Instantaneous threat detection based on a semantic representation of activities, zones and trajectories

Threat detection is a challenging problem, because threats appear in many variations and differences to normal behaviour can be very subtle. In this paper, we consider threats on a parking lot, where theft of a truck’s cargo occurs. The threats range from explicit, e.g. a person attacking the truck driver, to implicit, e.g. somebody loitering and then fiddling with the exterior of the truck in order to open it. Our goal is a system that is able to recognize a threat instantaneously as they develop. Typical observables of the threats are a person’s activity, presence in a particular zone and the trajectory. The novelty of this paper is an encoding of these threat observables in a semantic, intermediate-level representation, based on low-level visual features that have no intrinsic semantic meaning themselves. The aim of this representation was to bridge the semantic gap between the low-level tracks and motion and the higher-level notion of threats. In our experiments, we demonstrate that our semantic representation is more descriptive for threat detection than directly using low-level features. We find that a person’s activities are the most important elements of this semantic representation, followed by the person’s trajectory. The proposed threat detection system is very accurate: 96.6 % of the tracks are correctly interpreted, when considering the temporal context.

A Road Following Approach Using Artificial Neural Networks Combinations

Navigation is a broad topic that has been receiving considerable attention from the mobile robotic community over the years. In order to execute autonomous driving in outdoor urban environments it is necessary to identify parts of the terrain that can be traversed and parts that should be avoided. This paper describes an analyses of terrain identification based on different visual information using a MLP artificial neural network and combining responses of many classifiers. Experimental tests using a vehicle and a video camera have been conducted in real scenarios to evaluate the proposed approach.

Chaotic phase synchronization and desynchronization in an oscillator network for object selection

Object selection refers to the mechanism of extracting objects of interest while ignoring other objects and background in a given visual scene. It is a fundamental issue for many computer vision and image analysis techniques and it is still a challenging task to artificial Visual systems. Chaotic phase synchronization takes place in cases involving almost identical dynamical systems and it means that the phase difference between the systems is kept bounded over the time, while their amplitudes remain chaotic and may be uncorrelated. Instead of complete synchronization, phase synchronization is believed to be a mechanism for neural integration in brain. In this paper, an object selection model is proposed. Oscillators in the network representing the salient object in a given scene are phase synchronized, while no phase synchronization occurs for background objects. In this way, the salient object can be extracted. In this model, a shift mechanism is also introduced to change attention from one object to another. Computer simulations show that the model produces some results similar to those observed in natural vision systems.

Texture analysis and classification using deterministic tourist walk

In this paper, we present a study on a deterministic partially self-avoiding walk (tourist walk), which provides a novel method for texture feature extraction. The method is able to explore an image on all scales simultaneously. Experiments were conducted using different dynamics concerning the tourist walk. A new strategy, based on histograms. to extract information from its joint probability distribution is presented. The promising results are discussed and compared to the best-known methods for texture description reported in the literature. (C) 2009 Elsevier Ltd. All rights reserved.

A novel MAP-MRF approach for multispectral image contextual classification using combination of suboptimal iterative algorithms

In this paper we present a novel approach for multispectral image contextual classification by combining iterative combinatorial optimization algorithms. The pixel-wise decision rule is defined using a Bayesian approach to combine two MRF models: a Gaussian Markov Random Field (GMRF) for the observations (likelihood) and a Potts model for the a priori knowledge, to regularize the solution in the presence of noisy data. Hence, the classification problem is stated according to a Maximum a Posteriori (MAP) framework. In order to approximate the MAP solution we apply several combinatorial optimization methods using multiple simultaneous initializations, making the solution less sensitive to the initial conditions and reducing both computational cost and time in comparison to Simulated Annealing, often unfeasible in many real image processing applications. Markov Random Field model parameters are estimated by Maximum Pseudo-Likelihood (MPL) approach, avoiding manual adjustments in the choice of the regularization parameters. Asymptotic evaluations assess the accuracy of the proposed parameter estimation procedure. To test and evaluate the proposed classification method, we adopt metrics for quantitative performance assessment (Cohen`s Kappa coefficient), allowing a robust and accurate statistical analysis. The obtained results clearly show that combining sub-optimal contextual algorithms significantly improves the classification performance, indicating the effectiveness of the proposed methodology. (C) 2010 Elsevier B.V. All rights reserved.

Improved voice activity detection algorithm using wavelet and support vector machine

This paper proposes an improved voice activity detection (VAD) algorithm using wavelet and support vector machine (SVM) for European Telecommunication Standards Institution (ETS1) adaptive multi-rate (AMR) narrow-band (NB) and wide-band (WB) speech codecs. First, based on the wavelet transform, the original IIR filter bank and pitch/tone detector are implemented, respectively, via the wavelet filter bank and the wavelet-based pitch/tone detection algorithm. The wavelet filter bank can divide input speech signal into several frequency bands so that the signal power level at each sub-band can be calculated. In addition, the background noise level can be estimated in each sub-band by using the wavelet de-noising method. The wavelet filter bank is also derived to detect correlated complex signals like music. Then the proposed algorithm can apply SVM to train an optimized non-linear VAD decision rule involving the sub-band power, noise level, pitch period, tone flag, and complex signals warning flag of input speech signals. By the use of the trained SVM, the proposed VAD algorithm can produce more accurate detection results. Various experimental results carried out from the Aurora speech database with different noise conditions show that the proposed algorithm gives considerable VAD performances superior to the AMR-NB VAD Options 1 and 2, and AMR-WB VAD. (C) 2009 Elsevier Ltd. All rights reserved.

An Information Theory framework for two-stage binary image operator design

The design of translation invariant and locally defined binary image operators over large windows is made difficult by decreased statistical precision and increased training time. We present a complete framework for the application of stacked design, a recently proposed technique to create two-stage operators that circumvents that difficulty. We propose a novel algorithm, based on Information Theory, to find groups of pixels that should be used together to predict the Output Value. We employ this algorithm to automate the process of creating a set of first-level operators that are later combined in a global operator. We also propose a principled way to guide this combination, by using feature selection and model comparison. Experimental results Show that the proposed framework leads to better results than single stage design. (C) 2009 Elsevier B.V. All rights reserved.

Extended depth from focus reconstruction using NIH ImageJ plugins: Quality and resolution of elevation maps

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Reducing the gap between mobile and intelligent software agents

This paper presents an approach to integrate an artificial intelligence (AI) technique, concretely rule-based processing, into mobile agents. In particular, it focuses on the aspects of designing and implementing an appropriate inference engine of small size to reduce migration costs. The main goal is combine two lines of agent research, First, the engineering oriented approach on mobile agent architectures, and, second, the AI related approach on inference engines driven by rules expressed in a restricted subset of first-order predicate logic (FOPL). In addition to size reduction, the main functions of this type of engine were isolated, generalized and implemented as dynamic components, making possible not only their migration with the agent, but also their dynamic migration and loading on demand. A set of classes for representing and exchanging knowledge between rule-based systems was also proposed.

Computer-assisted analysis of p53 and PCNA expression in oral lesions infected with human papillomavirus

OBJECTIVE: To carry out a retrospective study to determine whether human papillomavirus (HPV) infection and immunohistochemical expression of p53 and proliferating cell nuclear antigen (PCNA) are related to the risk of oral cancer. STUDY DESIGN: Fifty-seven oral biopsies, consisting of 30 oral squamous papillomas (OSPs) and 27 oral squamous cell carcinomas (OSCCs) were tested for the presence of HPV 6/11 and 16/18 by in situ hybridization using catalyzed signal amplification and in situ hybridization. p53 And PCNA expression was analyzed by immunohistochemistry and evaluated quantitatively by image analysis. RESULTS: Nineteen of the 57 oral lesions (33.3%) were positive for HPV. HPV 6/11 was found in 6 of 30 (20%) OSPs and 1 of 27 (3.7%) OSCCs. HPV 16/18 was found in 10 of 27 (37%) OSCCs and 2 of 30 (6.7%) OSPs. Sixteen of the 19 HPV-positive cases (84.2%) were p53 negative; 5 (9%) were HPV 6/11 and 11 (19%) HPV 16/18, with an inverse correlation between the presence of HPV DNA and p53 expression (P=.017, P < .05). PCNA expression appeared in 18 (94.7%) of HPV positive cases, showing that HPV 16/18 was associated with intensity of PCNA expression and with OSCCs (P=.037, P < .05). CONCLUSION: Quantitative evaluation of p53 by image analysis showed an inverse correlation between p53 expression and HPV presence, suggesting protein degradation. Image analysis also demonstrated that PCNA expression was more intense in HPV DNA 16/18 OSCCs. These findings suggest involvement of high-risk HPV types in oral carcinogenesis.

Road segment delineation using active testing principle and an edge-based post-processing strategy

This paper presents a semi-automated method for extracting road segments from medium-resolution images based on active testing and edge analysis. The method is based on two sequential and independent stages. Firstly, an active testing method is used to extract an approximated road centreline which is based on a sequential and local exploitation of the image. Secondly, an iterative strategy based on edge analysis and the approximated centreline is used to measure precisely the road centreline. Based on the results obtained using medium-resolution test images, the method seems to be very promising. In general, the method proved to be very accurate whenever the roads are characterized by two well-defined anti-parallel edges and robust even in the presence of larger obstacles such as trees and shadows.

A photogrammetric method for single image orientation and measurement

The aim of this paper is to present a photogrammetric method for determining the dimensions of flat surfaces, such as billboards, based on a single digital image. A mathematical model was adapted to generate linear equations for vertical and horizontal lines in the object space. These lines are identified and measured in the image and the rotation matrix is computed using an indirect method. The distance between the camera and the surface is measured using a lasermeter, providing the coordinates of the camera perspective center. Eccentricity of the lasermeter center related to the camera perspective center is modeled by three translations, which are computed using a calibration procedure. Some experiments were performed to test the proposed method and the achieved results are within a relative error of about 1 percent in areas and distances in the object space. This accuracy fulfills the requirements of the intended applications. © 2005 American Society for Photogrammetry and Remote Sensing.

Bone healing in surgically created defects treated with either bioactive glass particles, a calcium sulfate barrier, or a combination of both materials: A histological and histometric study in rat tibias

Objective: The purpose of this study was to histologically analyze the influence of bioactive glass and/or a calcium sulfate barrier on bone healing in surgically created defects in rat tibias. Material and methods: Sixty-four rats were divided into 4 groups: C (control), CS (calcium sulfate), BG (bioactive glass), and BG/CS (bioactive glass/calcium sulfate). A surgical defect was created in the tibia of each animal. In Group CS, a calcium sulfate barrier was placed to cover the defect. In Group BG the defect was filled with bioactive glass. In Group BG/CS, it was filled with bioactive glass and protected by a barrier of calcium sulfate. Animals were sacrificed at 10 or 30 days post-operative. The formation of new bone in the cortical area of the defect was evaluated histomorphometrically. Results: At 10 days post-operative, Group C presented significantly more bone formation than Groups CS, BG, or BG/CS. No statistically significant differences were found between the experimental groups. At 30 days post-operative, Group C demonstrated significantly more bone formation than the experimental groups. Groups CS and BG/CS showed significantly more bone formation than Group BG. No statistically significant differences were found between Group CS and BG/CS. Conclusions: (a) the control groups had significantly more bone formation than the experimental groups; (b) at 10 days post-operative, no significant differences were found between any of the experimental groups; and (c) at 30 days post-operative, the groups with a calcium sulfate barrier had significantly more bone formation than the group that used bioactive glass only. Copyright © Blackwell Munksgaard 2005.

Video target tracking by using competitive neural networks

A target tracking algorithm able to identify the position and to pursuit moving targets in video digital sequences is proposed in this paper. The proposed approach aims to track moving targets inside the vision field of a digital camera. The position and trajectory of the target are identified by using a neural network presenting competitive learning technique. The winning neuron is trained to approximate to the target and, then, pursuit it. A digital camera provides a sequence of images and the algorithm process those frames in real time tracking the moving target. The algorithm is performed both with black and white and multi-colored images to simulate real world situations. Results show the effectiveness of the proposed algorithm, since the neurons tracked the moving targets even if there is no pre-processing image analysis. Single and multiple moving targets are followed in real time.

Image categorization through optimum path forest and visual words

Different from the first attempts to solve the image categorization problem (often based on global features), recently, several researchers have been tackling this research branch through a new vantage point - using features around locally invariant interest points and visual dictionaries. Although several advances have been done in the visual dictionaries literature in the past few years, a problem we still need to cope with is calculation of the number of representative words in the dictionary. Therefore, in this paper we introduce a new solution for automatically finding the number of visual words in an N-Way image categorization problem by means of supervised pattern classification based on optimum-path forest. © 2011 IEEE.