W ramach zadania nr 4 „Rozpoznawanie wypowiedzi Polskiego Języka Migowego w układzie wizyjnym” przeprowadzono prace naukowo-badawcze, których wyniki zostały opublikowane w czasopiśmie Symmetry (obecna punktacja ministerialna to 70 pkt, Impact Factor: 2.645).
Warchoł, D.; Kapuściński, T. Human Action Recognition Using Bone Pair Descriptor and Distance Descriptor. Symmetry 2020, 12(10), 1580. https://doi.org/10.3390/sym12101580
Abstract
The paper presents a method for the recognition of human actions based on skeletal data. A novel Bone Pair Descriptor is proposed, which encodes the angular relations between pairs of bones. Its features are combined with Distance Descriptor, previously used for hand posture recognition, which describes relationships between distances of skeletal joints. Five different time series classification methods are tested. The selection of features, input joints, and bones is performed. The experiments are conducted using person-independent validation tests and a challenging, publicly available dataset of human actions. The proposed method is compared with other approaches found in the literature achieving relatively good results.
