Real-Time and Robust Compressive Background Subtraction for Embedded Camera Networks

Shen, Yiran; Hu, Wen; Yang, Mingrui; Liu, Junbin; Wei, Bo; Lucey, Simon; Chou, Chun Tung

doi:10.1109/tmc.2015.2418775

Cited by 38 publications

(21 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They report that extending their model with optical flow for modeling temporal information increases the segmentation accuracy. Shen et al [2] propose an efficient approach to BGS by reducing the dimensionality of the input data with a random projection matrix. Finally, they apply a GMM on the projected data.…”

Section: Related Work a Gaussian Mixture Modelsmentioning

confidence: 99%

“…Unlike object detection, the task lies on a pixel-wise level, and therefore being inherently more challenging. It is commonly considered as the first step of many real-world applications, such as person re-identification [1], object tracking [2], gesture recognition [3], vehicle tracking [4], crowd analysis [5] and even use cases of the medical domain [6]. Thus, the development of robust BGS methods is of paramount importance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Illumination-Aware Multi-Task GANs for Foreground Segmentation

Sakkos

Shum

2019

IEEE Access

View full text Add to dashboard Cite

Foreground-background segmentation has been an active research area over the years. However, conventional models fail to produce accurate results when challenged with the videos of challenging illumination conditions. In this paper, we present a robust model that allows accurately extracting the foreground even in exceptionally dark or bright scenes and in continuously varying illumination in a video sequence. This is accomplished by a triple multi-task generative adversarial network (TMT-GAN) that effectively models the semantic relationship between the dark and bright images and performs binary segmentation end-to-end. Our contribution is twofold: first, we show that by jointly optimizing the GAN loss and the segmentation loss, our network simultaneously learns both tasks that mutually benefit each other. Second, fusing features of images with varying illumination into the segmentation branch vastly improve the performance of the network. Comparative evaluations on highly challenging real and synthetic benchmark datasets (ESI and SABS) demonstrate the robustness of TMT-GAN and its superiority over state-of-the-art approaches. INDEX TERMS Background subtraction, multi-task learning, generative adversarial networks, video segmentation, illumination-aware.

show abstract

Section: Related Work a Gaussian Mixture Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Illumination-Aware Multi-Task GANs for Foreground Segmentation

Sakkos

Shum

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Besides recognition, compressed sensing is also applied to background subtraction [28,29,52], data compression for in-situ soil moisture sensing [47], and cross-correlation for acoustic ranging [19] and GPS ranging [20].…”

Section: Application Of Compressed Sensing On Wireless Sensor Networkmentioning

confidence: 99%

From Real to Complex

Wei

Yang

et al. 2019

ACM Trans. Sen. Netw.

Self Cite

View full text Add to dashboard Cite

Activity recognition is an important component of many pervasive computing applications. Radio-based activity recognition has the advantage that it does not have the privacy concern compared with camera-based solutions, and subjects do not have to carry a device on them. It has been shown channel state information(CSI) can be used for activity recognition in a device-free setting. With the proliferation of wireless devices, it is important to understand how radio frequency interference(RFI) can impact on pervasive computing applications. In this paper, we investigate the impact of RFI on device-free CSI-based location-oriented activity recognition. We present data to show that RFI can have a significant impact on the CSI vectors. In the absence of RFI, different activities give rise to different CSI vectors that can be differentiated visually. However, in the presence of RFI, the CSI vectors become much noisier, and activity recognition also becomes harder. Our extensive experiments show that the performance may degrade significantly with RFI. We then propose a number of countermeasures to mitigate the impact of RFI and improve the performance. We are also the first to use complex-valued CSI along with the state-of-the-art Sparse Representation Classification method to enhance the performance in the environment with RFI.

show abstract

“…the static parts of a given scene) [1]. A large number of realworld applications, such as person re-identification [2], object tracking [3], gesture recognition [4], vehicle tracking [5], video recognition [6], action recognition [7], [8], crowd analysis [9] and even use cases of the medical domain [10], [11], depend on accurate and robust background subtraction as a first step of their pipelines.…”

Section: Introductionmentioning

confidence: 99%

Illumination-Based Data Augmentation for Robust Background Subtraction

Sakkos

Shum

2019

2019 13th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)

View full text Add to dashboard Cite

A core challenge in background subtraction (BGS) is handling videos with sudden illumination changes in consecutive frames. In this paper, we tackle the problem from a data point-of-view using data augmentation. Our method performs data augmentation that not only creates endless data on the fly, but also features semantic transformations of illumination which enhance the generalisation of the model. It successfully simulates flashes and shadows by applying the Euclidean distance transform over a binary mask generated randomly. Such data allows us to effectively train an illumination-invariant deep learning model for BGS. Experimental results demonstrate the contribution of the synthetics in the ability of the models to perform BGS even when significant illumination changes take place. The source code of the project is made publicly available at https://github.com/dksakkos/illumination augmentation.

show abstract

Real-Time and Robust Compressive Background Subtraction for Embedded Camera Networks

Abstract: Tung (2016) Real-Time and Robust Compressive Background Subtraction for Embedded Camera Networks. IEEE Transactions on Mobile Computing, 15 (2). pp. 406-418.

Cited by 38 publications

References 36 publications

Illumination-Aware Multi-Task GANs for Foreground Segmentation

Illumination-Aware Multi-Task GANs for Foreground Segmentation

From Real to Complex

Illumination-Based Data Augmentation for Robust Background Subtraction

Contact Info

Product

Resources

About