Distributed low-power image processing in wireless sensor networks for intelligent video surveillance applications

Distributed Wireless Smart Camera (DWSC) network is a special type of Wireless Sensor Network (WSN) that processes captured images in a distributed manner. While image processing on DWSCs sees a great potential for growth, with its applications possessing a vast practical application domain such as security surveillance and health care, it suffers from tremendous constraints. In addition to the limitations of conventional WSNs, image processing on DWSCs requires more computational power, bandwidth and energy that presents significant challenges for large scale deployments. This dissertation has developed a number of algorithms that are highly scalable, portable, energy efficient and performance efficient, with considerations of practical constraints imposed by the hardware and the nature of WSN. More specifically, these algorithms tackle the problems of multi-object tracking and localisation in distributed wireless smart camera net- works and optimal camera configuration determination. Addressing the first problem of multi-object tracking and localisation requires solving a large array of sub-problems. The sub-problems that are discussed in this dissertation are calibration of internal parameters, multi-camera calibration for localisation and object handover for tracking. These topics have been covered extensively in computer vision literatures, however new algorithms must be invented to accommodate the various constraints introduced and required by the DWSC platform. A technique has been developed for the automatic calibration of low-cost cameras which are assumed to be restricted in their freedom of movement to either pan or tilt movements. Camera internal parameters, including focal length, principal point, lens distortion parameter and the angle and axis of rotation, can be recovered from a minimum set of two images of the camera, provided that the axis of rotation between the two images goes through the camera's optical centre and is parallel to either the vertical (panning) or horizontal (tilting) axis of the image. For object localisation, a novel approach has been developed for the calibration of a network of non-overlapping DWSCs in terms of their ground plane homographies, which can then be used for localising objects. In the proposed approach, a robot travels through the camera network while updating its position in a global coordinate frame, which it broadcasts to the cameras. The cameras use this, along with the image plane location of the robot, to compute a mapping from their image planes to the global coordinate frame. This is combined with an occupancy map generated by the robot during the mapping process to localised objects moving within the network. In addition, to deal with the problem of object handover between DWSCs of non-overlapping fields of view, a highly-scalable, distributed protocol has been designed. Cameras that follow the proposed protocol transmit object descriptions to a selected set of neighbours that are determined using a predictive forwarding strategy. The received descriptions are then matched at the subsequent camera on the object's path using a probability maximisation process with locally generated descriptions. The second problem of camera placement emerges naturally when these pervasive devices are put into real use. The locations, orientations, lens types etc. of the cameras must be chosen in a way that the utility of the network is maximised (e.g. maximum coverage) while user requirements are met. To deal with this, a statistical formulation of the problem of determining optimal camera configurations has been introduced and a Trans-Dimensional Simulated Annealing (TDSA) algorithm has been proposed to effectively solve the problem.

Optimal camera planning under versatile user constraints in multi-camera image processing systems

The selection of optimal camera configurations (camera locations, orientations, etc.) for multi-camera networks remains an unsolved problem. Previous approaches largely focus on proposing various objective functions to achieve different tasks. Most of them, however, do not generalize well to large scale networks. To tackle this, we propose a statistical framework of the problem as well as propose a trans-dimensional simulated annealing algorithm to effectively deal with it. We compare our approach with a state-of-the-art method based on binary integer programming (BIP) and show that our approach offers similar performance on small scale problems. However, we also demonstrate the capability of our approach in dealing with large scale problems and show that our approach produces better results than two alternative heuristics designed to deal with the scalability issue of BIP. Last, we show the versatility of our approach using a number of specific scenarios.

Multi-shot person re-identification via relational stein divergence

Person re-identification is particularly challenging due to significant appearance changes across separate camera views. In order to re-identify people, a representative human signature should effectively handle differences in illumination, pose and camera parameters. While general appearance-based methods are modelled in Euclidean spaces, it has been argued that some applications in image and video analysis are better modelled via non-Euclidean manifold geometry. To this end, recent approaches represent images as covariance matrices, and interpret such matrices as points on Riemannian manifolds. As direct classification on such manifolds can be difficult, in this paper we propose to represent each manifold point as a vector of similarities to class representers, via a recently introduced form of Bregman matrix divergence known as the Stein divergence. This is followed by using a discriminative mapping of similarity vectors for final classification. The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately. Comparative evaluations on benchmark ETHZ and iLIDS datasets for the person re-identification task show that the proposed approach obtains better performance than recent techniques such as Histogram Plus Epitome, Partial Least Squares, and Symmetry-Driven Accumulation of Local Features.

Multi-site genetic analysis of diffusion images and voxelwise heritability analysis: A pilot project of the ENIGMA-DTI working group

The ENIGMA (Enhancing NeuroImaging Genetics through Meta-Analysis) Consortium was set up to analyze brain measures and genotypes from multiple sites across the world to improve the power to detect genetic variants that influence the brain. Diffusion tensor imaging (DTI) yields quantitative measures sensitive to brain development and degeneration, and some common genetic variants may be associated with white matter integrity or connectivity. DTI measures, such as the fractional anisotropy (FA) of water diffusion, may be useful for identifying genetic variants that influence brain microstructure. However, genome-wide association studies (GWAS) require large populations to obtain sufficient power to detect and replicate significant effects, motivating a multi-site consortium effort. As part of an ENIGMA-DTI working group, we analyzed high-resolution FA images from multiple imaging sites across North America, Australia, and Europe, to address the challenge of harmonizing imaging data collected at multiple sites. Four hundred images of healthy adults aged 18-85 from four sites were used to create a template and corresponding skeletonized FA image as a common reference space. Using twin and pedigree samples of different ethnicities, we used our common template to evaluate the heritability of tract-derived FA measures. We show that our template is reliable for integrating multiple datasets by combining results through meta-analysis and unifying the data through exploratory mega-analyses. Our results may help prioritize regions of the FA map that are consistently influenced by additive genetic factors for future genetic discovery studies. Protocols and templates are publicly available at (http://enigma.loni.ucla.edu/ongoing/dti-working-group/).

Learning Nonlinear Visual Processing from Natural Images

The paradigm of computational vision hypothesizes that any visual function -- such as the recognition of your grandparent -- can be replicated by computational processing of the visual input. What are these computations that the brain performs? What should or could they be? Working on the latter question, this dissertation takes the statistical approach, where the suitable computations are attempted to be learned from the natural visual data itself. In particular, we empirically study the computational processing that emerges from the statistical properties of the visual world and the constraints and objectives specified for the learning process. This thesis consists of an introduction and 7 peer-reviewed publications, where the purpose of the introduction is to illustrate the area of study to a reader who is not familiar with computational vision research. In the scope of the introduction, we will briefly overview the primary challenges to visual processing, as well as recall some of the current opinions on visual processing in the early visual systems of animals. Next, we describe the methodology we have used in our research, and discuss the presented results. We have included some additional remarks, speculations and conclusions to this discussion that were not featured in the original publications. We present the following results in the publications of this thesis. First, we empirically demonstrate that luminance and contrast are strongly dependent in natural images, contradicting previous theories suggesting that luminance and contrast were processed separately in natural systems due to their independence in the visual data. Second, we show that simple cell -like receptive fields of the primary visual cortex can be learned in the nonlinear contrast domain by maximization of independence. Further, we provide first-time reports of the emergence of conjunctive (corner-detecting) and subtractive (opponent orientation) processing due to nonlinear projection pursuit with simple objective functions related to sparseness and response energy optimization. Then, we show that attempting to extract independent components of nonlinear histogram statistics of a biologically plausible representation leads to projection directions that appear to differentiate between visual contexts. Such processing might be applicable for priming, \ie the selection and tuning of later visual processing. We continue by showing that a different kind of thresholded low-frequency priming can be learned and used to make object detection faster with little loss in accuracy. Finally, we show that in a computational object detection setting, nonlinearly gain-controlled visual features of medium complexity can be acquired sequentially as images are encountered and discarded. We present two online algorithms to perform this feature selection, and propose the idea that for artificial systems, some processing mechanisms could be selectable from the environment without optimizing the mechanisms themselves. In summary, this thesis explores learning visual processing on several levels. The learning can be understood as interplay of input data, model structures, learning objectives, and estimation algorithms. The presented work adds to the growing body of evidence showing that statistical methods can be used to acquire intuitively meaningful visual processing mechanisms. The work also presents some predictions and ideas regarding biological visual processing.

Comparison of 10 Multi-Sensor Image Fusion Paradigms for IKONOS Images

Fusion of multi-sensor imaging data enables a synergetic interpretation of complementary information obtained by sensors of different spectral ranges. Multi-sensor data of diverse spectral, spatial and temporal resolutions require advanced numerical techniques for analysis and interpretation. This paper reviews ten advanced pixel based image fusion techniques – Component substitution (COS), Local mean and variance matching, Modified IHS (Intensity Hue Saturation), Fast Fourier Transformed-enhanced IHS, Laplacian Pyramid, Local regression, Smoothing filter (SF), Sparkle, SVHC and Synthetic Variable Ratio. The above techniques were tested on IKONOS data (Panchromatic band at 1 m spatial resolution and Multispectral 4 bands at 4 m spatial resolution). Evaluation of the fused results through various accuracy measures, revealed that SF and COS methods produce images closest to corresponding multi-sensor would observe at the highest resolution level (1 m).

MAST: multi-script annotation toolkit for scenic text

This paper describes a semi-automatic tool for annotation of multi-script text from natural scene images. To our knowledge, this is the maiden tool that deals with multi-script text or arbitrary orientation. The procedure involves manual seed selection followed by a region growing process to segment each word present in the image. The threshold for region growing can be varied by the user so as to ensure pixel-accurate character segmentation. The text present in the image is tagged word-by-word. A virtual keyboard interface has also been designed for entering the ground truth in ten Indic scripts, besides English. The keyboard interface can easily be generated for any script, thereby expanding the scope of the toolkit. Optionally, each segmented word can further be labeled into its constituent characters/symbols. Polygonal masks are used to split or merge the segmented words into valid characters/symbols. The ground truth is represented by a pixel-level segmented image and a '.txt' file that contains information about the number of words in the image, word bounding boxes, script and ground truth Unicode. The toolkit, developed using MATLAB, can be used to generate ground truth and annotation for any generic document image. Thus, it is useful for researchers in the document image processing community for evaluating the performance of document analysis and recognition techniques. The multi-script annotation toolokit (MAST) is available for free download.

Multi-script and multi-oriented text localization from scene images

This paper describes a new method of color text localization from generic scene images containing text of different scripts and with arbitrary orientations. A representative set of colors is first identified using the edge information to initiate an unsupervised clustering algorithm. Text components are identified from each color layer using a combination of a support vector machine and a neural network classifier trained on a set of low-level features derived from the geometric, boundary, stroke and gradient information. Experiments on camera-captured images that contain variable fonts, size, color, irregular layout, non-uniform illumination and multiple scripts illustrate the robustness of the method. The proposed method yields precision and recall of 0.8 and 0.86 respectively on a database of 100 images. The method is also compared with others in the literature using the ICDAR 2003 robust reading competition dataset.

High-Temperature Deformation Processing Map Approach for Obtaining the Desired Microstructure in a Multi-component (Ni-Ti-Cu-Fe) Alloy

An equiatomic NiTiCuFe multi-component alloy with simple body-centered cubic (bcc) and face-centered cubic solid-solution phases in the microstructure was processed by vacuum induction melting furnace under dynamic Ar atmosphere. High-temperature uniaxial compression experiments were conducted on it in the temperature range of 1073 K to 1303 K (800 degrees C to 1030 degrees C) and strain rate range of 10(-3) to 10(-1) s(-1). The data generated were analyzed with the aid of the dynamic materials model through which power dissipation efficiency and instability maps were generated so as to identify the governing deformation mechanisms that are operative in different temperature-strain rate regimes with the aid of complementary microstructural analysis of the deformed specimens. Results indicate that the stable domain for the high temperature deformation of the multi-component alloy occurs in the temperature range of 1173 K to 1303 K (900 degrees C to 1030 degrees C) and (epsilon) over dot range of 10(-3) to 10(-1.2) s(-1), and the deformation is unstable at T = 1073 K to 1153 K (800 degrees C to 880 degrees C) and (epsilon) over dot = 10(-3) to 10(-1.4) s(-1) as well as T = 1223 K to 1293 K (950 degrees C to 1020 degrees C) and (epsilon) over dot = 10(-1.4) to 10(-1) s(-1), with adiabatic shear banding, localized plastic flow, or cracking being the unstable mechanisms. A constitutive equation that describes the flow stress of NiTiCuFe multi-component alloy as a function of strain rate and deformation temperature was also determined. (C) The Minerals, Metals & Materials Society and ASM International 2015

Digitized Processing Track Generation of a Computer Integrated Multi-Functional 5-Axis Laser Processing System

Based on the computer integrated and flexible laser processing system, an intelligent measuring sub-system was developed. A novel model has been built up to compensate the deviations of the main frame-structure, and a new 3-D laser tracker system is applied to adjust the accuracy of the system. To analyze the characteristic of all kind surfaces of automobile outer penal moulds and dies, classification of types of the surface、brim and ridge(or vale) area to be measured and processed has been established, resulting in one of the main processing functions of the laser processing system. According to different type of surfaces, a 2-D adaptive measuring method based on B?zier curve was developed; furthermore a 3-D adaptive measuring method based on Spline curve was also developed. According to the laser materials processing characteristics and data characteristics, necessary methods have been developed to generate processing tracks, they are explained in details. Measuring experiments and laser processing experiments were carried out to testify the above mentioned methods, which have been applied in the computer integrated and flexible laser processing system developed by the Institute of Mechanics, CAS.

MCBoost: Multiple classifier boosting for perceptual co-clustering of images and visual features

We present a new co-clustering problem of images and visual features. The problem involves a set of non-object images in addition to a set of object images and features to be co-clustered. Co-clustering is performed in a way that maximises discrimination of object images from non-object images, thus emphasizing discriminative features. This provides a way of obtaining perceptual joint-clusters of object images and features. We tackle the problem by simultaneously boosting multiple strong classifiers which compete for images by their expertise. Each boosting classifier is an aggregation of weak-learners, i.e. simple visual features. The obtained classifiers are useful for object detection tasks which exhibit multimodalities, e.g. multi-category and multi-view object detection tasks. Experiments on a set of pedestrian images and a face data set demonstrate that the method yields intuitive image clusters with associated features and is much superior to conventional boosting classifiers in object detection tasks.