Analysis of warm season thunderstorms using an object-oriented tracking method based on radar and total lightning data

Monitoring thunderstorms activity is an essential part of operational weather surveillance given their potential hazards, including lightning, hail, heavy rainfall, strong winds or even tornadoes. This study has two main objectives: firstly, the description of a methodology, based on radar and total lightning data to characterise thunderstorms in real-time; secondly, the application of this methodology to 66 thunderstorms that affected Catalonia (NE Spain) in the summer of 2006. An object-oriented tracking procedure is employed, where different observation data types generate four different types of objects (radar 1-km CAPPI reflectivity composites, radar reflectivity volumetric data, cloud-to-ground lightning data and intra-cloud lightning data). In the framework proposed, these objects are the building blocks of a higher level object, the thunderstorm. The methodology is demonstrated with a dataset of thunderstorms whose main characteristics, along the complete life cycle of the convective structures (development, maturity and dissipation), are described statistically. The development and dissipation stages present similar durations in most cases examined. On the contrary, the duration of the maturity phase is much more variable and related to the thunderstorm intensity, defined here in terms of lightning flash rate. Most of the activity of IC and CG flashes is registered in the maturity stage. In the development stage little CG flashes are observed (2% to 5%), while for the dissipation phase is possible to observe a few more CG flashes (10% to 15%). Additionally, a selection of thunderstorms is used to examine general life cycle patterns, obtained from the analysis of normalized (with respect to thunderstorm total duration and maximum value of variables considered) thunderstorm parameters. Among other findings, the study indicates that the normalized duration of the three stages of thunderstorm life cycle is similar in most thunderstorms, with the longest duration corresponding to the maturity stage (approximately 80% of the total time).

Effect of Video Camera-Based Remote Roadway Condition Monitoring on Snow Removal-Related Maintenance Operations. 2014

Remote monitoring through the use of cameras is widely utilized for traffic operation, but has not been utilized widely for roadway maintenance operations. The Utah Department of Transportation (UDOT) has implemented a new remote monitoring system, referred to as a Cloud-enabled Remote Video Streaming (CRVS) camera system for snow removal-related maintenance operations in the winter. The purpose of this study was to evaluate the effectiveness of the use of the CRVS camera system in snow removal-related maintenance operations. This study was conducted in two parts: opinion surveys of maintenance station supervisors and an analysis on snow removal-related maintenance costs. The responses to the opinion surveys mostly displayed positive reviews of the use of the CRVS cameras. On a scale of 1 (least effective) to 5 (most effective), the average overall effectiveness given by the station supervisors was 4.3. An expedition trip for this study was defined as a trip that was made to just check the roadways if snow-removal was necessary. The average of the responses received from surveys was calculated to be a 33 percent reduction in expedition trips. For the second part of this study, an analysis was performed on the snow removal-related maintenance cost data provided by UDOT to see if the installation of a CRVS camera had an effect in reducing expedition trips. This expedition cost comparison was performed for 10 sets of maintenance stations within Utah. It was difficult to make any definitive inferences from the comparison of expedition costs over the years for which precipitation and expedition cost data were available; hence a statistical analysis was performed using the Mixed Model ANOVA. This analysis resulted in an average of 14 percent higher ratio of expedition costs at maintenance stations with a CRVS camera before the installation of the camera compared to the ratio of expedition costs after the installation of the camera. This difference was not proven to be statistically significant at the 95 percent confident level, but indicated that the installation of CRVS cameras was on the average helpful in reducing expedition costs and may be considered practically significant. It is recommended that more detailed and consistent maintenance cost records be prepared for accurate analysis of cost records for this type of study in the future.

A feature-based object-oriented expert system to model and support product design

In this paper a computer program to model and support product design is presented. The product is represented through a hierarchical structure that allows the user to navigate across the product��s components, and it aims at facilitating each step of the detail design process. A graphical interface was also developed, which shows visually to the user the contents of the product structure. Features are used as building blocks for the parts that compose the product, and object-oriented methodology was used as a means to implement the product structure. Finally, an expert system was also implemented, whose knowledge base rules help the user design a product that meets design and manufacturing requirements.

The Role of Video Based Content Marketing as a Part of Modern Marketing Communications

The thesis studies the role of video based content marketing as a part of modern marketing communications.

Generative Part-Based Gabor Object Detector

Object detection is a fundamental task of computer vision that is utilized as a core part in a number of industrial and scientific applications, for example, in robotics, where objects need to be correctly detected and localized prior to being grasped and manipulated. Existing object detectors vary in (i) the amount of supervision they need for training, (ii) the type of a learning method adopted (generative or discriminative) and (iii) the amount of spatial information used in the object model (model-free, using no spatial information in the object model, or model-based, with the explicit spatial model of an object). Although some existing methods report good performance in the detection of certain objects, the results tend to be application specific and no universal method has been found that clearly outperforms all others in all areas. This work proposes a novel generative part-based object detector. The generative learning procedure of the developed method allows learning from positive examples only. The detector is based on finding semantically meaningful parts of the object (i.e. a part detector) that can provide additional information to object location, for example, pose. The object class model, i.e. the appearance of the object parts and their spatial variance, constellation, is explicitly modelled in a fully probabilistic manner. The appearance is based on bio-inspired complex-valued Gabor features that are transformed to part probabilities by an unsupervised Gaussian Mixture Model (GMM). The proposed novel randomized GMM enables learning from only a few training examples. The probabilistic spatial model of the part configurations is constructed with a mixture of 2D Gaussians. The appearance of the parts of the object is learned in an object canonical space that removes geometric variations from the part appearance model. Robustness to pose variations is achieved by object pose quantization, which is more efficient than previously used scale and orientation shifts in the Gabor feature space. Performance of the resulting generative object detector is characterized by high recall with low precision, i.e. the generative detector produces large number of false positive detections. Thus a discriminative classifier is used to prune false positive candidate detections produced by the generative detector improving its precision while keeping high recall. Using only a small number of positive examples, the developed object detector performs comparably to state-of-the-art discriminative methods.

Video-based postural sway analysis in a controlled environment

�� mesure que la population des personnes ag��es dans les pays industrialis��s augmente au fil de ann��es, les ressources n��cessaires au maintien du niveau de vie de ces personnes augmentent aussi. Des statistiques montrent que les chutes sont l���une des principales causes d���hospitalisation chez les personnes ag��es, et, de plus, il a ��t�� d��montr�� que le risque de chute d���une personne ag��e a une correlation avec sa capacit�� de maintien de l�����quilibre en ��tant debout. Il est donc d���int��r��t de d��velopper un syst��me automatis�� pour analyser l�����quilibre chez une personne, comme moyen d�����valuation objective. Dans cette ��tude, nous avons propos�� l���impl��mentation d���un tel syst��me. En se basant sur une installation simple contenant une seule cam��ra sur un tr��pied, on a d��velopp�� un algorithme utilisant une impl��mentation de la m��thode de d��tection d���objet de Viola-Jones, ainsi qu���un appariement de gabarit, pour suivre autant le mouvement lat��ral que celui ant��rieur-post��rieur d���un sujet. On a obtenu des bons r��sultats avec les deux types de suivi, cependant l���algorithme est sensible aux conditions d�����clairage, ainsi qu����� toute source de bruit pr��sent dans les images. Il y aurait de l���int��r��t, comme d��veloppement futur, d���int��grer les deux types de suivi, pour ainsi obtenir un seul ensemble de donn��es facile �� interpr��ter.

Video-based analysis of Gait pathologies

L���analyse de la marche a e��merge�� comme l���un des domaines me��dicaux le plus im- portants re��cemment. Les syste��mes a�� base de marqueurs sont les me��thodes les plus fa- vorise��es par l���e��valuation du mouvement humain et l���analyse de la marche, cependant, ces syste��mes ne��cessitent des e��quipements et de l���expertise spe��cifiques et sont lourds, cou��teux et difficiles a�� utiliser. De nombreuses approches re��centes base��es sur la vision par ordinateur ont e��te�� de��veloppe��es pour re��duire le cou��t des syste��mes de capture de mou- vement tout en assurant un re��sultat de haute pre��cision. Dans cette the��se, nous pre��sentons notre nouveau syste��me d���analyse de la de��marche a�� faible cou��t, qui est compose�� de deux came��ras vide��o monoculaire place��es sur le co��te�� gauche et droit d���un tapis roulant. Chaque mode��le 2D de la moitie�� du squelette humain est reconstruit a�� partir de chaque vue sur la base de la segmentation dynamique de la couleur, l���analyse de la marche est alors effectue��e sur ces deux mode��les. La validation avec l���e��tat de l���art base��e sur la vision du syste��me de capture de mouvement (en utilisant le Microsoft Kinect) et la re��alite�� du ter- rain (avec des marqueurs) a e��te�� faite pour de��montrer la robustesse et l���efficacite�� de notre syste��me. L���erreur moyenne de l���estimation du mode��le de squelette humain par rapport a�� la re��alite�� du terrain entre notre me��thode vs Kinect est tre��s prometteur: les joints des angles de cuisses (6,29��� contre 9,68���), jambes (7,68��� contre 11,47���), pieds (6,14��� contre 13,63���), la longueur de la foule��e (6.14cm rapport de 13.63cm) sont meilleurs et plus stables que ceux de la Kinect, alors que le syste��me peut maintenir une pre��cision assez proche de la Kinect pour les bras (7,29��� contre 6,12���), les bras infe��rieurs (8,33��� contre 8,04���), et le torse (8,69���contre 6,47���). Base�� sur le mode��le de squelette obtenu par chaque me��thode, nous avons re��alise�� une e��tude de syme��trie sur diffe��rentes articulations (coude, genou et cheville) en utilisant chaque me��thode sur trois sujets diffe��rents pour voir quelle me��thode permet de distinguer plus efficacement la caracte��ristique syme��trie / asyme��trie de la marche. Dans notre test, notre syste��me a un angle de genou au maximum de 8,97��� et 13,86��� pour des promenades normale et asyme��trique respectivement, tandis que la Kinect a donne�� 10,58���et 11,94���. Par rapport a�� la re��alite�� de terrain, 7,64���et 14,34���, notre syste��me a montre�� une plus grande pre��cision et pouvoir discriminant entre les deux cas.

FPGA-based object detection using classification circuits

Dans l'apprentissage machine, la classification est le processus d���assigner une nouvelle observation �� une certaine cat��gorie. Les classifieurs qui mettent en ��uvre des algorithmes de classification ont ��t�� largement ��tudi�� au cours des derni��res d��cennies. Les classifieurs traditionnels sont bas��s sur des algorithmes tels que le SVM et les r��seaux de neurones, et sont g��n��ralement ex��cut��s par des logiciels sur CPUs qui fait que le syst��me souffre d���un manque de performance et d���une forte consommation d'��nergie. Bien que les GPUs puissent ��tre utilis��s pour acc��l��rer le calcul de certains classifieurs, leur grande consommation de puissance emp��che la technologie d'��tre mise en ��uvre sur des appareils portables tels que les syst��mes embarqu��s. Pour rendre le syst��me de classification plus l��ger, les classifieurs devraient ��tre capable de fonctionner sur un syst��me mat��riel plus compact au lieu d'un groupe de CPUs ou GPUs, et les classifieurs eux-m��mes devraient ��tre optimis��s pour ce mat��riel. Dans ce m��moire, nous explorons la mise en ��uvre d'un classifieur novateur sur une plate-forme mat��rielle �� base de FPGA. Le classifieur, con��u par Alain Tapp (Universit�� de Montr��al), est bas�� sur une grande quantit�� de tables de recherche qui forment des circuits arborescents qui effectuent les t��ches de classification. Le FPGA semble ��tre un ��l��ment fait sur mesure pour mettre en ��uvre ce classifieur avec ses riches ressources de tables de recherche et l'architecture �� parall��lisme ��lev��. Notre travail montre que les FPGAs peuvent impl��menter plusieurs classifieurs et faire les classification sur des images haute d��finition �� une vitesse tr��s ��lev��e.

Motion Segmentation And Meanshift Assisted Contour Refinement For Airborne Video

This paper presents methods for moving object detection in airborne video surveillance. The motion segmentation in the above scenario is usually difficult because of small size of the object, motion of camera, and inconsistency in detected object shape etc. Here we present a motion segmentation system for moving camera video, based on background subtraction. An adaptive background building is used to take advantage of creation of background based on most recent frame. Our proposed system suggests CPU efficient alternative for conventional batch processing based background subtraction systems. We further refine the segmented motion by meanshift based mode association.

Hybrid Background Subtraction in Video using Bi-level CodeBook Model

Detection of Objects in Video is a highly demanding area of research. The Background Subtraction Algorithms can yield better results in Foreground Object Detection. This work presents a Hybrid CodeBook based Background Subtraction to extract the foreground ROI from the background. Codebooks are used to store compressed information by demanding lesser memory usage and high speedy processing. This Hybrid method which uses Block-Based and Pixel-Based Codebooks provide efficient detection results; the high speed processing capability of block based background subtraction as well as high Precision Rate of pixel based background subtraction are exploited to yield an efficient Background Subtraction System. The Block stage produces a coarse foreground area, which is then refined by the Pixel stage. The system���s performance is evaluated with different block sizes and with different block descriptors like 2D-DCT, FFT etc. The Experimental analysis based on statistical measurements yields precision, recall, similarity and F measure of the hybrid system as 88.74%, 91.09%, 81.66% and 89.90% respectively, and thus proves the efficiency of the novel system.

View-Based Strategies for 3D Object Recognition

A persistent issue of debate in the area of 3D object recognition concerns the nature of the experientially acquired object models in the primate visual system. One prominent proposal in this regard has expounded the use of object centered models, such as representations of the objects' 3D structures in a coordinate frame independent of the viewing parameters [Marr and Nishihara, 1978]. In contrast to this is another proposal which suggests that the viewing parameters encountered during the learning phase might be inextricably linked to subsequent performance on a recognition task [Tarr and Pinker, 1989; Poggio and Edelman, 1990]. The 'object model', according to this idea, is simply a collection of the sample views encountered during training. Given that object centered recognition strategies have the attractive feature of leading to viewpoint independence, they have garnered much of the research effort in the field of computational vision. Furthermore, since human recognition performance seems remarkably robust in the face of imaging variations [Ellis et al., 1989], it has often been implicitly assumed that the visual system employs an object centered strategy. In the present study we examine this assumption more closely. Our experimental results with a class of novel 3D structures strongly suggest the use of a view-based strategy by the human visual system even when it has the opportunity of constructing and using object-centered models. In fact, for our chosen class of objects, the results seem to support a stronger claim: 3D object recognition is 2D view-based.

On the difficulty of feature-based attentional modulations in visual object recognition: A modeling study.

Numerous psychophysical experiments have shown an important role for attentional modulations in vision. Behaviorally, allocation of attention can improve performance in object detection and recognition tasks. At the neural level, attention increases firing rates of neurons in visual cortex whose preferred stimulus is currently attended to. However, it is not yet known how these two phenomena are linked, i.e., how the visual system could be "tuned" in a task-dependent fashion to improve task performance. To answer this question, we performed simulations with the HMAX model of object recognition in cortex [45]. We modulated firing rates of model neurons in accordance with experimental results about effects of feature-based attention on single neurons and measured changes in the model's performance in a variety of object recognition tasks. It turned out that recognition performance could only be improved under very limited circumstances and that attentional influences on the process of object recognition per se tend to display a lack of specificity or raise false alarm rates. These observations lead us to postulate a new role for the observed attention-related neural response modulations.

New Architectural Models for Visibly Controllable Computing: The Relevance of Dynamic Object Oriented Architectures and Plan Based Computing Models

Traditionally, we've focussed on the question of how to make a system easy to code the first time, or perhaps on how to ease the system's continued evolution. But if we look at life cycle costs, then we must conclude that the important question is how to make a system easy to operate. To do this we need to make it easy for the operators to see what's going on and to then manipulate the system so that it does what it is supposed to. This is a radically different criterion for success. What makes a computer system visible and controllable? This is a difficult question, but it's clear that today's modern operating systems with nearly 50 million source lines of code are neither. Strikingly, the MIT Lisp Machine and its commercial successors provided almost the same functionality as today's mainstream sytsems, but with only 1 Million lines of code. This paper is a retrospective examination of the features of the Lisp Machine hardware and software system. Our key claim is that by building the Object Abstraction into the lowest tiers of the system, great synergy and clarity were obtained. It is our hope that this is a lesson that can impact tomorrow's designs. We also speculate on how the spirit of the Lisp Machine could be extended to include a comprehensive access control model and how new layers of abstraction could further enrich this model.

Group stochastic search for object detection and tracking

A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320x240 resolution video at up to 15fps.