Current Issue : October - December Volume : 2014 Issue Number : 4 Articles : 5 Articles
In visual surveillance of both humans and vehicles, a video stream is processed to characterize the events of\ninterest through the detection of moving objects in each frame. The majority of errors in higher-level tasks such as\ntracking are often due to false detection. In this paper, a novel method is introduced for the detection of moving\nobjects in surveillance applications which combines adaptive filtering technique with the Bayesian change detection\nalgorithm. In proposed method, an adaptive structure firstly detects the edges of motion objects. Then, Bayesian\nalgorithm corrects the shape of detected objects. The proposed method exhibits considerable robustness against\nnoise, shadows, illumination changes, and repeated motions in the background compared to earlier works. In the\nproposed algorithm, no prior information about foreground and background is required and the motion detection is\nperformed in an adaptive scheme. Besides, it is shown that the proposed algorithm is computationally efficient so that\nit can be easily implemented for online surveillance systems as well as similar applications....
Polynomial texture mapping (PTM) uses simple polynomial regression to interpolate and re-light image sets taken\nfrom a fixed camera but under different illumination directions. PTM is an extension of the classical photometric\nstereo (PST), replacing the simple Lambertian model employed by the latter with a polynomial one. The advantage\nand hence wide use of PTM is that it provides some effectiveness in interpolating appearance including more\ncomplex phenomena such as interreflections, specularities and shadowing. In addition, PTM provides estimates of\nsurface properties, i.e., chromaticity, albedo and surface normals. The most accurate model to date utilizes multivariate\nLeast Median of Squares (LMS) robust regression to generate a basic matte model, followed by radial basis function\n(RBF) interpolation to give accurate interpolants of appearance. However, robust multivariate modelling is slow. Here\nwe show that the robust regression can find acceptably accurate inlier sets using a much less burdensome 1D LMS\nrobust regression (or ââ?¬Ë?mode-finderââ?¬â?¢). We also show that one can produce good quality appearance interpolants, plus\naccurate surface properties using PTM before the additional RBF stage, provided one increases the dimensionality\nbeyond 6D and still uses robust regression. Moreover, we model luminance and chromaticity separately, with\ndimensions 16 and 9 respectively. It is this separation of colour channels that allows us to maintain a relatively low\ndimensionality for the modelling. Another observation we show here is that in contrast to current thinking, using the\noriginal idea of polynomial terms in the lighting direction outperforms the use of hemispherical harmonics (HSH) for\nmatte appearance modelling. For the RBF stage, we use Tikhonov regularization, which makes a substantial difference\nin performance. The radial functions used here are Gaussians; however, to date the Gaussian dispersion width and the\nvalue of the Tikhonov parameter have been fixed. Here we show that one can extend a theorem from graphics that\ngenerates a very fast error measure for an otherwise difficult leave-one-out error analysis. Using our extension of the\ntheorem, we can optimize on both the Gaussian width and the Tikhonov parameter....
Several methods have been proposed to describe face images in order to recognize them automatically. Local\nmethods based on spatial histograms of local patterns (or operators) are among the best-performing ones. In this\npaper, a new method that allows to obtain more robust histograms of local patterns by using a more discriminative\nspatial division strategy is proposed. Spatial histograms are obtained from regions clustered according to the\nsemantic pixel relations, making better use of the spatial information. Here, a simple rule is used, in which pixels in an\nimage patch are clustered by sorting their intensity values. By exploring the information entropy on image patches,\nthe number of sets on each of them is learned. Besides, Principal Component Analysis with a Whitening process is\napplied for the final feature vector dimension reduction, making the representation more compact and discriminative.\nThe proposed division strategy is invariant to monotonic grayscale changes, and shows to be particularly useful when\nthere are large expression variations on the faces. The method is evaluated on three widely used face recognition\ndatabases: AR, FERET and LFW, with the very popular LBP operator and some of its extensions. Experimental results\nshow that the proposal not only outperforms those methods that use the same local patterns with the traditional\ndivision, but also some of the best-performing state-of-the-art methods....
Stress is a serious concern facing our world today, motivating the development of a better objective understanding\nthrough the use of non-intrusive means for stress recognition by reducing restrictions to natural human behavior.\nAs an initial step in computer vision-based stress detection, this paper proposes a temporal thermal spectrum (TS)\nand visible spectrum (VS) video database ANUStressDB - a major contribution to stress research. The database\ncontains videos of 35 subjects watching stressed and not-stressed film clips validated by the subjects. We present\nthe experiment and the process conducted to acquire videos of subjects' faces while they watched the films for\nthe ANUStressDB. Further, a baseline model based on computing local binary patterns on three orthogonal planes\n(LBP-TOP) descriptor on VS and TS videos for stress detection is presented. A LBP-TOP-inspired descriptor was used\nto capture dynamic thermal patterns in histograms (HDTP) which exploited spatio-temporal characteristics in TS\nvideos. Support vector machines were used for our stress detection model. A genetic algorithm was used to select\nsalient facial block divisions for stress classification and to determine whether certain regions of the face of subjects\nshowed better stress patterns. Results showed that a fusion of facial patterns from VS and TS videos produced\nstatistically significantly better stress recognition rates than patterns from VS or TS videos used in isolation.\nMoreover, the genetic algorithm selection method led to statistically significantly better stress detection rates than\nclassifiers that used all the facial block divisions. In addition, the best stress recognition rate was obtained from\nHDTP features fused with LBP-TOP features for TS and VS videos using a hybrid of a genetic algorithm and a\nsupport vector machine stress detection model. The model produced an accuracy of 86%....
Video surveillance has significant application prospects such as security, law enforcement, and traffic monitoring.\nVisual traffic surveillance using computer vision techniques can be non-invasive, cost effective, and automated.\nDetecting and recognizing the objects in a video is an important part of many video surveillance systems which\ncan help in tracking of the detected objects and gathering important information. In case of traffic video surveillance,\nvehicle detection and classification is important as it can help in traffic control and gathering of traffic statistics that\ncan be used in intelligent transportation systems. Vehicle classification poses a difficult problem as vehicles have\nhigh intra-class variation and relatively low inter-class variation. In this work, we investigate five different object\nrecognition techniques: PCA + DFVS, PCA + DIVS, PCA + SVM, LDA, and constellation-based modeling applied to the\nproblem of vehicle classification. We also compare them with the state-of-the-art techniques in vehicle classification. In\ncase of the PCA-based approaches, we extend face detection using a PCA approach for the problem of vehicle\nclassification to carry out multi-class classification. We also implement constellation model-based approach that\nuses the dense representation of scale-invariant feature transform (SIFT) features as presented in the work of Ma\nand Grimson (Edge-based rich representation for vehicle classification. Paper presented at the international conference\non computer vision, 2006, pp. 1185ââ?¬â??1192) with slight modification. We consider three classes: sedans, vans, and taxis,\nand record classification accuracy as high as 99.25% in case of cars vs vans and 97.57% in case of sedans vs taxis. We\nalso present a fusion approach that uses both PCA + DFVS and PCA + DIVS and achieves a classification accuracy of\n96.42% in case of sedans vs vans vs taxis....
Loading....