Counting in the wild

Carlos Arteta, Victor Lempitsky, Andrew Zisserman

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    118 Citations (Scopus)

    Abstract

    In this paper we explore the scenario of learning to count multiple instances of objects from images that have been dot-annotated through crowdsourcing. Specifically, we work with a large and challenging image dataset of penguins in the wild, for which tens of thousands of volunteer annotators have placed dots on instances of penguins in tens of thousands of images. The dataset, introduced and released with this paper, shows such a high-degree of object occlusion and scale variation that individual object detection or simple counting-density estimation is not able to estimate the bird counts reliably. To address the challenging counting task, we augment and interleave density estimation with foreground-background segmentation and explicit local uncertainty estimation. The three tasks are solved jointly by a new deep multi-task architecture. Using this multi-task learning, we show that the spread between the annotators can provide hints about local object scale and aid the foreground-background segmentation, which can then be used to set a better target density for learning density prediction. Considerable improvements in counting accuracy over a single-task density estimation approach are observed in our experiments.

    Original languageEnglish
    Title of host publicationComputer Vision - 14th European Conference, ECCV 2016, Proceedings
    EditorsMax Welling, Nicu Sebe, Jiri Matas, Bastian Leibe
    PublisherSpringer Verlag
    Pages483-498
    Number of pages16
    Volume9911
    ISBN (Print)9783319464770
    DOIs
    Publication statusPublished - 2016

    Publication series

    NameLecture Notes in Computer Science

    Fingerprint

    Dive into the research topics of 'Counting in the wild'. Together they form a unique fingerprint.

    Cite this