Semi-automatic Annotation of Objects in Visual-Thermal Video

Berg, Amanda, 1988- (author): Linköpings universitet,Datorseende,Tekniska fakulteten,Termisk Systemteknik AB, Linköping, Sweden

Johnander, Joakim (author): Linköpings universitet,Datorseende,Tekniska fakulteten,Zenuity AB, Göteborg, Sweden

Durand de Gevigney, Flavie (author): Linköpings universitet,Datorseende,Tekniska fakulteten,Grenoble INP, France

Ahlberg, Jörgen (author): Linköpings universitet,Datorseende,Tekniska fakulteten,Termisk Systemteknik AB, Linköping, Sweden

Felsberg, Michael (author): Linköpings universitet,Datorseende,Tekniska fakulteten

(creator_code:org_t)

Institute of Electrical and Electronics Engineers (IEEE), 2019
2019
English.
In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781728150239 - 9781728150246

Related links:: https://liu.diva-por... (primary) (Raw object); show more...; https://urn.kb.se/re...; https://doi.org/10.1...; show less...

Abstract Subject headings

Deep learning requires large amounts of annotated data. Manual annotation of objects in video is, regardless of annotation type, a tedious and time-consuming process. In particular, for scarcely used image modalities human annotationis hard to justify. In such cases, semi-automatic annotation provides an acceptable option.In this work, a recursive, semi-automatic annotation method for video is presented. The proposed method utilizesa state-of-the-art video object segmentation method to propose initial annotations for all frames in a video based on only a few manual object segmentations. In the case of a multi-modal dataset, the multi-modality is exploited to refine the proposed annotations even further. The final tentative annotations are presented to the user for manual correction.The method is evaluated on a subset of the RGBT-234 visual-thermal dataset reducing the workload for a human annotator with approximately 78% compared to full manual annotation. Utilizing the proposed pipeline, sequences are annotated for the VOT-RGBT 2019 challenge.

By the author/editor: Berg, Amanda, 19 ...; Johnander, Joaki ...; Durand de Gevign ...; Ahlberg, Jörgen; Felsberg, Michae ...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Vision ...

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.