Since instance segmentation are popular in the field of unmanned driving, object recognition and instance segmentation in the case of high ambiguity are lacking at the present stage, this paper compares the training results of mask-RCNN algorithm under normal conditions and low visibility with fuzzy conditions. Firstly, for the dataset part, video downloaded from YouTube and be divided into pictures frame by frame by video processing software, which are used as datasets under normal conditions. Then, images are blurred by Fourier transform, which are used as training sets under low visibility conditions. After that, the dataset needs to be normalization, which is to divide the pixel value of the picture by 255 and map them to 0-1 and to improve the training speed. Then we test the data through mask-RCNN, through the tensor Flow library, and train the results on Colabortary. And this algorithm is based on Feature Pyramid Network (FPN) and ResNet101 backbone. Meanwhile there is an Area of Interest (ROI) Pool layer that processes of different sizes into a uniform size output. Through the test of these two datasets, the results show that mask-RCNN's test accuracy can reach more than 99% under normal visibility, and the error rate is extremely low.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Robustness of Mask-RCNN at High Ambiguous Environments


    Contributors:
    Lu, Yunrong (author)


    Publication date :

    2022-10-12


    Size :

    1405916 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Lane Tracking with Deep Learning: Mask RCNN and Faster RCNN

    Ortatas, Fatma Nur / Cetin, Emrah | IEEE | 2022


    Enhanced Mask-RCNN for Ship Detection and Segmentation

    Rakhi, Anusree Mondal / Dhorajiya, Arya P. / Saranya, P. | Springer Verlag | 2022



    TARGET RECOGNITION METHOD AND DEVICE BASED ON MASK RCNN NETWORK MODEL

    SONG XIUFENG | European Patent Office | 2022

    Free access