An object detection system may generate regions of interest (ROIs) from an input image that can be processed by a wide range of object detectors. According to the techniques described herein, an image is processed by a light-weight neural network (e.g., a heatmap network) that outputs object center and object scale heat-maps. The heatmaps are processed to define ROIs that are likely to include objects. Overlapping ROIs are then merged to reduce the aggregate size of the ROIs, and merged ROIs are downscaled to a reduced set of pre-defined resolutions. Fully-convolutional, high-accuracy object detectors may then operate on the downscaled ROIs to output accurate detections at a fraction of the computations by operating on a reduced image. For example, fully-convolutional, high-accuracy object detectors may operate on a subset of the entire image (e.g., cropped images based on ROIs) thus reducing computations otherwise performed over the entire image.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Region of interest selection for object detection


    Beteiligte:
    VITEK RAN (Autor:in) / DANA ALEXANDRA (Autor:in) / SHUTMAN MAOR (Autor:in) / SHOEF MATAN (Autor:in) / PERLITZ YOTAM (Autor:in) / PELEG TOMER (Autor:in) / STEIN NETANEL (Autor:in) / JEVNISEK ROY JOSEF (Autor:in)

    Erscheinungsdatum :

    2022-10-04


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    IPC:    G06V / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06K Erkennen von Daten , RECOGNITION OF DATA





    The region of interest extraction system for moving object

    CHOI KWANG HO / HWANG IN HO / JIN SEUNG MO et al. | Europäisches Patentamt | 2018

    Freier Zugriff

    DEVICES AND METHODS FOR DETERMINING REGION OF INTEREST FOR OBJECT DETECTION IN CAMERA IMAGES

    ALPERT BENJAMIN OREN / MAHMUD TAHMIDA BINTE / WU ALEXANDER DION et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    ARSD: An Adaptive Region Selection Object Detection Framework for UAV Images

    Yuzhuang Wan / Yi Zhong / Yan Huang et al. | DOAJ | 2022

    Freier Zugriff