious concern facing our world today, motivating the development of a better objective understanding through the use of non-intrusive means for stress recognition by reducing restrictions to natural human behavior. As an initial step in computer vision-based stress detection, this paper proposes a temporal thermal spectrum (TS) and visible spectrum (VS) video database ANUStressDB - a major contribution to stress research. The database contains videos of 35 subjects watching stressed and not-stressed film clips validated by the subjects. We present the experiment and the process conducted to acquire videos of subjects' faces while they watched the films for the ANUStressDB. Further, a baseline model based on computing local binary patterns on three orthogonal planes (LBP-TOP) descriptor on VS and TS videos for stress detection is presented. A LBP-TOP-inspired descriptor was used to capture dynamic thermal patterns in histograms (HDTP) which exploited spatio-temporal characteristics in TS videos. Support vector machines were used for our stress detection model. A genetic algorithm was used to select salient facial block divisions for stress classification and to determine whether certain regions of the face of subjects showed better stress patterns. Results showed that a fusion of facial patterns from VS and TS videos produced statistically significantly better stress recognition rates than patterns from VS or TS videos used in isolation. Moreover, the genetic algorithm selection method led to statistically significantly better stress detection rates than classifiers that used all the facial block divisions. In addition, the best stress recognition rate was obtained from HDTP features fused with LBP-TOP features for TS and VS videos using a hybrid of a genetic algorithm and a support vector machine stress detection model. The model produced an accuracy of 86%.

    AB - Stress is a serious concern facing our world today, motivating the development of a better objective understanding through the use of non-intrusive means for stress recognition by reducing restrictions to natural human behavior. As an initial step in computer vision-based stress detection, this paper proposes a temporal thermal spectrum (TS) and visible spectrum (VS) video database ANUStressDB - a major contribution to stress research. The database contains videos of 35 subjects watching stressed and not-stressed film clips validated by the subjects. We present the experiment and the process conducted to acquire videos of subjects' faces while they watched the films for the ANUStressDB. Further, a baseline model based on computing local binary patterns on three orthogonal planes (LBP-TOP) descriptor on VS and TS videos for stress detection is presented. A LBP-TOP-inspired descriptor was used to capture dynamic thermal patterns in histograms (HDTP) which exploited spatio-temporal characteristics in TS videos. Support vector machines were used for our stress detection model. A genetic algorithm was used to select salient facial block divisions for stress classification and to determine whether certain regions of the face of subjects showed better stress patterns. Results showed that a fusion of facial patterns from VS and TS videos produced statistically significantly better stress recognition rates than patterns from VS or TS videos used in isolation. Moreover, the genetic algorithm selection method led to statistically significantly better stress detection rates than classifiers that used all the facial block divisions. In addition, the best stress recognition rate was obtained from HDTP features fused with LBP-TOP features for TS and VS videos using a hybrid of a genetic algorithm and a support vector machine stress detection model. The model produced an accuracy of 86%.

    KW - stress recognition

    KW - thermal images

    KW - spatio-temporal data

    U2 - 10.1186/1687-5281-2014-28

    DO - 10.1186/1687-5281-2014-28

    M3 - Article

    VL - 28

    SP - 1

    EP - 7

    JO - Eurasip Journal on Image and Video Processing

    JF - Eurasip Journal on Image and Video Processing

    SN - 1687-5176

    ER -