Dynamic Background Learning through Deep Auto-encoder Networks

Xu, Pei; Ye, Mao; Li, Xue; Liu, Qihe; Yang, Yi; Ding, Jian

doi:10.1145/2647868.2654914

Cited by 35 publications

(25 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These last years, many researchers applied deep learning to background subtraction for more robust algorithms [40][41][42][43][44][45]. Xu et al proposed an efficient method for dynamic background based on deep auto-encoder networks [43], where the auto-encoder is an artificial neural network used for unsupervised learning of efficient codings.…”

Section: Recent Approachesmentioning

confidence: 99%

“…Xu et al proposed an efficient method for dynamic background based on deep auto-encoder networks [43], where the auto-encoder is an artificial neural network used for unsupervised learning of efficient codings. Zhang [42] proposed a deep learning based block-wise scene analysis method equipped with a binary spatio-temporal scene model.…”

Section: Recent Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Background Subtraction Based on a New Fuzzy Mixture of Gaussians for Moving Object Detection

et al. 2018

View full text Add to dashboard Cite

Abstract:Moving foreground detection is a very important step for many applications such as human behavior analysis for visual surveillance, model-based action recognition, road traffic monitoring, etc. Background subtraction is a very popular approach, but it is difficult to apply given that it must overcome many obstacles, such as dynamic background changes, lighting variations, occlusions, and so on. In the presented work, we focus on this problem (foreground/background segmentation), using a type-2 fuzzy modeling to manage the uncertainty of the video process and of the data. The proposed method models the state of each pixel using an imprecise and adjustable Gaussian mixture model, which is exploited by several fuzzy classifiers to ultimately estimate the pixel class for each frame. More precisely, this decision not only takes into account the history of its evolution, but also its spatial neighborhood and its possible displacements in the previous frames. Then we compare the proposed method with other close methods, including methods based on a Gaussian mixture model or on fuzzy sets. This comparison will allow us to assess our method's performance, and to propose some perspectives to this work.

show abstract

Section: Recent Approachesmentioning

confidence: 99%

Section: Recent Approachesmentioning

confidence: 99%

Background Subtraction Based on a New Fuzzy Mixture of Gaussians for Moving Object Detection

et al. 2018

View full text Add to dashboard Cite

show abstract

“…In [30], a non-convolutional autoencoder has been used to dynamically reconstruct the background and detect foreground elements. In [31], the concept is similar to this work, as high level convolutional features are used in detecting foreground elements.…”

Section: Introductionmentioning

confidence: 99%

“…The method is dependent on either human annotations or a simple background subtraction algorithm to initially generate training data. A critical drawback of both [30,31] for a tractor mounted camera is that they are developed for a static camera.…”

Section: Introductionmentioning

confidence: 99%

DeepAnomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field

Christiansen

Nielsen²,

Steen³

et al. 2016

Sensors

120

View full text Add to dashboard Cite

Convolutional neural network (CNN)-based systems are increasingly used in autonomous vehicles for detecting obstacles. CNN-based object detection and per-pixel classification (semantic segmentation) algorithms are trained for detecting and classifying a predefined set of object types. These algorithms have difficulties in detecting distant and heavily occluded objects and are, by definition, not capable of detecting unknown object types or unusual scenarios. The visual characteristics of an agriculture field is homogeneous, and obstacles, like people, animals and other obstacles, occur rarely and are of distinct appearance compared to the field. This paper introduces DeepAnomaly, an algorithm combining deep learning and anomaly detection to exploit the homogenous characteristics of a field to perform anomaly detection. We demonstrate DeepAnomaly as a fast state-of-the-art detector for obstacles that are distant, heavily occluded and unknown. DeepAnomaly is compared to state-of-the-art obstacle detectors including “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” (RCNN). In a human detector test case, we demonstrate that DeepAnomaly detects humans at longer ranges (45–90 m) than RCNN. RCNN has a similar performance at a short range (0–30 m). However, DeepAnomaly has much fewer model parameters and (182 ms/25 ms =) a 7.28-times faster processing time per image. Unlike most CNN-based methods, the high accuracy, the low computation time and the low memory footprint make it suitable for a real-time system running on a embedded GPU (Graphics Processing Unit).

show abstract

“…To make scene modeling more flexible, a number of sparse optimization based scene models [12,13] are recently proposed; but they cannot be highly scalable due to the high complexity induced by the 1 optimization. In recent years, deep learning is applied for dynamic background learning [16]; however, this work does not consider the further transformation for computational efficiency.…”

Section: Introductionmentioning

confidence: 99%

Deep learning driven blockwise moving object detection with binary scene modeling

Zhang

et al. 2015

Neurocomputing

View full text Add to dashboard Cite

Dynamic Background Learning through Deep Auto-encoder Networks

Cited by 35 publications

References 29 publications

Background Subtraction Based on a New Fuzzy Mixture of Gaussians for Moving Object Detection

Background Subtraction Based on a New Fuzzy Mixture of Gaussians for Moving Object Detection

DeepAnomaly: Combining Background Subtraction and Deep Learning for Detecting Obstacles and Anomalies in an Agricultural Field

Deep learning driven blockwise moving object detection with binary scene modeling

Contact Info

Product

Resources

About