Per citar aquest document:
Efficient Labelling of Pedestrian Supervisions
Htike, Kyaw Kyaw (UCSI University (Kuala Lumpur). School of Information Technology)

Data: 2016
Resum: Object detection is a fundamental goal to achieve intelligent visual perception by computers due to the fact that objects are the basic building blocks to achieve higher level image understanding. Among the numerous categories of objects in the real-world, pedestrians are among the most important due to several potential benefits brought about by successful pedestrian detection. Often, pedestrian detectors are trained in state-of-the-art systems using supervised machine learning algorithms which necessitates costly and often tedious manual annotation of pedestrians in the form of precise bounding boxes. In this paper, a novel weakly supervised learning algorithm is proposed to train a pedestrian detector that requires, instead of bounding boxes, only annotations of estimated centres of pedestrians. The algorithm makes use of a pedestrian prior learnt in an unsupervised way from the video and this prior is fused with the given weak supervision information in a systematic manner. By evaluating on publicly available datasets, we demonstrate that our weakly supervised algorithm reduces the cost of manual annotation of pedestrians by more than four times while achieving similar performance to a pedestrian detector trained with standard bounding box annotations.
Drets: Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades. Creative Commons
Llengua: Anglès.
Document: article ; recerca ; publishedVersion
Matèria: Object detection ; Pedestrian detecton ; Weakly supervised learning ; Cue fusion
Publicat a: ELCVIA : Electronic Letters on Computer Vision and Image Analysis, Vol. 15 núm. 1 (2016) , p. 77-99 (Regular Issue) , ISSN 1577-5097

Adreça original:
DOI: 10.5565/rev/elcvia.881

23 p, 1.9 MB

El registre apareix a les col·leccions:
Articles > Articles publicats > ELCVIA
Articles > Articles de recerca

 Registre creat el 2016-09-16, darrera modificació el 2017-01-26

   Favorit i Compartir