Autoencoder-based background reconstruction and foreground segmentation with background noise estimation
Even after decades of research, dynamic scene background reconstruction and foreground object segmentation are still considered as open problems due various challenges such as illumination changes, camera movements, or background noise caused by air turbulence or moving trees. We propose in this paper to model the background of a frame sequence as a low dimensional manifold using an autoencoder and compare the reconstructed background provided by this autoencoder with the original image to compute the foreground/background segmentation masks. The main novelty of the proposed model is that the autoencoder is also trained to predict the background noise, which allows to compute for each frame a pixel-dependent threshold to perform the foreground segmentation. Although the proposed model does not use any temporal or motion information, it exceeds the state of the art for unsupervised background subtraction on the CDnet 2014 and LASIESTA datasets, with a significant improvement on videos where the camera is moving. It is also able to perform background reconstruction on some non-video image datasets.
Code (1)
Tasks
Foreground SegmentationSegmentationUnsupervised Video Object SegmentationVideo Background SubtractionVideo Object SegmentationSimilar Papers 제목 키워드 기반
EAA-Net: Rethinking the Autoencoder Architecture with Intra-class Features for Medical Image Segmentation
Automatic image segmentation technology is critical to the visual analysis. The autoencoder architecture has satisfying performance in various image segmentation tasks. However, autoencoders based on convolutional neural…
Image SegmentationMedical Image SegmentationMulti-Task LearningSegmentation+1Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
Foreground segmentation in video sequences is a classic topic in computer vision. Due to the lack of semantic and prior knowledge, it is difficult for existing methods to deal with sophisticated scenes well. Therefore, i…
DecoderForeground SegmentationSegmentationJoint Motion Segmentation and Background Estimation in Dynamic Scenes
We propose a joint foreground-background mixture model (FBM) that simultaneously performs background estimation and motion segmentation in complex dynamic scenes. Our FBM consist of a set of location-specific dynamic tex…
Motion SegmentationSegmentationIllumination Invariant Foreground Object Segmentation using ForeGANs
The foreground segmentation algorithms suffer performance degradation in the presence of various challenges such as dynamic backgrounds, and various illumination conditions. To handle these challenges, we present a foreg…
Foreground SegmentationGenerative Adversarial NetworkObjectSegmentation+1A Robust Regression Approach for Background/Foreground Segmentation
Background/foreground segmentation has a lot of applications in image and video processing. In this paper, a segmentation algorithm is proposed which is mainly designed for text and line extraction in screen content. The…
ClusteringForeground SegmentationregressionSegmentation