Detection of moving objects is a very important task in autonomous driving systems. After the perception phase, motion planning is typically performed in Bird's Eye View (BEV) space. This would require projection of objects detected on the image plane to top view BEV plane. Such a projection is prone to errors due to lack of depth information and noisy mapping in far away areas. CNNs can leverage the global context in the scene to project better. In this work, we explore end-to-end Moving Object Detection (MOD) on the BEV map directly using monocular images as input. To the best of our knowledge, such a dataset does not exist and we create an extended KITTI - raw dataset consisting of 12.9k images with annotations of moving object masks in BEV space for five classes. The dataset is intended to be used for class agnostic motion cue based object detection and classes are provided as meta-data for better tuning. We design and implement a two-stream RGB and optical flow fusion architecture which outputs motion segmentation directly in BEV space. We compare it with inverse perspective mapping of state-of-the-art motion segmentation predictions on the image plane. We observe a significant improvement of 13 % in mIoU using the simple baseline implementation. This demonstrates the ability to directly learn motion segmentation output in BEV space. Qualitative results of our baseline and the dataset annotations can be found in https://sites.google.com/view/bev-modnet.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    BEV-MODNet: Monocular Camera based Bird's Eye View Moving Object Detection for Autonomous Driving


    Beteiligte:
    Rashed, Hazem (Autor:in) / Essam, Mariam (Autor:in) / Mohamed, Maha (Autor:in) / Ei Sallab, Ahmad (Autor:in) / Yogamani, Senthil (Autor:in)


    Erscheinungsdatum :

    19.09.2021


    Format / Umfang :

    888719 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    VM-MODNet: Vehicle Motion aware Moving Object Detection for Autonomous Driving

    Rashed, Hazem / Sallab, Ahmad El / Yogamani, Senthil | IEEE | 2021


    Autonomous driving: a bird's eye view

    Martínez‐Díaz, Margarita / Soriguera, Francesc / Pérez, Ignacio | Wiley | 2019

    Freier Zugriff

    Autonomous driving: a bird's eye view

    Martínez Díaz, Margarita / Soriguera Martí, Francesc / Pérez Pérez, Ignacio | BASE | 2019

    Freier Zugriff

    Autonomous driving: a bird's eye view

    Martínez-Díaz, Margarita / Soriguera, Francesc / Pérez, Ignacio | IET | 2018

    Freier Zugriff

    BEVDetNet: Bird's Eye View LiDAR Point Cloud based Real-time 3D Object Detection for Autonomous Driving

    Mohapatra, Sambit / Yogamani, Senthil / Gotzig, Heinrich et al. | IEEE | 2021