Object detection in still images has drawn a lot of attention over past few years, and with the advent of Deep Learning impressive performances have been achieved with numerous industrial applications. Most of these deep learning models rely on RGB images to localize and identify objects in the image. However in some application scenarii, images are compressed either for storage savings or fast transmission. Therefore a time consuming image decompression step is compulsory in order to apply the aforementioned deep models. To alleviate this drawback, we propose a fast deep architecture for object detection in JPEG images, one of the most widespread compression format. We train a neural network to detect objects based on the blockwise DCT (discrete cosine transform) coefficients issued from the JPEG compression algorithm. We modify the well-known Single Shot multibox Detector (SSD) by replacing its first layers with one convolutional layer dedicated to process the DCT inputs. Experimental evaluations on PASCAL VOC and industrial dataset comprising images of road traffic surveillance show that the model is about 2× faster than regular SSD with promising detection performances. To the best of our knowledge, this paper is the first to address detection in compressed JPEG images.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Fast object detection in compressed JPEG Images


    Contributors:


    Publication date :

    2019-10-01


    Size :

    991961 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fast segmentation of the JPEG compressed documents

    De Queiroz, R. L. / Eschbach, R. | British Library Online Contents | 1998


    Retrieving digital images from a JPEG compressed image database

    Chang, C. C. / Chuang, J. C. / Hu, Y. S. | British Library Online Contents | 2004


    Recognition of JPEG compressed face images based on statistical methods

    Eickeler, S. / Muller, S. / Rigoll, G. | British Library Online Contents | 2000



    Feature Extraction from Hyperspectral Images Compressed Using the JPEG-2000 Standard

    Pal, M. D. / Brislawn, C. M. / Brumby, S. P. et al. | British Library Conference Proceedings | 2002