Dynamic Deep Pixel Distribution Learning for Background Subtraction

Zhao, Chenqiu; Basu, Anup

doi:10.1109/tcsvt.2019.2951778

Cited by 24 publications

(7 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning-based methods are mostly supervised and have been recently proposed for MOD problems [30]- [32], [42], [44]. The first work based on CNNs is ConvNet-GT [33], which replaces the pixel classification component with a well-defined network structure.…”

Section: Related Workmentioning

confidence: 99%

A Fast Lightweight 3D Separable Convolutional Neural Network With Multi-Input Multi-Output for Moving Object Detection

Hou¹,

Liu

Ling

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Advances in moving object detection have been driven by the active application of deep learning methods. However, many existing models render superior detection accuracy at the cost of high computational complexity and slow inference speed. This fact has hindered the development of such models in mobile and embedded vision tasks, which need to be carried out in a timely fashion on a computationally limited platform. In this paper, we propose a super-fast (inference speed-154 fps) and lightweight (model size-1.45 MB) end-to-end 3D separable convolutional neural network with a multi-input multi-output (MIMO) strategy named "3DS_MM" for moving object detection. To improve detection accuracy, the proposed model adopts 3D convolution which is more suitable to extract both spatial and temporal information in video data than 2D convolution. To reduce model size and computational complexity, the standard 3D convolution is decomposed into depthwise and pointwise convolutions. Besides, we proposed a MIMO strategy to increase inference speed, which can take multiple frames as the network input and output multiple frames of detection results. Further, we conducted the scene dependent evaluation (SDE) and scene independent evaluation (SIE) on the benchmark CDnet2014 and DAVIS2016 datasets. Compared to stateof-the-art approaches, our proposed method significantly increases the inference speed, reduces the model size, meanwhile achieving the highest detection accuracy in the SDE setup and maintaining a competitive detection accuracy in the SIE setup.

show abstract

Section: Related Workmentioning

confidence: 99%

A Fast Lightweight 3D Separable Convolutional Neural Network With Multi-Input Multi-Output for Moving Object Detection

Hou¹,

Liu

Ling

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This section introduces three state-of-the-arts related to our topic. Dynamic Deep Pixel Distribution Learning (D-DPDL) proposed by Zhao et al in 2019 [1] focuses on handling the noise in the binary mask after background subtraction. Dense U-net Based on Patch-Based Learning proposed by Wang et al in 2019 [2] and Global-Feature Encoding U-Net (GEU-Net) proposed by Xiao et al in 2020 [3] modified the original U-Net to supplement the information lost when the background is subtracted from the traditional model.…”

Section: Brief Summary Of Existing Workmentioning

confidence: 99%

“…2. The proposed approach of D-DPDL [1] testing images are used to calculate the average final segmentation result. The model can learn these features efficiently.…”

Section: B Dense U-net Based On Patch-based Learningmentioning

confidence: 99%

Representation, Analysis of Bayesian Refinement Approximation Network: A Survey

Zhu¹,

Yang²

2021

Preprint

View full text Add to dashboard Cite

After an artificial model background subtraction, the pixels have been labelled as foreground and background. Previous approaches to secondary processing the output for denoising usually use traditional methods such as the Bayesian refinement method. In this paper, we focus on using a modified U-Net model to approximate the result of the Bayesian refinement method and improve the result. In our modified U-Net model, the result of background subtraction from other models will be combined with the source image as input for learning the statistical distribution. Thus, the losing information caused by the background subtraction model can be restored from the source image. Moreover, since the part of the input image is already the output of the other background subtraction model, the feature extraction should be convenient, it only needs to change the labels of the noise pixels. Compare with traditional methods, using deep learning methods superiority in keeping details.

show abstract

“…Target detection in the static background mainly includes the frame difference method [ 11 ], background difference method [ 12 ], etc. These methods are very effective in static backgrounds and are well established with high accuracy [ 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Video Global Motion Compensation Based on Affine Inverse Transform Model

Zhang,

Liu,

Xia

2023

Sensors

View full text Add to dashboard Cite

Global motion greatly increases the number of false alarms for object detection in video sequences against dynamic backgrounds. Therefore, before detecting the target in the dynamic background, it is necessary to estimate and compensate the global motion to eliminate the influence of the global motion. In this paper, we use the SURF (speeded up robust features) algorithm combined with the MSAC (M-Estimate Sample Consensus) algorithm to process the video. The global motion of a video sequence is estimated according to the feature point matching pairs of adjacent frames of the video sequence and the global motion parameters of the video sequence under the dynamic background. On this basis, we propose an inverse transformation model of affine transformation, which acts on each adjacent frame of the video sequence in turn. The model compensates the global motion, and outputs a video sequence after global motion compensation from a specific view for object detection. Experimental results show that the algorithm proposed in this paper can accurately perform motion compensation on video sequences containing complex global motion, and the compensated video sequences achieve higher peak signal-to-noise ratio and better visual effects.

show abstract

Dynamic Deep Pixel Distribution Learning for Background Subtraction

Cited by 24 publications

References 84 publications

A Fast Lightweight 3D Separable Convolutional Neural Network With Multi-Input Multi-Output for Moving Object Detection

A Fast Lightweight 3D Separable Convolutional Neural Network With Multi-Input Multi-Output for Moving Object Detection

Representation, Analysis of Bayesian Refinement Approximation Network: A Survey

Video Global Motion Compensation Based on Affine Inverse Transform Model

Contact Info

Product

Resources

About