Moving objects have special importance for Autonomous Driving tasks. Detecting moving objects can be posed as Moving Object Segmentation, by segmenting the object pixels, or Moving Object Detection, by generating a bounding box for the moving targets. In this paper, we present a Multi-Task Learning architecture, based on Transformers, to jointly perform both tasks through one network. Due to the importance of the motion features to the task, the whole setup is based on a Spatio-Temporal aggregation. We evaluate the performance of the individual tasks architecture versus the MTL setup, both with early shared encoders, and late shared encoder-decoder transformers. For the latter, we present a novel joint tasks query decoder transformer, that enables us to have tasks dedicated heads out of the shared model. To evaluate our approach, we use the KITTI MOD [23] data set. Results show 1.5% mAP improvement for Moving Object Detection, and 2% IoU improvement for Moving Object Segmentation, over the individual tasks networks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Spatio-Temporal Multi-Task Learning Transformer for Joint Moving Object Detection and Segmentation


    Contributors:


    Publication date :

    2021-09-19


    Size :

    462410 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    A Spatio-Temporal Video Analysis System for Object Segmentation

    Xia, J. / Wang, Y. / IEEE | British Library Conference Proceedings | 2003



    Tracking moving objects as spatio-temporal boundary detection

    Mitiche, A. / Feghali, R. / Mansouri, A. | IEEE | 2002


    Tracking Moving Objects as Spatio-Temporal Boundary Detection

    Mitiche, A. / Feghali, R. / Mansouri, A. et al. | British Library Conference Proceedings | 2002