Urban network travel time estimation from stop-line loop detector data and signal controller data

This paper presents a model to estimate travel time using cumulative plots. Three different cases considered are i) case-Det, for only detector data; ii) case-DetSig, for detector data and signal controller data and iii) case-DetSigSFR: for detector data, signal controller data and saturation flow rate. The performance of the model for different detection intervals is evaluated. It is observed that detection interval is not critical if signal timings are available. Comparable accuracy can be obtained from larger detection interval with signal timings or from shorter detection interval without signal timings. The performance for case-DetSig and for case-DetSigSFR is consistent with accuracy generally more than 95% whereas, case-Det is highly sensitive to the signal phases in the detection interval and its performance is uncertain if detection interval is integral multiple of signal cycles.

A procedure to estimate parameters of a line segment taking into account its representation through pi circuits: Theoretical development

The objective of this paper is to show an alternative methodology to estimate per unit length parameters of a line segment of a transmission line. With this methodology the line segment parameters can be obtained starting from the phase currents and -voltages in receiving and sending end of the line segment. If the line segment is represented as being one or more pi circuits whose frequency dependent parameters are considered lumped, its impedance and admittance can be easily expressed as functions of the currents and voltages at the sending and receiving end. Because we are supposing that voltages and currents at the sending and receiving end of the tine segment (in frequency domain) are known, it is possible to obtains its impedance and admittance and consequently its per unit length longitudinal and transversal parameters. The procedure will be applied to estimate the longitudinal and transversal parameters of a small segment of a single-phase line that is already built.

A procedure to estimate parameters of a line segment taking into account its representation through π circuits: Theoretical development

The objective of this paper is to show an alternative methodology to estimate per unit length parameters of a line segment of a transmission line. With this methodology the line segment parameters can be obtained starting from the phase currents and voltages in receiving and sending end of the line segment. If the line segment is represented as being one or more π circuits whose frequency dependent parameters are considered lumped, its impedance and admittance can be easily expressed as functions of the currents and voltages at the sending and receiving end. Because we are supposing that voltages and currents at the sending and receiving end of the line segment (in frequency domain) are known, it is possible to obtains its impedance and admittance and consequently its per unit length longitudinal and transversal parameters. The procedure will be applied to estimate the longitudinal and transversal parameters of a small segment of a single-phase line that is already built. © 2006 IEEE.

The Two-Interval Line-Segment Problem

In this paper, the NPMLE in the one-dimensional line segment problem is defined and studied, where line segments on the real line through two non-overlapping intervals are observed. The self-consistency equations for the NPMLE are defined and a quick algorithm for solving them is provided. Supnorm weak convergence to a Gaussian process and efficiency of the NPMLE is proved. The problem has a strong geological application in the study of the lifespan of species.

Video analytics for the detection of near-miss incidents on approach to railway level crossings

Recent modelling of socio-economic costs by the Australian railway industry in 2010 has estimated the cost of level crossing accidents to exceed AU$116 million annually. To better understand causal factors that contribute to these accidents, the Cooperative Research Centre for Rail Innovation is running a project entitled Baseline Level Crossing Video. The project aims to improve the recording of level crossing safety data by developing an intelligent system capable of detecting near-miss incidents and capturing quantitative data around these incidents. To detect near-miss events at railway level crossings a video analytics module is being developed to analyse video footage obtained from forward-facing cameras installed on trains. This paper presents a vision base approach for the detection of these near-miss events. The video analytics module is comprised of object detectors and a rail detection algorithm, allowing the distance between a detected object and the rail to be determined. An existing publicly available Histograms of Oriented Gradients (HOG) based object detector algorithm is used to detect various types of vehicles in each video frame. As vehicles are usually seen from a sideway view from the cabin’s perspective, the results of the vehicle detector are verified using an algorithm that can detect the wheels of each detected vehicle. Rail detection is facilitated using a projective transformation of the video, such that the forward-facing view becomes a bird’s eye view. Line Segment Detector is employed as the feature extractor and a sliding window approach is developed to track a pair of rails. Localisation of the vehicles is done by projecting the results of the vehicle and rail detectors on the ground plane allowing the distance between the vehicle and rail to be calculated. The resultant vehicle positions and distance are logged to a database for further analysis. We present preliminary results regarding the performance of a prototype video analytics module on a data set of videos containing more than 30 different railway level crossings. The video data is captured from a journey of a train that has passed through these level crossings.

Urban Detection From Hyperspectral Images Using Dimension-Reduction Model and Fusion of Multiple Segmentations Based on Stuctural and Textural Features

Ce mémoire de maîtrise présente une nouvelle approche non supervisée pour détecter et segmenter les régions urbaines dans les images hyperspectrales. La méthode proposée n ́ecessite trois étapes. Tout d’abord, afin de réduire le coût calculatoire de notre algorithme, une image couleur du contenu spectral est estimée. A cette fin, une étape de réduction de dimensionalité non-linéaire, basée sur deux critères complémentaires mais contradictoires de bonne visualisation; à savoir la précision et le contraste, est réalisée pour l’affichage couleur de chaque image hyperspectrale. Ensuite, pour discriminer les régions urbaines des régions non urbaines, la seconde étape consiste à extraire quelques caractéristiques discriminantes (et complémentaires) sur cette image hyperspectrale couleur. A cette fin, nous avons extrait une série de paramètres discriminants pour décrire les caractéristiques d’une zone urbaine, principalement composée d’objets manufacturés de formes simples g ́eométriques et régulières. Nous avons utilisé des caractéristiques texturales basées sur les niveaux de gris, la magnitude du gradient ou des paramètres issus de la matrice de co-occurrence combinés avec des caractéristiques structurelles basées sur l’orientation locale du gradient de l’image et la détection locale de segments de droites. Afin de réduire encore la complexité de calcul de notre approche et éviter le problème de la ”malédiction de la dimensionnalité” quand on décide de regrouper des données de dimensions élevées, nous avons décidé de classifier individuellement, dans la dernière étape, chaque caractéristique texturale ou structurelle avec une simple procédure de K-moyennes et ensuite de combiner ces segmentations grossières, obtenues à faible coût, avec un modèle efficace de fusion de cartes de segmentations. Les expérimentations données dans ce rapport montrent que cette stratégie est efficace visuellement et se compare favorablement aux autres méthodes de détection et segmentation de zones urbaines à partir d’images hyperspectrales.

Riconoscimento e localizzazione di carrelli per la spesa da immagini.

Il lavoro di tesi è stato svolto presso Datalogic ADC, azienda attiva nel campo dell'automazione industriale. La divisione presso cui mi sono recato per 6 mesi ha sede a Pasadena (California, USA) e si occupa principalmente di sistemi di visione e riconoscimento oggetti, con particolare applicazione al settore della grande distribuzione. L'azienda ha in catalogo diversi prodotti finalizzati ad automatizzare e velocizzare il processo di pagamento alle casse da parte dei clienti. In questo contesto, al mio arrivo, era necessario sviluppare un software che permettesse di riconoscere i comuni carrelli per la spesa quando sono inquadrati dall'alto, con posizione verticale della camera. Mi sono quindi occupato di sviluppare ed implementare un algoritmo che permetta di riconoscere i carrelli della spesa sotto ben precise ipotesi e dati iniziali. Come sarà spiegato più dettagliatamente in seguito, è necessario sia individuare la posizione del carrello sia il suo orientamento, al fine di ottenere in quale direzione si stia muovendo. Inoltre, per i diversi impieghi che si sono pensati per il software in oggetto, è necessario che l'algoritmo funzioni sia con carrelli vuoti, sia con carrelli pieni, anche parzialmente. In aggiunta a ciò il programma deve essere in grado di gestire immagini in cui siano presenti più di un carrello, identificando correttamente ciascuno di essi. Nel Capitolo 1 è data una più specifica introduzione al problema e all'approccio utilizzato per risolverlo. Il Capitolo 2 illustra nel dettaglio l'algoritmo utilizzato. Il Capitolo 3 mostra i risultati sperimentali ottenuti e il procedimento seguito per l'analisi degli stessi. Infine il Capitolo 4 espone alcuni accorgimenti che sono stati apportati all'algoritmo iniziale per cercare di velocizzarlo in vista di un possibile impiego, distinguendo i cambiamenti che introducono un leggero degrado delle prestazioni da quelli che non lo implicano. Il Capitolo 5 conclude sinteticamente questa trattazione ricordando i risultati ottenuti.

Real-time power line extraction from unmanned aerial system video images

In this paper a real-time vision based power line extraction solution is investigated for active UAV guidance. The line extraction algorithm starts from ridge points detected by steerable filters. A collinear line segments fitting algorithm is followed up by considering global and local information together with multiple collinear measurements. GPU boosted algorithm implementation is also investigated in the experiment. The experimental result shows that the proposed algorithm outperforms two baseline line detection algorithms and is able to fitting long collinear line segments. The low computational cost of the algorithm make suitable for real-time applications.

Robust Stereo Visual Odometry through a Probabilistic Combination of Points and Line Segments

Most approaches to stereo visual odometry reconstruct the motion based on the tracking of point features along a sequence of images. However, in low-textured scenes it is often difficult to encounter a large set of point features, or it may happen that they are not well distributed over the image, so that the behavior of these algorithms deteriorates. This paper proposes a probabilistic approach to stereo visual odometry based on the combination of both point and line segment that works robustly in a wide variety of scenarios. The camera motion is recovered through non-linear minimization of the projection errors of both point and line segment features. In order to effectively combine both types of features, their associated errors are weighted according to their covariance matrices, computed from the propagation of Gaussian distribution errors in the sensor measurements. The method, of course, is computationally more expensive that using only one type of feature, but still can run in real-time on a standard computer and provides interesting advantages, including a straightforward integration into any probabilistic framework commonly employed in mobile robotics.

Syntactic Approach to ECG Rhythm Analysis

A diagnostic system for ECG rhythm monitoring based on syntactic approaches to pattern recognition is presented here. The method proposed exploits the difference in shape and structure between arrhythmic and normal ECG patterns to generate distinctly different descriptions in terms of a chosen set of primitives. A given frame of signal is first approximated piecewise linearly into a set of line segments which are completely specified in terms of their length and slope values. The slope values are quantized into seven distinct levels and a unit-length line segment with a slope value in each of these levels is coded as a slope symbol. Seven such slope symbols constitute the set of primitives. The given signal is represented as a string of such symbols based on the length and angle of the line segments approximating the signal. Context-free languages are used for describing the classes of abnormal and normal ECG patterns considered here. Analysis of actual ECG data shows efficiency comparable with that of existing methods and a saving in processing time.

A Model of Anomalous Enzyme-Catalyzed Gel Degradation Kinetics

We show that a model of target location involving n noninteracting particles moving subdiffusively along a line segment (a generalization of a model introduced by Sokolov et al. [Biophys. J. 2005, 89, 895.]) provides a basis for understanding recent experiments by Pelta et al. [Phys. Rev. Lett. 2007, 98, 228302.] on the kinetics of diffusion-limited gel degradation. These experiments find that the time t(c) taken by the enzyme thermolysin to completely hydrolyze a gel varies inversely as roughly the 3/2 power of the initial enzyme concentration [E]. In general, however, this time would be expected to vary either as [E](-1) or as [E](-2), depending on whether the Brownian diffusion of the enzyme to the site of cleavage took place along the network chains (1-d diffusion) or through the pore spaces (3-d diffusion). In our model, the unusual dependence of t(c) on [E] is explained in terms of a reaction-diffusion equation that is formulated in terms of fractional rather than ordinary time derivatives.

Biomimetic pattern recognition theory and its applications

Biomimetic pattern recogntion (BPR), which is based on "cognition" instead of "classification", is much closer to the function of human being. The basis of BPR is the Principle of homology-continuity (PHC), which means the difference between two samples of the same class must be gradually changed. The aim of BPR is to find an optimal covering in the feature space, which emphasizes the "similarity" among homologous group members, rather than "division" in traditional pattern recognition. Some applications of BPR are surveyed, in which the results of BPR are much better than the results of Support Vector Machine. A novel neuron model, Hyper sausage neuron (HSN), is shown as a kind of covering units in BPR. The mathematical description of HSN is given and the 2-dimensional discriminant boundary of HSN is shown. In two special cases, in which samples are distributed in a line segment and a circle, both the HSN networks and RBF networks are used for covering. The results show that HSN networks act better than RBF networks in generalization, especially for small sample set, which are consonant with the results of the applications of BPR. And a brief explanation of the HSN networks' advantages in covering general distributed samples is also given.

Study on the localization of the electric dipole sources

The research of dipole source localization has great significance in both clinical research and applications. For example, the EEG recording from the scalp is widely used for the localization of sources of electrical activity in the brain. This paper presents a closed formula that describes the electric field of dipoles at arbitrary position, which is a linear transformer called the transfer matrix. The expression of transfer matrix and its many useful characteristics are given, which can be used for the analysis of the electrical fields of dipoles. This paper also presents the closed formula for determining the location and magnitude of single dipole or multi-dipoles according to its electrical field distribution. A calculation result for a single dipole shows that the dipole will be located at the midpoint of a line segment if there are equivalent fields at its two ends.

基于外极线分区的动态立体匹配算法

基于区域的立体匹配算法仅针对支撑窗内的灰度信息定义匹配代价函数,导致在弱(无)纹理区域采用WTA优化出现歧义性。该文在外极线分区的基础上,改用区域作为匹配基元,针对歧义性区域,在代价函数中引入遮挡项和平滑项,并按照区域优先级的高低,动态匹配相应区域,获得可靠的视差信息。实验证明,该算法在保持实时性的同时对弱纹理区域处理具有有效性。

装配机器人系统快速碰撞检测算法

提出一种面向操作手装配系统的快速碰撞检测算法。该算法以机器人运动学和空间解析几何为基础 ,将判断机械手手臂与障碍物是否发生碰撞问题转化为直线段与有界平面是否存在公共点的简单解析几何问题 ,并以 PU MA5 6 0操作手为例对算法加以说明。该算法不仅适用于静态的障碍物已知的环境 ,而且适用于障碍物运动规律已知的动态环境 ,减少了碰撞检测占用的时间 ,提高了路径规划的效率