P
Prashant W. Patil
Researcher at Indian Institute of Technology Ropar
Publications - 26
Citations - 547
Prashant W. Patil is an academic researcher from Indian Institute of Technology Ropar. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 8, co-authored 20 publications receiving 194 citations. Previous affiliations of Prashant W. Patil include Deakin University.
Papers
More filters
Journal ArticleDOI
MSFgNet: A Novel Compact End-to-End Deep Network for Moving Object Detection
TL;DR: A novel compact end-to-end convolutional neural network architecture, motion saliency foreground network (MSFgNet), to estimate the background and to extract the foreground from video frames to outperforms the existing state-of-the-art methods for MOD in videos.
Journal ArticleDOI
Deep Underwater Image Restoration and Beyond
TL;DR: Experimental analysis shows that the proposed network is superior than the existing state-of-the-art approaches for underwater image restoration and validated for underwater images restoration task on real-world underwater images.
Proceedings ArticleDOI
An End-to-End Edge Aggregation Network for Moving Object Segmentation
TL;DR: Experimental results show that the proposed approach outperforms the state-of-the-art methods for MOS and does not require any pre-trained models or fine-tuning of the parameters with the initial frame of the test video.
Proceedings ArticleDOI
Varicolored Image De-Hazing
Akshay Dudhane,Kuldeep Marotirao Biradar,Prashant W. Patil,Praful Hambarde,Subrahmanyam Murala +4 more
TL;DR: Visual results on a set of real-world hazy images captured in different weather conditions demonstrate the effectiveness of the proposed approach for varicolored image de-hazing.
Proceedings ArticleDOI
FgGAN: A Cascaded Unpaired Learning for Background Estimation and Foreground Segmentation
TL;DR: From experimental results, it is evident that the proposed FgGAN shows significant improvement in terms of F-measure and PWC as compared to the existing state-of-the-art methods for MOS.