paper-with-me

Papers

Illumination-Based Data Augmentation for Robust Background Subtraction

2019-10-18 · Dimitrios Sakkos, Hubert P. H. Shum, Edmond S. L. Ho

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly, but also features semantic transformations of illumination which enhance the generalisation of the model. It successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask that is randomly generated. Such data allows us to effectively train an illumination-invariant deep learning model for BGS. Experimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place. The source code of the project is made publicly available at https://github.com/dksakkos/illumination_augmentation.

📄 PDF Abstract BibTeX arXiv:1910.08470

Code (1)

dksakkos/illumination_augmentation

Tasks

Data AugmentationForeground SegmentationVideo Background SubtractionVideo Object Segmentation

Similar Papers 제목 키워드 기반

BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos

2019-07-26 · M. Ozan Tezcan, Prakash Ishwar, Janusz Konrad

Background subtraction is a basic task in computer vision and video processing often applied as a pre-processing step for object tracking, people recognition, etc. Recently, a number of successful background-subtraction …

Data AugmentationObject TrackingSemantic Segmentation

BSUV-Net: A Fully-Convolutional Neural Network forBackground Subtraction of Unseen Videos

2020-01-14 · ICCV 2020 1 · M. Ozan Tezcan, Prakash Ishwar, Janusz Konrad

Background subtraction is a basic task in computer vision and video processing often applied as a pre-processing step for object tracking, people recognition, etc. Recently, a number of successful background-subtraction …

Data AugmentationObject Tracking

Spatio-temporal Data Augmentation for Visual Surveillance

2021-01-25 · Jae-Yeul Kim, Jong-Eun Ha

Visual surveillance aims to stably detect a foreground object using a continuous image acquired from a fixed camera. Recent deep learning methods based on supervised learning show superior performance compared to classic…

Data AugmentationDeep Learningimage-classificationImage Classification+2

Combining Background Subtraction Algorithms with Convolutional Neural Network

2018-07-05 · Dongdong Zeng, Ming Zhu, Arjan Kuijper

Accurate and fast extraction of foreground object is a key prerequisite for a wide range of computer vision applications such as object tracking and recognition. Thus, enormous background subtraction methods for foregrou…

DecoderObjectobject-detectionObject Detection+1

Complex Background Subtraction by Pursuing Dynamic Spatio-Temporal Models

2015-02-02 · Liang Lin, Yuanlu Xu, Xiaodan Liang, Jian-Huang Lai

Although it has been widely discussed in video surveillance, background subtraction is still an open problem in the context of complex scenarios, e.g., dynamic backgrounds, illumination variations, and indistinct foregro…