000143050 001__ 143050
000143050 005__ 20190619003257.0
000143050 0247_ $$2doi$$a10.5075/epfl-thesis-4629
000143050 02470 $$2urn$$aurn:nbn:ch:bel-epfl-thesis4629-9
000143050 02471 $$2nebis$$a5943421
000143050 037__ $$aTHESIS
000143050 041__ $$aeng
000143050 088__ $$a4629
000143050 245__ $$aPedestrian localization, tracking and behavior analysis from multiple cameras
000143050 269__ $$a2010
000143050 260__ $$bEPFL$$c2010$$aLausanne
000143050 300__ $$a199
000143050 336__ $$aTheses
000143050 520__ $$aVideo surveillance is currently undergoing a rapid growth. However, while thousands of cameras are being installed in public places all over the world, computer programs that could reliably detect and track people in order to analyze their behavior are not yet operational. Challenges are numerous, ranging from low image quality, suboptimal scene lighting, changing appearances of pedestrians, occlusions with environment and between people, complex interacting trajectories in crowds, etc. In this thesis, we propose a complete approach for detecting and tracking an unknown number of interacting people from multiple cameras located at eye level. Our system works reliably in spite of significant occlusions and delivers metrically accurate trajectories for each tracked individual. Furthermore, we develop a method for representing the most common types of motion in a specific environment and learning them automatically from image data. We demonstrate that a generative model for detection can effectively handle occlusions in each time frame independently, even when the only data available comes from the output of a simple background subtraction algorithm and when the number of individuals is unknown a priori. We then advocate that multi-people tracking can be achieved by detecting people in individual frames and then linking detections across frames. We formulate the linking step as a problem of finding the most probable state of a hidden Markov process given the set of images and frame-independent detections. We first propose to solve this problem by optimizing trajectories independently with Dynamic Programming. In a second step, we reformulate the problem as a constrained flow optimization resulting in a convex problem that can be solved using standard Linear Programming techniques and is far simpler formally and algorithmically than existing techniques. We show that the particular structure of this framework lets us solve it equivalently using the k-shortest paths algorithm, which leads to a much faster optimization. Finally, we introduce a novel behavioral model to describe pedestrians motions, which is able to capture sophisticated motion patterns resulting from the mixture of different categories of random trajectories. Due to its simplicity, this model can be learned from video sequences in a totally unsupervised manner through an Expectation-Maximization procedure. We show that this behavior model can be used to make tracking systems more robust in ambiguous situations. Moreover, we demonstrate its ability to characterize and detect atypical individual motions.
000143050 6531_ $$aComputer Vision
000143050 6531_ $$aMulti-View
000143050 6531_ $$aPeople Detection
000143050 6531_ $$aPeople Tracking
000143050 6531_ $$aBehavior Model
000143050 6531_ $$avision par ordinateur
000143050 6531_ $$amulti-caméras
000143050 6531_ $$adétection de personnes
000143050 6531_ $$asuivi de personnes
000143050 6531_ $$amodèles de comportement
000143050 700__ $$aBerclaz, Jérôme
000143050 720_2 $$aFua, Pascal$$edir.$$g112366$$0240252
000143050 720_2 $$aFleuret, François$$edir.$$g146262$$0240254
000143050 8564_ $$uhttps://infoscience.epfl.ch/record/143050/files/EPFL_TH4629.pdf$$zTexte intégral / Full text$$s8823952$$yTexte intégral / Full text
000143050 909C0 $$xU10659$$0252087$$pCVLAB
000143050 909CO $$pthesis-public$$pDOI$$pIC$$ooai:infoscience.tind.io:143050$$qGLOBAL_SET$$pthesis$$pthesis-bn2018$$qDOI2
000143050 918__ $$dEDIC2005-2015$$cISIM$$aIC
000143050 919__ $$aCVLAB
000143050 920__ $$b2010
000143050 970__ $$a4629/THESES
000143050 973__ $$sPUBLISHED$$aEPFL
000143050 980__ $$aTHESIS