Branding/Logomark minus Citation Combined Shape Icon/Bookmark-empty Icon/Copy Icon/Collection Icon/Close Copy 7 no author result Created with Sketch. Icon/Back Created with Sketch. Match!

DeepPBM: Deep Probabilistic Background Model Estimation from Video Sequences.

Amirreza Farnoosh1
Estimated H-index: 1
(NU: Northeastern University),
Behnaz Rezaei1
Estimated H-index: 1
(NU: Northeastern University),
Sarah Ostadabbas10
Estimated H-index: 10
(NU: Northeastern University)
Abstract
This paper presents a novel unsupervised probabilistic model estimation of visual background in video sequences using a variational autoencoder framework. Due to the redundant nature of the backgrounds in surveillance videos, visual information of the background can be compressed into a low-dimensional subspace in the encoder part of the variational autoencoder, while the highly variant information of its moving foreground gets filtered throughout its encoding-decoding process. Our deep probabilistic background model (DeepPBM) estimation approach is enabled by the power of deep neural networks in learning compressed representations of video frames and reconstructing them back to the original domain. We evaluated the performance of our DeepPBM in background subtraction on 9 surveillance videos from the background model challenge (BMC2012) dataset, and compared that with a standard subspace learning technique, robust principle component analysis (RPCA), which similarly estimates a deterministic low dimensional representation of the background in videos and is widely used for this application. Our method outperforms RPCA on BMC2012 dataset with 23% in average in F-measure score, emphasizing that background subtraction using the trained model can be done in more than 10 times faster.
  • References (23)
  • Citations (1)
References23
Newest
Behnaz Rezaei1
Estimated H-index: 1
(NU: Northeastern University),
Sarah Ostadabbas10
Estimated H-index: 10
(NU: Northeastern University)
We present a novel approach for unsupervised detection of moving objects with nonsalient movements (e.g., rodents in their home cage). The proposed approach starts with separating the moving object from its background by modeling the background in a computationally efficient way. The background modeling is based on the assumption that background in natural videos lies on a low-dimensional subspace. We formulated and solved this problem using a low-rank matrix completion framework. To achieve com...
Published on Sep 1, 2018in Multimedia Tools and Applications 2.10
Dimitrios Sakkos1
Estimated H-index: 1
(Northumbria University),
Heng Liu7
Estimated H-index: 7
(Anhui University of Technology)
+ 1 AuthorsLing Shao41
Estimated H-index: 41
(UEA: University of East Anglia)
Background subtraction in videos is a highly challenging task by definition, as it lays on a pixel-wise classification level. Therefore, great attention to detail is essential. In this paper, we follow the success of Deep Learning in Computer Vision and present an end-to-end system for background subtraction in videos. Our model is able to track temporal changes in a video sequence by applying 3D convolutions to the most recent frames of the video. Thus, no background model is needed to be retai...
Published on Sep 1, 2018in Pattern Recognition Letters 2.81
Long Ang Lim2
Estimated H-index: 2
(Ankara University),
Hacer Yalim Keles4
Estimated H-index: 4
(Ankara University)
Abstract Several methods have been proposed to solve moving objects segmentation problem accurately in different scenes. However, many of them lack the ability of handling various difficult scenarios such as illumination changes, background or camera motion, camouflage effect, shadow etc. To address these issues, we propose two robust encoder-decoder type neural networks that generate multi-scale feature encodings in different ways and can be trained end-to-end using only a few training samples....
Published on Apr 1, 2018in Pattern Recognition 5.90
Mohammadreza Babaee7
Estimated H-index: 7
(TUM: Technische Universität München),
Duc Tung Dinh2
Estimated H-index: 2
(TUM: Technische Universität München),
Gerhard Rigoll37
Estimated H-index: 37
(TUM: Technische Universität München)
We propose a novel approach based on deep learning for background subtraction from video sequences.A new algorithm to generate background model has been proposed.Input image patches and their corresponding background images are fed into CNN to do background subtraction.We utilized median filter to enhance the segmentation results.Experiments of Change detection results confirm the performance of the proposed approach. In this work, we present a novel background subtraction from video sequences a...
Behnaz Rezaei1
Estimated H-index: 1
(NU: Northeastern University),
Sarah Ostadabbas10
Estimated H-index: 10
(NU: Northeastern University)
Background subtraction is the primary task of the majority of video inspection systems. The most important part of the background subtraction which is common among different algorithms is background modeling. In this regard, our paper addresses the problem of background modeling in a computationally efficient way, which is important for current eruption of "big data" processing coming from high resolution multi-channel videos. Our model is based on the assumption that background in natural image...
Published on Sep 11, 2017 in ICIAP (International Conference on Image Analysis and Processing)
Simone Bianco17
Estimated H-index: 17
(University of Milano-Bicocca),
Gianluigi Ciocca20
Estimated H-index: 20
(University of Milano-Bicocca),
Raimondo Schettini31
Estimated H-index: 31
(University of Milano-Bicocca)
Given the existence of many change detection algorithms, each with its own peculiarities and strengths, we propose a combination strategy, that we termed IUTIS (In Unity There Is Strength), based on a genetic Programming framework. This combination strategy is aimed at leveraging the strengths of the algorithms and compensate for their weakness. In this paper we show our findings in applying the proposed strategy in two different scenarios. The first scenario is purely performance-based. The sec...
Published on Sep 1, 2017in Pattern Recognition Letters 2.81
Yi Wang3
Estimated H-index: 3
(Université de Sherbrooke),
Zhiming Luo4
Estimated H-index: 4
(Ha Tai: Xiamen University),
Pierre-Marc Jodoin23
Estimated H-index: 23
(Université de Sherbrooke)
The first machine learning method for ground truthing a video is proposed.We devise different sampling strategies for training different categories.Our results can be considered within the error margin of a human. With the increasing number of machine learning methods used for segmenting images and analyzing videos, there has been a growing need for large datasets with pixel accurate ground truth. In this letter, we propose a highly accurate semi-automatic method for segmenting foreground moving...
Published on Apr 3, 2017in Journal of the American Statistical Association 3.41
David M. Blei64
Estimated H-index: 64
(Columbia University),
Alp Kucukelbir7
Estimated H-index: 7
(Columbia University),
Jon McAuliffe14
Estimated H-index: 14
(University of California, Berkeley)
ABSTRACTOne of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation involving the posterior density. In this article, we review variational inference (VI), a method from machine learning that approximates probability densities through optimization. VI has been used in many applications and tends to be faster than classic...
Published on May 1, 2016 in IWSSIP (International Conference on Systems, Signals and Image Processing)
Marc Braham3
Estimated H-index: 3
(University of Liège),
Marc Van Droogenbroeck13
Estimated H-index: 13
(University of Liège)
Background subtraction is usually based on low-level or hand-crafted features such as raw color components, gradients, or local binary patterns. As an improvement, we present a background subtraction algorithm based on spatial features learned with convolutional neural networks (ConvNets). Our algorithm uses a background model reduced to a single background image and a scene-specific training dataset to feed ConvNets that prove able to learn how to subtract the background from an input image pat...
Published on Jan 1, 2016in arXiv: Machine Learning
Carl Doersch10
Estimated H-index: 10
In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function approximators (neural networks), and can be trained with stochastic gradient descent. VAEs have already shown promise in generating many kinds of complicated data, including handwritten digits, faces, house numbers, CIFAR images, physical models of scenes, segmentation, ...
Cited By1
Newest