12 research outputs found
Multitarget Tracking with a Corner-based Particle Filter
No full textThis paper presents a multitarget tracking algorithm based on a particle filter framework that exploits a sparse distributed shape model to handle partial occlusions. The state vector is composed by a set of points of interest (i.e. corners) and it enables to jointly describe position and shape of the target. An efficient importance sampling strategy is developed to limit the number of used particles and it is based on multiple Kanade-Lucas-Tomasi (KLT) feature trackers used to estimate local motion. The importance sampling strategy adaptively handles KLT failures and partial occlusions. Particles weights are computed exploiting a shape matching technique combined with object local appearance encoded in color histograms of patches centered on the points of interest constituting the state. The proposed approach does not require background subtraction techniques and overcomes several common difficulties in the tracking domain as partial occlusions, object deformations, scale changes, abrupt motion and non-static background. Extensive experimental results are provided on challenging sequences to demonstrate the robustness of the algorithm
"MULTIPLE CUE ADAPTIVE TRACKING OF DEFORMABLE OBJECTS WITH PARTICLE FILTER,"
No full textThis paper presents a tracking algorithm based on a sequential importance sampling (SIS) particle filter scheme followed by a resampling strategy where shape and color cues are exploited to handle deformable objects. The state vector is composed by a set of corners and it enables to jointly describe position and shape of the target. Mean Shift trackers, applied to color cues associated to state subspaces, are employed to predict the target global motion. An adaptive system noise is defined based on this information to cope with local deformations. The updating procedure is accomplished by a shape matching technique. Experimental results prove the effectiveness of the proposed approach with respect to simple deformations, partial occlusions and moving camera
A Nonlinear-Shift Approach to Object Tracking Based on Shape Information
No full textThis paper presents a corner-based method for tracking objects in video image frames. The method uses a vectorial shape representation based on relative object main corners positions and a non-linear voting method to evaluating the new object position at each iteration. The initialization consists of individuating an area including the object to be tracked. Information of the corners distribution around a reference point is used to find the most probable target position in the next frame. The method can be used in both fixed and mobile cameras both for vehicles and pedestrians
Tracking by using dynamic shape model learning in the presence of occlusion
No full textThe paper presents a new corner-model based learning method able to track non-rigid objects in the presence of occlusion. A voting mechanism followed by a probability density analysis of the voting space histogram is used to estimate new position of the target. The model is updated at any frame. The problem rises in the occlusion events where the occluder corners affect the model and the tracker may follow the occluder. The key point of the method toward success is automatically deciding on the corners to classify them into two classes, good and malicious corners. Good corners are used to update the model in a conservative way removing the corners that are voting to the highly voted wrong positions due to the occluder. This leads to a continuous model learning during occlusion. Experimental results show a successful tracking along with a more precise estimation of shape and motion durin
"Driver''s Behavior Assessment by On-board/Off-board Video Context Analysis"
No full textIn the last few years, the application of ICT technologies in automotive field has taken an increasing role in improving both the safety and the driving comfort. In this context, systems capable of determining the traffic situation and/or driver behavior through the analysis of signals from multiple sensors (e.g. radar, cameras, etc...) are the subject of active research in both industrial and academic sectors. The extraction of contextual information through the analysis of video streams captured by cameras can therefore have implications in many applications focused both on prevention of incidents and on provision of useful information to drivers. In this paper, we investigate the study and implementation of algorithms for the extraction of context data from on-board cameras mounted on vehicles. A camera is oriented so as to frame the portion of road in front of the vehicle while the other one is positioned inside the vehicle and pointed on the driver
"Multi-camera indoor video processing for context awareness"
No full textIn this paper a system is presented able to acquire images from multiple indoor network cameras and extract contextual information about persons detected within the considered environment. Distributed system architecture allows one to process images from several cameras on a network of PCs. Objects tracking and posture classification techniques are used in order to extract contextual information from video. These information are stored in a remote database that is accessed from an higher level application that is able to interact with users' mobile phones for delivering context-based-services. In particular, proposed scene understanding techniques have been used for implementing an automatic terminal silencing service in case of a meeting and a sos-call in case of a falling person
A Bayesian Framework for Online Interaction Classification
No full textReal-time automatic human behavior recognition is one
of the most challenging tasks for intelligent surveillance
systems. Its importance lies in the possibility of robust detection
of suspicious behaviors in order to prevent possible
threats. The widespread integration of tracking algorithms
into modern surveillance systems makes it possible to acquire
descriptive motion patterns of different human activities.
In this work, a statistical framework for human interaction
recognition based on Dynamic Bayesian Networks
(DBNs) is presented: the environment is partitioned by a
topological algorithm into a set of zones that are used to define
the state of the DBNs. Interactive and non-interactive
behaviors are described in terms of sequences of significant
motion events in the topological map of the environment.
Finally, by means of an incremental classification measure,
a scenario can be classified while it is currently evolving.
In this way an autonomous surveillance system can detect
and cope with potential threats in real-tim
