In this paper, we describe a new approach for synthetic image augmentation and its advantages in training Deep Neural Networks (DNNs) for object classification and localization. To address the need for a significant amount of data when training DNNs, for image-based ADAS functions, our method relies on virtually generated scenarios augmented via a physics-based camera model. The camera model implements various optical effects on ideal-synthetic images. For the scope of this paper, we illustrate the performance differences associated with the vignetting effect when training DNNs with and without image augmentation. We show that training on images altered by our camera vignetting model yield to a better performance than using ideal-synthetic images, additionally we illustrate the relationship between the network's performance results and the implemented effect (vignetting in this case). For a start, our results open the possibility for using camera models for training neural networks on synthetic data and pave the way toward further investigations on significant optical and image sensor effects to be modeled/implemented for performance enhancement during the training process. The approach is conducted and evaluated by training a DNN for car detection using the Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI) and Virtual KITTI (VKITTI) datasets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Camera Vignetting Model and its Effects on Deep Neural Networks for Object Detection


    Contributors:


    Publication date :

    2019-11-01


    Size :

    676059 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    On Cosine-Fourth and Vignetting Effects in Real Lenses

    Aggarwal, M. / Hua, H. / Ahuja, N. et al. | British Library Conference Proceedings | 2001


    On cosine-fourth and vignetting effects in real lenses

    Aggarwal, M. / Hua, H. / Ahuja, N. | IEEE | 2001


    Traffic Congestion Detection from Camera Images using Deep Convolution Neural Networks

    Chakraborty, Pranamesh / Adu-Gyamfi, Yaw Okyere / Poddar, Subhadipto et al. | Transportation Research Record | 2018



    QE reduction due to pixel vignetting in CMOS image sensors [3965-50]

    Catrysse, P. B. / Liu, X. / El Gamal, A. et al. | British Library Conference Proceedings | 2000