Questo sito utilizza cookie di terze parti per inviarti pubblicità in linea con le tue preferenze. Se vuoi saperne di più clicca QUI 
Chiudendo questo banner, scorrendo questa pagina, cliccando su un link o proseguendo la navigazione in altra maniera, acconsenti all'uso dei cookie. OK

Models, Algorithms and Architectures for Video Analysis in Real-time

This thesis is meant to be the final report of three years of research in the context of the Doctoral Curriculum “Dottorato di Ricerca in Ingegneria dell’Informazione (XIV Ciclo)” on the topic of video analysis in real-time. High speed processing of videos is a key need for many fields; first, multi-media applications in which the videos are growing as relevance. Think for instance to the videos through the Internet web: standards as the MPEG-1, MPEG-2, MPEG-4 and the upcoming MPEG-7 are video codecs (COmpressor-DECompressorS) very frequently used to broadcast videos through the web. In fact, the bandwidth limitation of current web infrastructures prevents from the transmission of a huge video as it is. Compression before transmitting it and decompression to view it “at the other side” is more efficient since it allows less bandwidth consumption. In the MPEG standards (especially in the more recent ones) the main part of the codec algorithm is the shape coding of the objects that are moving in the scene: this is, indeed, a typical video analysis task. A second very large field of application of the video analysis is the pure information extraction from the video itself. The “level” of the information to be extracted characterizes the video analysis application. Those applications range from the shot detection (low level of information) to the object detection and tracking (medium level) to the scene understanding and modeling (high level). For example, the shot detection task is used to segment a video into
scenes, where a scene is a subsequence of the video (i.e. a sequence of
consecutive frames) with a homogeneous context. This is a very useful task for indexing videos and for context-based information retrieval from videos. The object detection and tracking from a sequence of images is probably the more spread field of video analysis applications. It is a key process for video-based traffic analysis and management systems, for video-surveillance and security systems, for target detection and pointing in military applications, and for many other applications. Therefore, the researches on video analysis reported in the literature are basically on this topic. Lastly, the scene understanding and modeling task uses the information from the lower levels to model the scene (and, typically, also the objects present in the scene) in order to understand the behaviour of the objects or to represent the scene with a higher level of description. All the above-mentioned applications typically require a real-time (or quasi real-time) execution and are characterized by a huge amount of data to be processed. For instance, the real-time processing of a video at the standard PAL (25 frames/sec) at a low resolution of 320x240 pixels. If we have color images (that is 3 channels for each pixel by using the RGB color space), each frame will require 320x240x3 bytes and it must be processed in 40 msec. With this
low resolution a simple transfer of data will require, indeed, a bandwidth of 5.49 MB/sec!!! Studying and, consequently, improving the performance and the efficiency of such systems is one of the main topic of the research described in this thesis. The study has focused both on the hardware and on the software point of view, trying to propose solutions that fit both with an embedded specialized system and with a general-purpose one. Besides improving the performance of video analysis applications, during this research new computational models and algorithms for video analysis has been analyzed and defined. In particular, this research has developed novel algorithms for motion detection and moving object segmentation from cluttered and hostile environments, such as outdoor scene in which the sudden changes of the light conditions, the frequent occlusions of moving objects by
means of buildings, poles, and so on, and the presence of shadows, are very limiting factors.
Moreover, this research covers also motion analysis in “high speed” videos, that is videos in which the objects are moving with a very high speed and in which the noise often renders the images almost unusable. This last topic is very promising and little research has been done (for now) on it by the computer vision community.

Mostra/Nascondi contenuto.
Acknowledgments I really wish to thank all the persons that has helped me in these three years (and even now...). First of all, I give all my gratitude to my tutor Prof. Ing. Rita Cucchiara that has addressed my research when I was losing my bearings and that has given me the opportunity of doing a very exciting experience at UCSD. My best thank-you goes to Prof. Massimo Piccardi that has been not only a helpful support during my Ph.D. but, above all, he has been a special friend for me. I will miss him since he is going to leave for another country (hopefully, not forever). Special thanks to Ing. Costantino Grana with whom I have shared tri- umphs and defeats during these three years and with whom I hope to share many others in the future. Many other people has been a support during these years: Francesca Vigetti, Stefano Sirotti, Francesco Guerra, Eugenio Chiavac- cini, Luca Larcher, Riccardo Morselli, Germano Sandoni, Marco Messori, Marco Mambelli, Marco Mamei, Maurizio Vincini, Luca Pazzi, Riccardo Lancellotti, Alberto Corni, Giacomo Cabri, Fabrizio Vezzalini and many, many others. I hope to not forget any one. My best appreciations are for all my friends from the United States. In particular, Prof. Mohan M. Trivedi has been a great guide during my stay at UCSD. Even now that I am back in Italy, he does not lose a chance to support me and to try to keep me in the loop . My thanks to Ivana Miki ·c and to Brett Hall, probably the best friends I have had in the United States. But many other friends are still in my mind: Ofer Oachler, Koshia Huang, Greg Kogut and Gayle Morelan. Many thanks to everybody. Last but not least, I must say thank you to my family for sustaining me. In particular, all my love to my wife Daniela that has borne with me when I went in the United States for six months and when I get late at work.

Tesi di Dottorato

Dipartimento: Dipartimento di Scienze dell'Ingegneria

Autore: Andrea Prati Contatta »

Composta da 179 pagine.

 

Questa tesi ha raggiunto 949 click dal 20/03/2004.

Disponibile in PDF, la consultazione è esclusivamente in formato digitale.