There is an increasing interest in exploiting multiple images for scene understanding, with great progress in areas such as cosegmentation and video segmentation. Jointly analyzing the images in a large set offers the opportunity to exploit a greater source of information than when considering a single image on its own. However, this also yields challenges since, to effectively exploit all the available information, the resulting methods need to consider not just local connections, but efficiently analyze similarity between all pairs of pixels within and across all the images. In this paper, we propose to model an image set as a fully connected pairwise Conditional Random Field (CRF) defined over the image pixels, or superpixels, with Gaussian edge potentials. We show that this lets us co-label the images of a large set efficiently, thus yielding increased accuracy at no additional computational cost compared to sequential labeling of the images. Furthermore, we extend our framework to incorporate temporal dependence, thus effectively encompassing video segmentation as a special case of our approach, as well as to modeling label dependence over larger image regions. Our experimental evaluation demonstrates that our framework lets us handle over 10 000 images in a matter of seconds.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Exploiting Large Image Sets for Road Scene Parsing




    Publication date :

    2016




    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English



    Classification :

    BKL:    55.84 / 55.24 / 55.84 Straßenverkehr / 55.24 Fahrzeugführung, Fahrtechnik



    Exploiting Large Image Sets for Road Scene Parsing

    Alvarez, Jose M. / Salzmann, Mathieu / Barnes, Nick | IEEE | 2016


    Spatial Prior for Nonparametric Road Scene Parsing

    Di, Shuai / Zhang, Honggang / Mei, Xue et al. | IEEE | 2015


    Nighttime Road Scene Parsing by Unsupervised Domain Adaptation

    Song, Can / Wu, Jin / Zhu, Lei et al. | IEEE | 2022



    Pyramid Scene Parsing Network for Driver Distraction Classification

    Khadraoui, Abdelhak / Zemmouri, Elmoukhtar | Springer Verlag | 2024