Browse/search for people

Publication - Professor Majid Mirmehdi

    Markerless Active Trunk Shape Modelling for Motion Tolerant Remote Respiratory Assessment

    Citation

    Soleimani, V, Mirmehdi, M, Damen, D & Dodd, J, 2019, ‘Markerless Active Trunk Shape Modelling for Motion Tolerant Remote Respiratory Assessment’. in: 2018 25th IEEE International Conference on Image Processing (ICIP 2018): Proceedings of a meeting held 7-10 October 2018, Athens, Greece. Institute of Electrical and Electronics Engineers (IEEE), pp. 2077-2081

    Abstract

    We present a vision-based trunk-motion tolerant approach which estimates lung volume–time data remotely in forced vital capacity (FVC) and slow vital capacity (SVC) spirometry tests. After temporal modelling of trunk shape, generated using two opposing Kinects in a sequence, the chest-surface respiratory pattern is computed by performing principal component analysis on temporal geometrical features extracted from the chest and posterior shapes. We evaluate our method on a publicly available dataset of 35 subjects (300 sequences) and compare against the state-of-the-art. By filtering complex trunk motions, our proposed method calibrates the entire volume–time data using only the tidal volume scaling factor which reduces the state-of-the-art average normalised L2 error from 0.136 to 0.05.

    Full details in the University publications repository