Hierarchical Adaptive KL-Based Transform: Algorithms and Applications

For several signal processing applications, the usefulness of Fast Unitary Transforms (FUT) is now well recognized [1-7]. For signal representation, filtering and encoding, it is well known that the Karhunen-Loeve (KL) Transform, based on signal statistics, is optimum in various senses, but the KL Transform is slow. Suboptimum FUT's allow a trade-off between performance and speed. In this paper, we compare and rank the KL, Fourier, Walsh-Hadamard, Haar, Discrete Cosine, Slant Walsh Hadamard and Slant Haar Transforms by their performance in applications and by the number of elementary operations they require. In encoding and filtering, recursive techniques are widely used and are generally fast. By considering both performance and computations we are able to compare directly recursive and transform algorithms. The comparison brings to light a performance versus computation bound for the two classes of processing techniques.

One factor of human sperm health is sperm motility. Motility is the ability of sperm to move. Sperm with healthy motility move forward promptly, not inactive and not moving in circles. In this paper, we would like to analyse sperm motility by considering the problem of multi object tracking in video sequences of human sperms. The challenges in multi-sperm tracking are many human sperms have fast and unpredictable movement In addition, the sperm have similar size and shape comparing by each others. To solve this problem, we used sperm detection in each video sequence to get the position of sperms. In the same time, the estimated sperm position is calculated based on previous tracking by using Kalman Filter. Finally the positions of detected sperms are compared to estimation results by using Hungarian assignment method. In this way, the trajectory of each sperm can be conclude. This paper analyze sperm motility qualitatively based on the resulted sperm trajectories. The experiment results were conducted on both open video data and our own low-frame-rate video data. The experiment results shows that the proposed method can handle the challenges in multi sperm tracking, create their trajectory and then analyze their behaviors.

Object tracking in video sequences has broad applications in both military and civilian domains. However, as the length of input video sequence increases, a number of problems arise, such as severe object occlusion, object appearance variation, and object out-of-view (some portion or the entire object leaves the image space). To deal with these problems and identify the object being tracked from cluttered background, we present a robust appearance model using Speeded Up Robust Features (SURF) and advanced integrated features consisting of the Felzenszwalb's Histogram of Oriented Gradients (FHOG) and color attributes. Since re-detection is essential in long-term tracking, we develop an effective object re-detection strategy based on moving area detection. We employ the popular kernel correlation filters in our algorithm design, which facilitates high-speed object tracking. Our evaluation using the CVPR2013 Object Tracking Benchmark (OTB2013) dataset illustrates that the proposed algorithm outperforms reference state-of-the-art trackers in various challenging scenarios.

Moving object tracking in video sequences is an important task in the field of computer vision. In this paper, we propose a new population-based algorithm namely simplified swarm optimization (SSO) for tracking arbitrary objects. In SSO, the object model is first projected into a high-dimensional feature space, then the particles will fly over image pixels to find an optimal match of the target. While searching for the optimum, SSO progressively analyzes the occlusion situation. If any occlusion or disappearance of the target object is detected, the movement rules for the searching particles will be adaptively adjusted to recapture the target object. Experimental results showed that the SSO can robustly track an arbitrary target in various challenging conditions. Furthermore, SSO is capable to have 40% faster in speed and 36% higher in accuracy rate than the traditional PSO for varied environment.

This paper presents efficient object tracking in video sequences using multiple features by embedding mean shift into particle filters. When clutter background and occlusions are present. Particle filtering is used because it is very robust and performs well for non-linear and non-Gaussian dynamic state estimation problems. The image features, such as shape, texture, color, contours, and random motion appearance can be used to track the moving object(s) in videos. We proposed a smart video surveillance system with real-time as well as offline stored video database for moving object detection, classification and tracking capabilities. The graphical user interface of the proposed system using MATLAB 2012b is implemented that operates on both color and gray scale video images from a stationary camera. In this method, we proposed real time moving object detection and tracking system using static webcam that can processes 800*600, 640*480, and 320*240 resolution video sequences for capturing live scene as well as stored database of segmented videos. Issues related with object detection and tracking is jointly employed using mean shift and particle filters. Tracker will estimate the dynamic shape and random appearance of objects. Tracking requires location and shape of object in every segmented frame. Rectangular bounding box is used to improve the estimate of its shape and appearance. Target object may experience partial occlusions, intersection with other objects with similar color distributions, abrupt motion speed changes, and cluttered background. Test result shows improvement in terms of robustness, tracking drifts, accuracy of tracked bounding box to occlusions.

Particle filter (PF) is a method dedicated to posterior density estimations using weighted samples whose elements are called particles. In particular, this approach can be applied to object tracking in video sequences in complex situations and, in this paper, we focus on articulated object tracking, i.e., objects that can be decomposed as a set of subparts. One of PF's crucial step is a resampling step in which particles are resampled to avoid degeneracy problems. In this paper, we propose to exploit mathematical properties of articulated objects to swap conditionally independent subparts of the particles in order to generate new particle sets. We then introduce a new resampling method called Combinatorial Resampling that resamples over the particle set resulting from all the "admissible" swappings, the so-called combinatorial set. In essence, combinatorial resampling (CR) is quite similar to the combination of a crossover operator and a usual resampling, but there exists a fundamental difference between CR and the use of crossover operators: we prove that CR is sound, i.e., in a Bayesian framework, it is guaranteed to represent without any bias the posterior densities of the states over time. By construction, the particle sets produced by CR better represent the density to estimate over the whole state space than the original set and, therefore, CR produces higher quality samples. Unfortunately, the combinatorial set is generally of an exponential size and, therefore, to be scalable, we show how it can be implicitly constructed and resampled from, thus resulting in both an efficient and effective resampling scheme. Finally, through experimentations both on challenging synthetic and real video sequences, we also show that our resampling method outperforms all classical resampling methods both in terms of the quality of its results and in terms of computation times.

Two challenge problems in tracking objects in video are object segmentation and matching. Most previous methods can work with some user-specific control. In this paper, we will propose an adaptive algorithm for colour object tracking in video sequences based on background subtraction and image matching by using multiresolution critical point filter (CPFs). Which the background subtraction segment the blob and identify all the objects in the image no matter what they are moving or not. Using results from segmentation phase, object tracking is performed using the multiresolution critical point filter algorithm. This is based on research from prof. Shinagawa's image interpolation. For now, our approach is suitable for tracking of the object through a sequence of 64*64 images.

Moving object tracking is a tricky job in computer vision problems. In this approach, the object tracking system relies on the deterministic search of target, whose color content matches a reference histogram model. A simple RGB histogram-based color model is used to develop our observation system. Secondly and finally, we describe a new approach for moving object tracking with particle filter by shape information. Particle filtering has been proven very successful for non-Gaussian and non-linear estimation problems. In this approach we combine between particle filter and the probability product kernels as a similarity measure using integral image to compute the histograms of all possible target regions of object tracking in video sequence. The shape similarity between a target and estimated regions in the video sequence is measured by their normalized histogram. Target of object tracking is created instantly by selecting an object from the video sequence by a rectangle. Experimental results have been presented to show the effectiveness of our proposed system.

Aiming at improving the performance of non-rigid object tracking in video sequences acquired by a stationary camera, an effective method based on the adaptive color segmentation and object part model was presented. In this work, we modeled background and obtained the foreground blobs with an effective adaptive background updating method based on Gaussian mixture model (GMM), and then the regions in part model were generated online by the color segmentation based on region-growth. The region features and constraints between regions were taken into account and used to perform object tracking effectively and flexibly even under object partial occlusion and deformation. Experimental results with different real-world scenarios demonstrate validity and robust of our solution.

Convergence analysis of active contours

Parametric active contours, also called snakes, are a particular case of deformable models embebed in the image plane. The mathematical principles under their formulation represent the confluence of Geometry, Physics and Approximation Theory. Since their debut in 1978, their usefulness has been proven in medical image analysis, image segmentation, object tracking in video sequences, etc.

Approximation of the Karhunen–Loève transformation and its application to colour images

The main objective of developing the image watermarking technique is satisfying the robustness and the imperceptibility of multimedia protection. To achieve this objective, a novel hybrid image watermarking scheme based on Karhunen Loeve transform (KLT) and discrete hartley transform (DHT) and is proposed. In the proposed scheme (KL---DHT based watermarking scheme), the original image is divided into blocks using spiral scan, then the DHT is calculated for each block, after that, the KLT is applied for each DHT block. The watermark embedding process is carried out during the KLT transformation process. In the watermark extracting process, the watermarked image is distorted using several image attacks such as JPEG image compression, image rotation, image resizing, adding noise (Gaussian, impulsive or speckle) or image contrast adjustment using adaptive histogram equalization. Furthermore, the proposed scheme is carried out using block by block image scan and the achieved results are compared with those obtained from other watermarking schemes such as discrete cosine transform/singular value decomposition (DCT---SVD) based watermarking scheme, discrete wavelet transform/SVD (DWT---SVD) based watermarking scheme and SVD watermarking in the homomorphic domain watermarking scheme. The achieved results proved that, the superiority of the KL---DHT based watermarking scheme with spiral scan compared to other watermarking schemes in the presence of different image attacks.

In block-based video coding, the Discrete Cosine Transform (DCT) has been adopted for signal decorrelation in state-of-the-art standards. Although the Karhunen Loeve Transform (KLT) is known to achieve optimal energy compaction, it has been reported to offer only moderate compression as the KLT basis functions are source dependent and hence require the transform itself to be coded. This paper describes a technique for prediction-error block coding using the KLT. The proposed method does not require coding of the KLT bases. Instead the basis functions can be derived at the decoder in a manner similar to the encoder. The proposed method is incorporated into a standard H.264 video codec using an adaptive transform selection approach. Our experiments show that the Peak Signal-to-Noise Ratio (PSNR) improvement of up to 0.9 dB is achieved with the proposed technique when compared with the standard H.264 codec.

Seismic reflection data are used by geologists to identify the best site for oil and gas explorations. The raw seismic image cannot be directly used for explorations because the noises may hinder the primary reflections and result in misinterpretations. In the proposed research work, the denoising method with adaptive dictionary learning is attempted to attenuate the coherent and random noises which affect the seismic reflections. In this method, Karhunen Loeve Transform (KLT) is combined with K-means Singular Value Decomposition (KSVD) to improve the Signal to Noise Ratio (SNR) of the seismic data. The combination of fixed transform using KLT and learning-based dictionary using KSVD remove the redundant data while retaining the necessary data for further interpretations. KLT is applied on the whole seismic image to decorrelate the coefficients and retain the primary reflections. The horizontal events in the seismic image are preserved as they represent the eigen images with large energy. The KSVD is applied to the KLT resultant data, which denoises the patch of data while simultaneously updating the dictionary. The noise is eliminated using local sparsity of the image where mutually overlapping small image blocks are learned to yield the self-adaptive redundant dictionary. It is then used to obtain the sparse representation of the image blocks by eliminating noise. The algorithm is tested for both synthetic and field seismic images, and the results indicate a better reduction of random and coherent noise with the acceptable execution time compared to other denoising algorithms used. The KLT combined with KSVD method decorrelate the seismic data from noise by preserving the primary reflections and discarding the redundant noise.