Proceedings ArticleDOI
Dynamic Background Subtraction Using Least Square Adversarial Learning
Maryam Sultana,Arif Mahmood,Thierry Bouwmans,Soon Ki Jung +3 more
- pp 3204-3208
TLDR
The proposed method consisting of three loss-terms including least squares adversarial loss, L1-L Loss and Perceptual-Loss is evaluated on two benchmark datasets CDnet2014 and BMC and shows improved performance on both datasets compared with 10 existing state-of-the-art methods.Abstract:
Dynamic Background Subtraction (BS) is a fundamental problem in many vision-based applications. BS in real complex environments has several challenging conditions like illumination variations, shadows, camera jitters, and bad weather. In this study, we aim to address the challenges of BS in complex scenes by exploiting conditional least squares adversarial networks. During training, a scene-specific conditional least squares adversarial network with two additional regularizations including L 1 -Loss and Perceptual-Loss is employed to learn the dynamic background variations. The given input to the model is video frames conditioned on corresponding ground truth to learn the dynamic changes in complex scenes. Afterwards, testing is performed on unseen test video frames so that the generator would conduct dynamic background subtraction. The proposed method consisting of three loss-terms including least squares adversarial loss, L 1 -Loss and Perceptual-Loss is evaluated on two benchmark datasets CDnet2014 and BMC. The results of our proposed method show improved performance on both datasets compared with 10 existing state-of-the-art methods.read more
Citations
More filters
Journal Article
“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告
Journal ArticleDOI
Multi‑frame based adversarial learning approach for video surveillance
TL;DR: A novel multi-frame-based adversarial learning network is proposed with multi-scale inception and residual module for FBS to learn prominent features of the foreground object(s) to exhibit more temporal consistency.
Journal ArticleDOI
End-to-End Recurrent Generative Adversarial Network for Traffic and Surveillance Applications
TL;DR: In this paper, an end-to-end generative adversarial network (two generators) with recurrent technique is proposed for moving object segmentation (MOS), which is able to incorporate foreground probability knowledge with residual and weight sharing based recurrent technique for accurate segmentation.
Journal ArticleDOI
A Fast Lightweight 3D Separable Convolutional Neural Network With Multi-Input Multi-Output for Moving Object Detection
TL;DR: Wang et al. as discussed by the authors proposed a 3D separable convolutional neural network with a multi-input multi-output (MIMO) strategy for moving object detection.
Journal ArticleDOI
Unsupervised moving object segmentation using background subtraction and optimal adversarial noise sample search
TL;DR: In this article , the authors proposed a MOS algorithm exploiting multiple adversarial regularizations including conventional as well as least squares losses, which force the generator to synthesize dynamic background similar to the test sequences which upon subtraction results in moving objects segmentation.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Posted Content
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Proceedings ArticleDOI
Image-to-Image Translation with Conditional Adversarial Networks
TL;DR: Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Proceedings ArticleDOI
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
TL;DR: CycleGAN as discussed by the authors learns a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss.
Related Papers (5)
Data-driven background representation method to video surveillance.
Zhihui Li,Yingji Xia,Zhaowei Qu +2 more
Dual Discriminator Generative Adversarial Network for Video Anomaly Detection
Fei Dong,Yu Zhang,Xiushan Nie +2 more