Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Context Sensitivity of Spatio-Temporal Activity Detection using Hierarchical Deep Neural Networks in Extended Videos

: Hertlein, Felix; Münch, David; Arens, Michael

Volltext urn:nbn:de:0011-n-5930782 (956 KByte PDF)
MD5 Fingerprint: cd1bb9a99b6cad42e19fe157e322faf8
Erstellt am: 16.6.2020

Institute of Electrical and Electronics Engineers -IEEE-:
IEEE Winter Conference on Applications of Computer Vision Workshops, WACVW 2020. Proceedings : March 1-5, 2020, Snowmass Village, Colorado
Piscataway, NJ: IEEE, 2020
ISBN: 978-1-7281-7162-3
ISBN: 978-1-7281-7163-0
Winter Conference on Computer Vision and Applications (WACV) <2020, Snowmass Village/Colo.>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

The amount of available surveillance video data is increasing rapidly and therefore makes manual inspection impractical. The goal of activity detection is to automatically localize activities spatially and temporally in a large collection of video data. In this work we will answer the question to what extent context plays a role in spatio-temporal activity detection in extended videos. Towards this end we propose a hierarchical pipeline for activity detection which spatially localizes objects first and subsequently generates spatial-temporal action tubes. Additionally, a suitable metric for performance evaluation is enhanced. Thus, we evaluate our system using the TRECVID 2019 ActEV challenge dataset. We investigated the sensitivity by detecting activities multiple times with various spatial margins around the performing actor. The results showed that our pipeline and metric is suited for detecting activities in extended videos.