Deep learning based fence segmentation and removal from an image using a video sequence

09/25/2016
by   Sankaraganesh Jonna, et al.
0

Conventional approaches to image de-fencing use multiple adjacent frames for segmentation of fences in the reference image and are limited to restoring images of static scenes only. In this paper, we propose a de-fencing algorithm for images of dynamic scenes using an occlusion-aware optical flow method. We divide the problem of image de-fencing into the tasks of automated fence segmentation from a single image, motion estimation under known occlusions and fusion of data from multiple frames of a captured video of the scene. Specifically, we use a pre-trained convolutional neural network to segment fence pixels from a single image. The knowledge of spatial locations of fences is used to subsequently estimate optical flow in the occluded frames of the video for the final data fusion step. We cast the fence removal problem in an optimization framework by modeling the formation of the degraded observations. The inverse problem is solved using fast iterative shrinkage thresholding algorithm (FISTA). Experimental results show the effectiveness of proposed algorithm.

READ FULL TEXT

page 2

page 5

page 6

page 11

page 12

page 13

page 14

research
12/10/2016

Towards an Automated Image De-fencing Algorithm Using Sparsity

Conventional approaches to image de-fencing suffer from non-robust fence...
research
04/02/2020

Learning to See Through Obstructions

We present a learning-based approach for removing unwanted obstructions,...
research
12/05/2016

Stereo image de-fencing using smartphones

Conventional approaches to image de-fencing have limited themselves to u...
research
07/06/2023

Reference-based Motion Blur Removal: Learning to Utilize Sharpness in the Reference Image

Despite the recent advancement in the study of removing motion blur in a...
research
03/28/2018

Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework

Rain removal is important for improving the robustness of outdoor vision...
research
05/18/2018

My camera can see through fences: A deep learning approach for image de-fencing

In recent times, the availability of inexpensive image capturing devices...
research
02/22/2021

Deep Learning for Robust Motion Segmentation with Non-Static Cameras

This work proposes a new end-to-end DCNN based approach for motion segme...

Please sign up or login with your details

Forgot password? Click here to reset