On the role and the importance of features for background modeling and foreground detection

Bouwmans, Thierry; Silva, Caroline; Marghes, Cristina; Zitouni, M. Sami; Bhaskar, Harish; Frélicot, Carl

doi:10.1016/j.cosrev.2018.01.004

Cited by 91 publications

(38 citation statements)

References 450 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cascaded CNN provides an overall F-Measure of 0.9209 in CDnet2014 dataset [203]. For the Cascaded CNN's implementation 17 available online, Wang et al [204] used the Caffe library 18 [98] and MatConvNet 19 . The limitations of Cascaded CNN are as follows: 1) it is more dedicated to ground-truth generation than an automated background/foreground separation method, and 2) it is also computationally expensive.…”

Section: Multi-scale and Cascaded Cnnsmentioning

confidence: 99%

“…Features used played an important role in the robustness against the challenge met in video [19] [141] features were often employed to deal with illumination changes, dynamic background, and camouflage. But, it needs practically to choice an operator [5][7] [35] to fuse the results which come from the different features or a feature selection scheme [173] [174].…”

Section: Deep Learned Featuresmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2019

Self Cite

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: Deep Learned Featuresmentioning

confidence: 99%

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

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The feature extraction stage uses a set of training images to train an algorithm with a specific feature or series of features. There are a variety of feature types available for computer vision, often categorized into spectral, spatial, and temporal features (Bouwmans et al, ). After the feature extraction stage, the classification stage determines if each image in a testing set contains the object of interest.…”

Section: Introductionmentioning

confidence: 99%

Automatic counting of birds in a bird deterrence field trial

Simons

Hinders

2019

Ecology and Evolution

View full text Add to dashboard Cite

Decreasing costs in high‐quality digital cameras, image processing, and digital storage allow researchers to generate and store massive amounts of digital imagery. The time needed to manually analyze these images will always be a limiting factor for experimental design and analysis. Implementation of computer vision algorithms for automating the detection and counting of animals reduces the manpower needed to analyze field images.For this paper, we assess the ability of computer vision to detect and count birds in images from a field test that was not designed for computer vision. Using video stills from the field test and Matlab's Computer Vision Toolbox, we designed and evaluated a cascade object detection method employing Haar and Local Binary Pattern feature types.Without editing the images, we found that the Haar feature can have a recall over 0.5 with an Intersection over Union threshold of 0.5. However, using this feature, 86% of the frames without birds had false‐positive bird detections. Reducing the false positives could lead to these detection methods being implemented into a fully automated system for detecting and counting birds.Accurately detecting and counting birds using computer vision will reduce manpower for field experiments, both in experimental design and data analysis. Improvements in automated detection and counting will allow researchers to design extended trials without the added step of optimizing the experimental setup and/or captured images for computer vision.

show abstract

“…Most of them are developed under the assumption that foreground and background show visually distinct characteristics and thus the foreground can be detected once a good background model is obtained. However, there are cases of camouflage in color [14] where the foreground share similar color as the background. For example, in Fig.…”

Section: Introductionmentioning

confidence: 99%

A Fusion Framework for Camouflaged Moving Foreground Detection in the Wavelet Domain

Florêncio

et al. 2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Detecting camouflaged moving foreground objects has been known to be difficult due to the similarity between the foreground objects and the background. Conventional methods cannot distinguish the foreground from background due to the small differences between them and thus suffer from underdetection of the camouflaged foreground objects. In this paper, we present a fusion framework to address this problem in the wavelet domain. We first show that the small differences in the image domain can be highlighted in certain wavelet bands. Then the likelihood of each wavelet coefficient being foreground is estimated by formulating foreground and background models for each wavelet band. The proposed framework effectively aggregates the likelihoods from different wavelet bands based on the characteristics of the wavelet transform. Experimental results demonstrated that the proposed method significantly outperformed existing methods in detecting camouflaged foreground objects. Specifically, the average F-measure for the proposed algorithm was 0.87, compared to 0.71 to 0.8 for the other stateof- the-art methods.

show abstract

On the role and the importance of features for background modeling and foreground detection

Cited by 91 publications

References 450 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

Automatic counting of birds in a bird deterrence field trial

A Fusion Framework for Camouflaged Moving Foreground Detection in the Wavelet Domain

Contact Info

Product

Resources

About