Show simple item record

Authormaadeed, Somaya
AuthorAlMaadeed, Noor
Authorelharrouss, omar
Available date2020-10-25T08:10:18Z
Publication Date2020
Publication NameQatar University Annual Research Forum & Exhibition 2020
Citationmaadeed S., AlMaadeed N., elharrouss o., "Face recognition and summarization for surveillance video sequences", Qatar University Annual Research Forum and Exhibition (QUARFE 2020), Doha, 2020, https://doi.org/10.29117/quarfe.2020.0235
URIhttps://doi.org/10.29117/quarfe.2020.0235
URIhttp://hdl.handle.net/10576/16649
AbstractFace recognition and video summarization represent chal- lenging tasks for several computer vision applications including video surveil- lance, criminal investigations, and sports applications'. For long videos, it is difficult to search within a video for a specific action and/or person. Usually, human action recognition approaches presented in the literature deal with videos that contain only a single person, and they are able to recognize his action. This paper proposes an effective approach to multiple human action detection, recognition, and summarization. The multiple action detection ex- tracts human bodies' silhouette then generates a specific sequence for each one of them using motion detection and tracking method. Each of the extracted sequences is then divided into shots that represent homogeneous actions in the sequence using the similarity between each pair frames. Using the histogram of the oriented gradient (HOG) of the Temporal Difference Map (TDMap) of the frames of each shot, we recognize the action by performing a comparison be- tween the generated HOG and the existed HOGs in the training phase which represents all the HOGs of many actions using a set of videos for training
Languageen
PublisherQatar University Press
SubjectFace recognition
SubjectDeep learning
SubjectAction recognition.
TitleFace recognition and summarization for surveillance video sequences
TypePoster


Files in this item

Icon

This item appears in the following Collection(s)

Show simple item record