Data-driven street scene layout estimation for distant object detection

Donghao Zhang, Xuming He, Hanxi Li

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

    7 Citations (Scopus)

    Abstract

    We present a street scene layout estimation method based on transferring layout annotation from a (large) image database and its application for distant object detection. Inspired by nonparametric scene labeling approaches, we estimate a scene's geometric layout by matching global image descriptors and retrieving the most similar layout configuration. Our label transfer is done for each sub-region of an image and a tiered scene model is used to integrate all the local label information into a coherent scene layout prediction. Given the geometric layout, we use a super-resolution method to zoom in the distance region and refine the search in object detection. On KITTI dataset, we show that we can reliably generate scene layout and improve the detection of distant cars over the state of the art DPM detector.

    Original languageEnglish
    Title of host publication2014 International Conference on Digital Image Computing
    Subtitle of host publicationTechniques and Applications, DICTA 2014
    EditorsAbdesselam Bouzerdoum, Lei Wang, Philip Ogunbona, Wanqing Li, Son Lam Phung
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    ISBN (Electronic)9781479954094
    DOIs
    Publication statusPublished - 12 Jan 2015
    Event2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014 - Wollongong, Australia
    Duration: 25 Nov 201427 Nov 2014

    Publication series

    Name2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014

    Conference

    Conference2014 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2014
    Country/TerritoryAustralia
    CityWollongong
    Period25/11/1427/11/14

    Fingerprint

    Dive into the research topics of 'Data-driven street scene layout estimation for distant object detection'. Together they form a unique fingerprint.

    Cite this