Video Instance Segmentation with Recurrent Graph Neural Networks

Johnander, Joakim,1993-Linköpings universitet,Datorseende,Tekniska fakulteten,Zenseact, Gothenburg, Sweden (författare)

Video instance segmentation is one of the core problems in computer vision. Formulating a purely learning-based method, which models the generic track management required to solve the video instance segmentation task, is a highly challenging problem. In this work, we propose a novel learning framework where the entire video instance segmentation problem is modeled jointly. To this end, we design a graph neural network that in each frame jointly processes all detections and a memory of previously seen tracks. Past information is considered and processed via a recurrent connection. We demonstrate the effectiveness of the proposed approach in comprehensive experiments. Our approach, operating at over 25 FPS, outperforms previous video real-time methods. We further conduct detailed ablative experiments that validate the different aspects of our approach.

Brissman, EmilLinköpings universitet,Datorseende,Tekniska fakulteten,Saab, Linköping, Sweden(Swepub:liu)emibr12 (författare)
Danelljan, Martin,1989-Computer Vision Lab, ETH Zürich, Zürich, Switzerland(Swepub:liu)marda26 (författare)
Felsberg, Michael,1974-Linköpings universitet,Datorseende,Tekniska fakulteten,School of Engineering, University of KwaZulu-Natal, Durban, South Africa(Swepub:liu)micfe03 (författare)
Linköpings universitetDatorseende (creator_code:org_t)

Ingår i:Pattern RecognitionCham : Springer, s. 206-22197830309265889783030926595

Av författaren/redakt...: Johnander, Joaki ...; Brissman, Emil; Danelljan, Marti ...; Felsberg, Michae ...

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datorseende och ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.