Multiscale Cascaded Scene-Specific Convolutional Neural Networks for Background Subtraction

Liao, Jian; Guo, Guanjun; Yan, Yan; Wang, Hanzi

doi:10.1007/978-3-030-00776-8_48

Cited by 20 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some methods have also partitioned the frames into patches and use it as input layer to the network [66]- [68], [92], [152], [162]. Babaee et al [68] first generate a background image using SubSENSE and partition both the current frame and background into small patches and concatenated together to form the input layer.…”

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

“…Nguyen et al [92] process the smaller patches through a triplet CNN network to extract the relevant features for change detection. Similarly, the methods in [66], [67], [152], [162] also train the models in patch-based manner. In Fig.…”

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

“…Similarly, some studies have proposed the addition of well-designed auxiliary blocks or layers to enhance the motion-related representation capability of the network. The following statistical auxiliary blocks have been used in the literature: SuBSENSE [68], [89], [92], [139], [144], IUTIS [66], [152], PAWCS [83], designed algorithm [91 [141], [145], temporal median [70], [72], [74], [85], [87], [153], [156], [157], temporal histogram and motion saliency map [73], [146], [163], optical flow [127], [155], [164], [165], and conditional random fields (CRF) [67], [69].…”

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

“…The SubSENSE background estimation (BE) block has also been used in [68], [89], [139], [144]. Similarly, other proven methods such as IUTIS [66], [152] and PAWCS [83] have also been added as the BE block. Fig.…”

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

See 3 more Smart Citations

An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs

Mandal¹,

Vipparthi²

2021

Preprint

View full text Add to dashboard Cite

Visual change detection, aiming at segmentation of video frames into foreground and background regions, is one of the elementary tasks in computer vision and video analytics. The applications of change detection include anomaly detection, object tracking, traffic monitoring, human machine interaction, behavior analysis, action recognition, and visual surveillance. Some of the challenges in change detection include background fluctuations, illumination variation, weather changes, intermittent object motion, shadow, fast/slow object motion, camera motion, heterogeneous object shapes and realtime processing. Traditionally, this problem has been solved using hand-crafted features and background modelling techniques. In recent years, deep learning frameworks have been successfully adopted for robust change detection. This article aims to provide an empirical review of the state-of-the-art deep learning methods for change detection. More specifically, we present a detailed analysis of the technical characteristics of different model designs and experimental frameworks. We provide model design based categorization of the existing approaches, including the 2D-CNN, 3D-CNN, ConvLSTM, multi-scale features, residual connections, autoencoders and GAN based methods. Moreover, an empirical analysis of the evaluation settings adopted by the existing deep learning methods is presented. To the best of our knowledge, this is a first attempt to comparatively analyze the different evaluation frameworks used in the existing deep change detection methods. Finally, we point out the research needs, future directions and draw our own conclusions.

show abstract

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

See 2 more Smart Citations

An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs

Mandal¹,

Vipparthi²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These previous methods usually require a large amount of densely labeled video training data. To solve this problem, Liao et al [112] designed a multi-scale cascaded scene-specific (MCSS) CNNs based background subtraction method with a novel training strategy. The architecture combined the ConvNets [22] and the multiscalecascaded architecture [204] with a training that takes advantage of the balance of positive and negative training samples.…”

Section: Multi-scale and Cascaded Cnnsmentioning

confidence: 99%

Deep neural network concepts for background subtraction:A systematic review and comparative evaluation

et al. 2019

View full text Add to dashboard Cite

Conventional neural networks show a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known SOBS method and its variants based on neural networks were the leader methods on the largescale CDnet 2012 dataset during a long time. Recently, convolutional neural networks which belong to deep learning methods were employed with success for background initialization, foreground detection and deep learned features. Currently, the top current background subtraction methods in CDnet 2014 are based on deep neural networks with a large gap of performance in comparison on the conventional unsupervised approaches based on multi-features or multi-cues strategies. Furthermore, a huge amount of papers was published since 2016 when Braham and Van Droogenbroeck published their first work on CNN applied to background subtraction providing a regular gain of performance. In this context, we provide the first review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions. For this, we first surveyed the methods used background initialization, background subtraction and deep learned features. Then, we discuss the adequacy of deep neural networks for background subtraction. Finally, experimental results are presented on the CDnet 2014 dataset.

show abstract

Moving Objects Segmentation Based on DeepSphere in Video Surveillance

Ammar

Bouwmans

Zaghden

et al. 2019

Advances in Visual Computing

View full text Add to dashboard Cite

Multiscale Cascaded Scene-Specific Convolutional Neural Networks for Background Subtraction

Cited by 20 publications

References 13 publications

An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs

An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs

Deep neural network concepts for background subtraction:A systematic review and comparative evaluation

Moving Objects Segmentation Based on DeepSphere in Video Surveillance

Contact Info

Product

Resources

About