TY - JOUR

T1 - Real-Time and Robust Compressive Background Subtraction for Embedded Camera Networks

AU - Shen, Yiran

AU - Hu, Wen

AU - Yang, Mingrui

AU - Liu, Junbin

AU - Wei, Bo

AU - Lucey, Simon

AU - Chou, Chun Tung

PY - 2016/2/28

Y1 - 2016/2/28

N2 - Real-time target tracking is an important service provided by embedded camera networks. The first step in target tracking is to extract the moving targets from the video frames, which can be realised by using background subtraction. For a background subtraction method to be useful in embedded camera networks, it must be both accurate and computationally efficient because of the resource constraints on embedded platforms. This makes many traditional background subtraction algorithms unsuitable for embedded platforms because they use complex statistical models to handle subtle illumination changes. These models make them accurate but the computational requirement of these complex models is often too high for embedded platforms. In this paper, we propose a new background subtraction method which is both accurate and computationally efficient. We propose a baseline version which uses luminance only and then extend it to use colour information. The key idea is to use random projection matrics to reduce the dimensionality of the data while retaining most of the information. By using multiple datasets, we show that the accuracy of our proposed background subtraction method is comparable to that of the traditional background subtraction methods. Moreover, to show the computational efficiency of our methods is not platform specific, we implement it on various platforms. The real implementation shows that our proposed method is consistently better and is up to six times faster, and consume significantly less resources than the conventional approaches. Finally, we demonstrated the feasibility of the proposed method by the implementation and evaluation of an end-to-end real-time embedded camera network target tracking application.

AB - Real-time target tracking is an important service provided by embedded camera networks. The first step in target tracking is to extract the moving targets from the video frames, which can be realised by using background subtraction. For a background subtraction method to be useful in embedded camera networks, it must be both accurate and computationally efficient because of the resource constraints on embedded platforms. This makes many traditional background subtraction algorithms unsuitable for embedded platforms because they use complex statistical models to handle subtle illumination changes. These models make them accurate but the computational requirement of these complex models is often too high for embedded platforms. In this paper, we propose a new background subtraction method which is both accurate and computationally efficient. We propose a baseline version which uses luminance only and then extend it to use colour information. The key idea is to use random projection matrics to reduce the dimensionality of the data while retaining most of the information. By using multiple datasets, we show that the accuracy of our proposed background subtraction method is comparable to that of the traditional background subtraction methods. Moreover, to show the computational efficiency of our methods is not platform specific, we implement it on various platforms. The real implementation shows that our proposed method is consistently better and is up to six times faster, and consume significantly less resources than the conventional approaches. Finally, we demonstrated the feasibility of the proposed method by the implementation and evaluation of an end-to-end real-time embedded camera network target tracking application.

KW - Object Tracking

KW - Real-time Performance

KW - Embedded Camera Networks

KW - Background Subtraction

KW - Compressive Sensing

KW - Gaussian Mixture Models

U2 - 10.1109/TMC.2015.2418775

DO - 10.1109/TMC.2015.2418775

M3 - Journal article

VL - 15

SP - 406

EP - 418

JO - IEEE Transactions on Mobile Computing (TMC)

JF - IEEE Transactions on Mobile Computing (TMC)

IS - 2

ER -