Deep Background Subtraction with Guided Learning

Liang, Xingwei; Liao, Shengcai; Wang, Xiaobo; Liu, Wei; Chen, Yuxuan; Li, Stan Z.

doi:10.1109/icme.2018.8486556

Cited by 15 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Multi-scale and Cascaded Cnnsmentioning

confidence: 99%

“…Liang et al [111] developed a multi-scale CNN based background subtraction method by learning a specific CNN model for each video to ensure accuracy, but manage to avoid manual labeling. First, Liang et al [111] applied the SubSENSE algorithm to get an initial foreground mask. Then, an adaptive strategy is applied to select reliable pixels to guide the CNN training because the outputs of SubSENSE cannot be directly used as ground truth due the lack of accuracy of the results.…”

Section: Multi-scale and Cascaded Cnnsmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Multi-scale and Cascaded Cnnsmentioning

confidence: 99%

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

show abstract

“…Recently, both CNN and foreground attentive neural network (FANN) models have been developed to perform foreground segmentation [62], [63]. In addition to conventional Gaussian mixture model (GMM)-based background subtraction, recent explorations have also shown that CNN models could be effectively used for the same purpose [64], [65]. To address these separated foreground objects and background attributes, Zhang et al [66] introduced a new background mode to more compactly represent background information with better R-D efficiency.…”

Section: A Saliency-based Video Preprocessingmentioning

confidence: 99%

Advances in Video Compression System Using Deep Neural Network: A Review and Case Studies

Ding

Chen

et al. 2021

Proc. IEEE

View full text Add to dashboard Cite

Significant advances in video compression systems have been made in the past several decades to satisfy the near-exponential growth of Internet-scale video traffic. From the application perspective, we have identified three major functional blocks, including preprocessing, coding, and postprocessing, which have been continuously investigated to maximize the end-user quality of experience (QoE) under a limited bit rate budget. Recently, artificial intelligence (AI)-powered techniques have shown great potential to further increase the efficiency of the aforementioned functional blocks, both individually and jointly. In this article, we review recent technical advances in video compression systems extensively, with an emphasis on deep neural network (DNN)based approaches, and then present three comprehensive case studies. On preprocessing, we show a switchable texturebased video coding example that leverages DNN-based scene understanding to extract semantic areas for the improvement Manuscript

show abstract

“…In addition, Babaee et al [52] proposed a robust model in which a network is used to subtract the background from the current frame and only 5% of the labeled masks are utilized for training. Liang et al [53] utilized the foreground mask generated by the SubSENSE algorithm [15] rather than manual labeling for training, and Zeng et al [54] used a convolutional neural network to combine several background subtraction algorithms together. In our work, since the distributions of temporal pixels are captured from every spatial pixel, a large number of training instances can be captured with a limited number of ground truth frames.…”

Section: B Algorithms Based On Deep Learningmentioning

confidence: 99%

“…However, the comparison between FgSegNet and the proposed approach is unfair, since we only use 20 ground truth frames for training and the number of parameters in our network is much less than their network. In addition, there are a few semi-supervised algorithms (e.g., GuidedBS [53], BSUV-Net [90] and GraphMOS [56]) which did not utilize any ground truth frames from testing videos for training. However, these methods assumed a large number of binary masks from another video for training, and used several pretrained networks.…”

Section: Evaluation Of Arithmetic Distribution For Background Subtrac...mentioning

confidence: 99%

Dynamic Deep Pixel Distribution Learning for Background Subtraction

Zhao

Basu

2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

We propose a new Arithmetic Distribution Neural Network (ADNN) for learning the distributions of temporal pixels during background subtraction. In our ADNN, the arithmetic distribution operations are utilized to propose the arithmetic distribution layers, including the product distribution layer and the sum distribution layer. Furthermore, in order to improve the accuracy of the proposed approach, an improved Bayesian refinement model based on neighboring information, with a GPU implementation, is introduced. In the forward pass and backpropagation of the proposed arithmetic distribution layers, histograms are considered as probability density functions rather than matrices. Thus, the proposed approach is able to utilize the probability information of the histogram and achieve promising results with a very simple architecture compared to traditional convolutional neural networks. Evaluations using standard benchmarks demonstrate the superiority of the proposed approach compared to state-of-the-art traditional and deep learning methods. To the best of our knowledge, this is the first method to propose network layers based on arithmetic distribution operations for learning distributions during background subtraction.

show abstract

Deep Background Subtraction with Guided Learning

Cited by 15 publications

References 12 publications

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

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

Advances in Video Compression System Using Deep Neural Network: A Review and Case Studies

Dynamic Deep Pixel Distribution Learning for Background Subtraction

Contact Info

Product

Resources

About