On the semantics of similarity in deep trajectory representations

Aus SDQ-Institutsseminar
Vortragende(r) Zdravko Marinov
Vortragstyp Proposal
Betreuer(in) Saeed Taghizadeh
Termin Fr 31. Mai 2019
Vortragsmodus
Kurzfassung There are many approaches to compute the similarity between two trajectories. In 2018 a novel approach using deep learning had been introduced, which has several advantages against the classical models like Dynamic time warping, Edit distance with real penalty etc. In this thesis, the influence of the parameters of the deep learning approach on the similarity values are investigated. The similarity values are further compared between the novel and the classical models, and in the end the quality of the similarity computation is evaluated via trajectory clustering techniques and finding popular routes in cities.