A multithreaded implementation for TransLucid T Rahilly, J Plaice, Proceedings - International Computer Software and Applications Conference, Institute of Electrical and Electronics Engineers Computer Society, Piscataway, NJ 08855-1331, USA, Piscataway, NJ, USA, 2008, pp. 1272 - 1277
An experimental study on pedestrian classification using local features S Paisitkriangkrai, J Zhang, 2008 IEEE international symposium on circuits and systems, Proceedings, IEEE computer society, USA, 2008, pp. 2741 - 2744
This paper presents an experimental study on pedestrian detection using state-of-the-art local feature extraction and support vector machine (SVM) classifiers. The performance of pedestrian detection using region covariance, histogram of oriented gradients (HOG) and local receptive fields (LRF) feature descriptors is experimentally evaluated. The experiments are performed on both the benchmarking dataset used in [1] and the MIT CBCL dataset. Both can be publicly accessed. The experimental results show that region covariance features with radial basis function (RBF) kernel SVM and HOG features with quadratic kernel SVM outperform the combination of LRF features with quadratic kernel SVM reported in [1].
Face detection from few training examples S Paisitkriangkrai, J Zhang, 2008 15th IEEE international conference on image processing, Proceedings, IEEE, USA, 2008, pp. 2764 - 2767
Face detection in images is very important for many multimedia applications. Haar-like wavelet features have become dominant in face detection because of their tremendous success since Viola and Jones [1] proposed their AdaBoost based detection system. While Haar features' simplicity makes rapid computation possible, its discriminative power is limited. As a consequence, a large training dataset is required to train a classifier. This may hamper its application in scenarios that a large labeled dataset is difficult to obtain. In this work, we address the problem of learning to detect faces from a small set of training examples. In particular, we propose to use co- variance features. Also for better classification performance, linear hyperplane classifier based on Fisher discriminant analysis (FDA) is proffered. Compared with the decision stump, FDA is more discriminative and therefore fewer weak learners are needed. We show that the detection rate can be significantly improved with covariance features on a small dataset (a few hundred positive examples), compared to Haar features used in current most face detection systems.
Fast pedestrian detection using a cascade of boosted covariance features (None HERDC) S Paisitkriangkrai, S Paisitkriangkrai, J Zhang, C Shen, IEEE Transactions on Circuits and Systems for Video Technology, IEEE, 2008, 1140-1151
Efficiently and accurately detecting pedestrians plays a very important role in many computer vision applications such as video surveillance and smart cars. In order to find the right feature for this task, we first present a comprehensive experimental study on pedestrian detection using state-of-the-art locally extracted features (e.g., local receptive fields, histogram of oriented gradients, and region covariance). Building upon the findings of our experiments, we propose a new, simpler pedestrian detector using the covariance features. Unlike the work in , where the feature selection and weak classifier training are performed on the Riemannian manifold, we select features and train weak classifiers in the Euclidean space for faster computation. To this end, AdaBoost with weighted Fisher linear discriminant analysis-based weak classifiers are designed. A cascaded classifier structure is constructed for efficiency in the detection phase. Experiments on different datasets prove that the new pedestrian detector is not only comparable to the state-of-the-art pedestrian detectors but it also performs at a faster speed. To further accelerate the detection, we adopt a faster strategy—multiple layer boosting with heterogeneous features—to exploit the efficiency of the Haar feature and the discriminative power of the covariance feature. Experiments show that, by combining the Haar and covariance features, we speed up the original covariance feature detector by up to an order of magnitude in detection time with a slight drop in detection performance.
How much of DSRC is available for non-safety use? M Hassan, Z Wang, 5th ACM international workshop on vehicular inter-networking, Proceedings, ACM, New York, USA, 2008, pp. 23 - 29
The Dedicated Short Range Communication (DSRC) technology is currently being
standardized by the IEEE to enable a range of communication-based automotive
safety applications. However, for DSRC to be cost-effective, it is important to
accommodate commercial non-safety use of the spectrum as well. The co-existence
of safety and non-safety is achieved through a periodic channel switching scheme
whereby access to DSRC alternates between these two classes of applications. In
this paper, we propose a framework that links the non-safety share of DSRC as
effected by the channel switching to the performance requirements of safety
applications. Using simulation experiments, we analyze the non-safety
opportunity in the DSRC under varied road traffic conditions. We find that
non-safety use of DSRC may have to be severely restricted during peak hours of
traffic to insure that automotive safety is not compromised. Our study also
provides interesting insights into how simple strategies, e.g., optimizing the
message generation rate of the safety applications, can significantly increase
the commercial opportunities of DSRC. Finally, we find that adaptive schemes
that can dynamically adjust the switching parameters in response to observed
traffic conditions may help in maximizing the commercial use of DSRC.
Performance evaluation of local features in human classification and detection S Paisitkriangkrai, J Zhang, IET COMPUTER VISION, Inst Engineering Technology-Iet, Hertford, 2008, pp. 236 - 246
Detecting pedestrians accurately is the first fundamental step for many computer vision applications such as video surveillance, smart vehicles, intersection traffic analysis and so on. The authors present an experimental study on pedestrian detection using state-of-the-art local feature extraction and support vector machine (SVM) classifiers. The performance of pedestrian detection using region covariance, histogram of oriented gradients ( HOG) and local receptive fields (LRF) feature descriptors is experimentally evaluated. The experiments are performed on the DaimlerChrysler benchmarking data set, the MIT CBCL data set and `Intitut National de Recherche en Informatique et Automatique (INRIA) data set. All can be publicly accessed. The experimental results show that region covariance features with radial basis function kernel SVM and HOG features with quadratic kernel SVM outperform the combination of LRF features with quadratic kernel SVM. Furthermore, the results reveal that both covariance and HOG features perform very well in the context of pedestrian detection.
Real-time pedestrian detection using a boosted multi-layer classifier (None HERDC) S Paisitkriangkrai, J Zhang, C Shen, 8th IEEE International Workshop on Visual Surveillance, in conjunction with European Confe, IEEE, 2008
Pedestrian detection plays an important role for many computer vision applications. In this paper, we propose a new simpler pedestrian detector using state-of-the-art locally extracted features, namely, covariance features. Unlike the work in \cite{Tuzel2007Human}, where the feature selection and weak classifier training are performed on the Riemannian manifold, we select features and train weak classifiers in the Euclidean space for faster computation. To this end, AdaBoost with weighted Fisher linear discriminant analysis based weak classifiers are designed. %A cascaded classifier structure is constructed for %efficiency in the detection phase. %To further accelerate the detection, we propose a novel %strategy---multiple layer boosting with heterogeneous features---to %exploit the efficiency of the Haar-like feature and the %discriminative power of the covariance feature simultaneously. Multiple layer boosting with heterogeneous features is constructed to exploit the efficiency of the Haar-like feature and the discriminative power of the covariance feature simultaneously. Extensive experiments show that by combining the Haar-like and covariance features, we speed up the original covariance feature detector \cite{Tuzel2007Human} by up to an order of magnitude in processing time without compromising the detection performance. For the first time, the proposed work made covariance feature based pedestrian detection work real time.
Robust object tracking using the particle filtering and level set methods: a comparative experiment C Luo, J Zhang, X Cai, 2008 IEEE 10th international workshop on multimedia signal processing, Proceedings, D. Feng, et al.. IEEE, Australia, 2008, pp. 359 - 364
Robust visual tracking has become an important topic of research in computer vision. A novel method for robust object tracking, namely GATE, improves object tracking in complex environments using the particle filtering and the level set-based active contour method. GATE creates a spatial prior in the state space using shape information of the tracked object to filter particles in the state space in order to reshape and refine the posterior distribution of the particle filtering. This paper describes a comparative experiment that applies GATE and the standard particle filtering to track the object of interest in complex environments using simple features. Image sequences captured by the hand held, stationary and the PTZ camera are utilised. The experimental results demonstrate that GATE is able to solve the ambiguous outlier problem of particle filters in order to deal with heavy clutters in the background, occlusion, low resolution and noisy images, and thus significantly improves the particle filtering in object tracking.
Sequential demand-driven evaluation of eager TransLucid G Ditu, B Mancilla, J Plaice, Proceedings - International Computer Software and Applications Conference, J. Bosch and J. Wong. Institute of Electrical and Electronics Engineers Computer Society, Piscataway, NJ 08855-1331, Unite, Piscataway, NJ 08855-1331, United States, 2008, pp. 1266 - 1271
Single-bit messages are insufficient for data link over duplicating channels K Engelhardt, Y Moses, Information Processing Letters 107(6), Elsevier B.V., Amsterdam, 2008, 235 - 239
Ideal communication channels in asynchronous systems are reliable, deliver messages in FIFO order, and do not deliver spurious or duplicate messages. A message vocabulary of size two (i.e., single-bit messages) suffices to encode and transmit messages of arbitrary finite length over such channels. This note proves that single-bit messages are insufficient once channels potentially deliver duplicate messages. In particular, it is shown that no protocol allows the sender to notify the receiver which of three values it holds, over a bidirectional, reliable, FIFO channel that may duplicate messages. This implies that messages must encode some additional control information, e.g., in the form of headers or tags.
Synchronous communities B Mancilla, J Plaice, Proceedings - International Computer Software and Applications Conference, Institute of Electrical and Electronics Engineers Computer Society, Piscataway, NJ 08855-1331, US, Piscataway, NJ, USA, 2008, pp. 1284 - 1287
