Highly accurate, camera-based object detection is an essential component of autonomous navigation and assistive technologies. In particular, for on-road applications, localization quality of objects in the image plane is important for accurate distance estimation, safe trajectory prediction, and motion planning. In this paper, we mathematically formulate and study a strategy for improving object localization with a deep convolutional neural network. An iterative region-of-interest pooling framework is proposed for predicting increasingly tight object boxes and addressing limitations in current state-of-the-art deep detection models. The method is shown to significantly improve the performance on a variety of datasets, scene settings, and camera perspectives, producing high-quality object boxes at a minor additional computational expense. Specifically, the architecture achieves impressive gains in performance (up to 6% improvement in detection accuracy) at fast run-time speed (0.22 s per frame on $1242 \times 375$ sized images). The iterative refinement is shown to impact subsequent vision tasks, such as object tracking in the image plane and in ground plane.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    RefineNet: Refining Object Detectors for Autonomous Driving



    Published in:

    Publication date :

    2016-12-01


    Size :

    1180744 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    RefineNet: Iterative refinement for accurate object localization

    Rajaram, Rakesh N. / Ohn-Bar, Eshed / Trivedi, Mohan M. | IEEE | 2016


    Robustness and Deployability of Deep Object Detectors in Autonomous Driving

    Adam, Ganesh / Chitalia, Vibhav / Simha, Namrata et al. | IEEE | 2019



    USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving

    Liao, Brian Hsuan-Cheng / Cheng, Chih-Hong / Esen, Hasan et al. | IEEE | 2024


    Autonomous Driving Object Detection Platform

    Carabulea, Laurentiu / Pozna, Claudiu / Antonya, Csaba et al. | Springer Verlag | 2024