Mingrui Yang

Efficient background subtraction for real-time tracking in embedded camera networks

Background subtraction is often the first step of many computer vision applications. 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 computational efficient. The key idea is to use compressive sensing 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, real implementation on an embedded camera platform shows that our proposed method is at least 5 times faster, and consumes significantly less energy and memory 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.

Radio-based device-free activity recognition with radio frequency interference

Activity recognition is an important component of many pervasive computing applications. Device-free activity recognition has the advantage that it does not have the privacy concern of using cameras and the subjects do not have to carry a device on them. Recently, it has been shown that 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 conduct experiments in environments without and with RFI. 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 shows that the performance of state-of-the-art classification methods may degrade significantly with RFI. We then propose a number of counter measures to mitigate the impact of RFI and improve the location-oriented activity recognition performance. Our evaluation shows the proposed method can improve up to 10% true detection rate in the presence of RFI. We also study the impact of bandwidth on activity recognition performance. We show that with a channel bandwidth of 20 MHz (which is used by WiFi), it is possible to achieve a good activity recognition accuracy when RFI is present.

Face recognition on smartphones via optimised sparse representation classification

Face recognition is an element of many smartphone apps, e.g. face unlocking, people tagging and games. Sparse Representation Classification (SRC) is a state-of-the-art face recognition algorithm, which has been shown to outperform many classical face recognition algorithms in OpenCV. The success of SRC is due to its use of ℓ1 optimisation, which makes SRC robust to noise and occlusions. Since ℓ1 optimisation is computationally intensive, SRC uses random projection matrices to reduce the dimension of the ℓ1 problem. However, random projection matrices do not give consistent classification accuracy. In this paper, we propose a method to optimise the projection matrix for ℓ1-based classification1. Our evaluations, based on publicly available databases and real experiment, show that face recognition based on the optimised projection matrix can be 5-17% more accurate than its random counterpart and OpenCV algorithms. Furthermore, the optimised projection matrix does not have to be re-calculated even if new faces are added to the training set. We implement the SRC with optimised projection matrix on Android smartphones and find that the computation of residuals in SRC is a severe bottleneck, taking up 85-90% of the computation time. To address this problem, we propose a method to compute the residuals approximately, which is 50 times faster but without sacrificing recognition accuracy. Lastly, we demonstrate the feasibility of our new algorithm by the implementation and evaluation of a new face unlocking app and show its robustness to variation to poses, facial expressions, lighting changes and occlusions.

Efficient cross-correlation via sparse representation in sensor networks

Cross-correlation is a popular signal processing technique used in numerous localization and tracking systems for obtaining reliable range information. However, a practical efficient implementation has not yet been achieved on resource constrained wireless sensor network platforms. We propose cross-correlation via sparse representation: a new framework for ranging based on l1-minimization. The key idea is to compress the signal samples on the mote platform by efficient random projections and transfer them to a central device, where a convex optimization process estimates the range by exploiting its sparsity in our proposed correlation domain. Through sparse representation theory validation, extensive empirical studies and experiments on an end-to-end acoustic ranging system implemented on resource limited off-the-shelf sensor nodes, we show that the proposed framework, together with the proposed correlation domain achieved up to two order of magnitude better performance compared to naive approaches such as working on DCT domain and downsampling. Furthermore, compared to cross-correlation results, 30-40% measurements are sufficient to obtain precise range estimates with an additional bias of only 2-6cm for high accuracy application requirements, while 5% measurements are adequate to achieve approximately 100cm precision for lower accuracy applications.

Real-time classification via sparse representation in acoustic sensor networks

Acoustic Sensor Networks (ASNs) have a wide range of applications in natural and urban environment monitoring, as well as indoor activity monitoring. In-network classification is critically important in ASNs because wireless transmission costs several orders of magnitude more energy than computation. The main challenges of in-network classification in ASNs include effective feature selection, intensive computation requirement and high noise levels. To address these challenges, we propose a sparse representation based feature-less, low computational cost, and noise resilient framework for in-network classification in ASNs. The key component of Sparse Approximation based Classification (SAC), ℓ1 minimization, is a convex optimization problem, and is known to be computationally expensive. Furthermore, SAC algorithms assumes that the test samples are a linear combination of a few training samples in the training sets. For acoustic applications, this results in a very large training dictionary, making the computation infeasible to be performed on resource constrained ASN platforms. Therefore, we propose several techniques to reduce the size of the problem, so as to fit SAC for in-network classification in ASNs. Our extensive evaluation using two real-life datasets (consisting of calls from 14 frog species and 20 cricket species respectively) shows that the proposed SAC framework outperforms conventional approaches such as Support Vector Machines (SVMs) and k-Nearest Neighbor (kNN) in terms of classification accuracy and robustness. Moreover, our SAC approach can deal with multi-label classification which is common in ASNs. Finally, we explore the system design spaces and demonstrate the real-time feasibility of the proposed framework by the implementation and evaluation of an acoustic classification application on an embedded ASN testbed.

SimpleTrack: Adaptive Trajectory Compression With Deterministic Projection Matrix for Mobile Sensor Networks

Some mobile sensor network applications require the sensor nodes to transfer their trajectories to a data sink. This paper proposes an adaptive trajectory (lossy) compression algorithm based on compressive sensing. The algorithm has two innovative elements. First, we propose a method to compute a deterministic projection matrix from a learnt dictionary. Second, we propose a method for the mobile nodes to adaptively predict the number of projections needed based on the speed of the mobile nodes. Extensive evaluation of the proposed algorithm using six data sets shows that our proposed algorithm can achieve submeter accuracy. In addition, our method of computing projection matrices outperforms two existing methods. Finally, comparison of our algorithm against a state-of-the-art trajectory compression algorithm shows that our algorithm can reduce the error by 10-60 cm for the same compression ratio.

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

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.

Distributed sparse approximation for frog sound classification

Sparse approximation has now become a buzzword for classification in numerous research domains. We propose a distributed sparse approximation method based on ℓ1 minimization for frog sound classification, which is tailored to the resource constrained wireless sensor networks. Our pilot study demonstrates that ℓ1 minimization can run on wireless sensor nodes producing satisfactory classification accuracy.

New Coherence and RIP Analysis for Weak Orthogonal Matching Pursuit

In this paper we define a new coherence index, named the global 2-coherence, of a given dictionary and study its relationship with the conventional mutual coherence and the restricted isometry constant. By exploring this relationship, we obtain more general results on sparse signal reconstruction using greedy algorithms in the compressive sensing (CS) framework. In particular, we obtain an improved bound over the best known results on the restricted isometry constant for successful recovery of sparse signals using orthogonal matching pursuit (OMP).

Efficient background subtraction for tracking in embedded camera networks

Background subtraction is often the first step in many computer vision applications such as object localisation and tracking. It aims to segment out moving parts of a scene that represent object of interests. In the field of computer vision, researchers have dedicated their efforts to improve the robustness and accuracy of such segmentations but most of their methods are computationally intensive, making them nonviable options for our targeted embedded camera platform whose energy and processing power is significantly more con-strained. To address this problem as well as maintain an acceptable level of performance, we introduce Compressive Sensing (CS) to the widely used Mixture of Gaussian to create a new background subtraction method. The results show that our method not only can decrease the computation significantly (a factor of 7 in a DSP setting) but remains comparably accurate.