Superpixel is a local compact homogeneous region formed by adjacent pixels with similar characteristics. Compared with pixel features, replacing original pixels with superpixels can reduce the complexity of image processing algorithm. However, there are few researches on extracting superpixel features by deep neural networks. Aiming at the problem that the existing superpixel segmentation algorithm is not differentiable, which makes it unable to be integrated into the deep learning network. Based on SLIC, this paper converts the non-differentiable pixel-superpixel correlation calculation into differentiable operation, and proposes a differentiable superpixel segmentation method, which can extract superpixel features by using full convolution network. The new proposed superpixel segmentation algorithm has been tested on the BSDS 500 public dataset. The simulation results show it not only has excellent performance and higher accuracy, but also can used to learn other task-specific superpixels.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A novel improved SLIC superpixel segmentation algorithm


    Contributors:
    Chen, Zhijie (author) / Zhong, Zhaoqi (author) / Pan, Xiangyu (author) / Xi, Xin (author)


    Publication date :

    2022-10-12


    Size :

    1471285 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    The SLIC-7 laser gyro inertial guidance system

    Morrison, R.F. / Levinson, E. / Bryant, B.L. | Tema Archive | 1977


    Superpixel-Guided Multi-Type Rail Segmentation via Contextual Information Aggregation

    Ni, Xuefeng / Fieguth, Paul W. / Ma, Ziji et al. | IEEE | 2024


    Subsampling-based acceleration of simple linear iterative clustering for superpixel segmentation

    Choi, Kang-Sun / Oh, Ki-Won | British Library Online Contents | 2016