Detection of sitting posture using hierarchical image composition and deep learning

Machine learning and deep learning has shown very good results when applied to various computer vision applications such as detection of plant diseases in agriculture (Kamilaris & Prenafeta-Boldú, 2018), fault diagnosis in industrial engineering (Wen et al., 2018), brain tumor recognition from MR images (Chen et al., 2018a), segmentation of endoscopic images for gastric cancer (Hirasawa et al., 2018), or skin lesion recognition (Li & Shen, 2018) and even autonomous vehicles (Alam et al., 2019). As our daily life increasingly depends on sitting work and the opportunities for physical exercising (in the context of COVID-19 pandemic associated restrictions and lockdowns are diminished), many people are facing various medical conditions directly related to such sedentary lifestyles. One of the frequently mentioned problems is back pain, with bad sitting posture being one of the compounding factors to this problem (Grandjean & Hünting, 1977; Sharma & Majumdar, 2009). Inadequate postures adopted by office workers are one of the most significant risk factors of work-related musculoskeletal disorders. The direct consequence may be back pain, while indirectly it has been associated with cervical disease, myopia, cardiovascular diseases and premature mortality (Cagnie et al., 2006).