2006 Proceeding- General Chairs:
- Jake K. Aggarwal,
- Rita Cucchiara,
- Program Chair:
- Andrea Prati
It is our great pleasure to welcome you to the 4th ACM Workshop on Video Surveillance & Sensor Networks -- VSSN'06. This workshop is continuation of earlier workshops in Berkeley CA 2003, addressed video surveillance only, and New York NY, 2004 and Singapore, 2005 that extended the focus on sensor networks. The current proliferation of optical (cameras) and non-optical sensors, and the increase in cost-effective computational power has driven the exponential increase of interest in the topics of intelligent surveillance systems and sensor network protocols and coordination. This sensing technology requires scientific and technological knowledge in many different fields, from computer vision and pattern recognition, to behavior analysis, to wireless sensor networks, efficient video streaming, and so on.The workshop explores the state-of-the art of research activity in new generation video surveillance systems, sensor networks and their integration. New solutions are proposed in surveillance systems architecture and in novel techniques for background modeling, detecting and tracking objects. Most of the activities in the research laboratories and in the industrial research centers are now centered on human motion capture and human activity monitoring. Accordingly, we divided the workshop into two sessions: the former devoted to models and techniques to define develop and evaluate video- and sensor-based surveillance systems; the latter focused on human appearance and activity surveillance.The call for papers attracted submissions from USA (43.2% of authors of submitted papers), Spain (12.6%), Italy (12.6%), United Kingdom (6.3%), Taiwan (4.2%), Korea (4.2%), Singapore (3.2%), Pakistan (3.2%), Ireland (3.2%), Switzerland (3.2%), India (2.1%), and Germany (2.1%). A total of 33 papers have been submitted to the workshop. Due to the significant success gained in the past editions, we decided to also organize a poster session this year, to help researchers in disseminating their idea and to create a successful event for exchange of knowledge. Therefore, the program committee, consisting of 20 highly-referenced researchers in the field, accepted 13 papers for oral presentation, and 12 papers for poster presentation.The workshop schedules two oral and two poster sessions. In addition, the program includes a keynote by Prof. Larry Davis from University of Maryland, USA. Prof. Rainer Lienhart from University of Augsburg, Germany, organized, as the past edition, a competition of open source algorithms for foreground/background segmentation.
Proceeding Downloads
Segmenting people in small groups
In this paper we review prior work on the problem of segmenting small groups of people into individuals in surveillance video.
Synchronizing multimodal data streams acquired using commodity hardware
We have developed tools and techniques that allow video frame level synchronization of multiple free-running commodity video cameras,microphones,and computer nodes using non-realtime operating systems.The techniques rely on physical audiovisual ...
Collaborative node localization in surveillance networks using opportunistic target observations
A collaborative vision-based technique is proposed for localizing the nodes of a surveillance network based on observations of a non-cooperative moving target. The proposed method employs lightweight in-node image processing and limited data exchange ...
Support for effective use of multiple video streams in security
Video surveillance systems have become common across a wide number of environments. While these installations have included more video streams, they have been also placed in contexts with limited personnel for monitoring the video feeds. In such ...
Background modeling and object tracking using multi-spectral sensors
In this paper, we present a multi-spectral video surveillance system. Improved background modeling and appearance-based object tracking are proposed with both signal-level and decision-level multi-spectral information fusion. In addition to modeling ...
Motion-based background modeling for foreground segmentation
Foreground segmentation is an elementary process in an intelligent visual surveillance system.When a background is changed dynamically, it is difficult to distinguish the background from the foreground. In this paper, we propose an unified statistical ...
Performance evaluation in visual surveillance using the F-measure
Majority of visual surveillance algorithms rely on effective and accurate motion detection.However,most evaluation techniques described in literature do not address the complexity and range of the issues which underpin the design of good evaluation ...
Robust real-time upper body limb detection and tracking
We describe an efficient and robust system to detect and track the limbs of a human. Of special consideration in the design of this system are real-time and robustness issues. We thus utilize a detection/tracking scheme in which we detect the face and ...
Multiview fusion for canonical view generation based on homography constraints
Activity and gait recognition are among the various applications that necessitate view-specific input. In a real surveillance scenario it is impractical to assume that the desired canonical view will always be available. We present a framework to ...
Unsupervised analysis of activity sequences using event-motifs
We present an unsupervised framework to discover characterizations of everyday human activities, and demonstrate how such representations can be used to extract points of interest in event-streams. We begin with the usage of Suffix Trees as an efficient ...
Top-down, bottom-up multivalued default reasoning for identity maintenance
Persistent tracking systems require the capacity to track individuals by maintaining identity across visibility gaps caused by occlusion events. In traditional computer vision systems, the flow of information is typically bottom-up. The low level image ...
Detection of stable contacts for human motion analysis
Human motion analysis is one of the important topics in visual surveillance applications,the ultimate goal of which is to achieve automated scene understanding. This paper proposes a novel "stable contact "concept for temporal abstraction of image ...
Multimedia surveillance: content-based retrieval with multicamera people tracking
Multimedia surveillance relates to the exploitation of multimedia tools for retrieving information from surveillance data, for emerging applications such as video post-analysis for forensic purposes. Searching for all the sequences in which a certain ...
Analysis and query of person-vehicle interactions in homography domain
This paper presents an efficient and robust paradigm for analysis and query of moving-object interactions in planar homography domain.People and vehicle activities/interactions are analyzed for situational awareness by using a multi-perspective ...
On the optimal placement of multiple visual sensors
Many novel multimedia systems and applications use visual sensor arrays. An important issue in designing sensor arrays is the appropriate placement of the visual sensors such that they achieve a predefined goal. In this paper we focus on the placement ...
A design methodology for selection and placement of sensors in multimedia surveillance systems
This paper addresses the problem of how to select the optimal number of sensors and how to determine their placement in a given monitored area for multimedia surveillance systems. We propose to solve this problem by obtaining a novel performance metric ...
Extending surveillance systems capabilities using BDI cooperative sensor agents
In this paper we describe the Cooperative Sensor Agents (CSA), a logical framework of autonomous agents working in sensor network environments. CSA is a two-layer framework. In the first layer, called Sensor Layer, each agent controls and manages ...
Fusion-based multiview distributed video coding
In this paper, we introduce a scheme for coding video surveillance camera networks. It is based on multiview and Distributed Video Coding (DVC). DVC is known for its low complexity encoders. This makes it very interesting for a wide range of ...
Smart home care network using sensor fusion and distributed vision-based reasoning
A wireless sensor network employing multiple sensing and event detection modalities and distributed processing is proposed for smart home monitoring applications. Image sensing and vision-based reasoning are employed to verify and further analyze events ...
Real-time constant memory visual summaries for surveillance
In surveillance applications there may be multiple time scales at which it is important to monitor a scene. This work develops on-line, real-time algorithms that maintain background models simultaneously at many time scales. This creates a novel ...
Pedestrian detection in uncontrolled environments using stereo and biometric information
A method for pedestrian detection from challenging real world outdoor scenes is presented in this paper. This technique is able to extract multiple pedestrians, of varying orientations and appearances, from a scene even when faced with large and ...
Human action recognition using star skeleton
This paper presents a HMM-based methodology for action recogni-tion using star skeleton as a representative descriptor of human posture. Star skeleton is a fast skeletonization technique by connecting from centroid of target object to contour extremes. ...
A reinforcement learning approach to active camera foveation
In this paper we report on techniques for automatically learning foveal sensing strategies for an active pan-tilt-zoom camera. The approach uses reinforcement learning to discover foveal actions maximizing the performance of visual detectors, that are ...
Tracking mean shift clustered point clouds for 3D surveillance
We present in this paper a method of tracking multiple objects (people) in 3D for application in video surveillance. The tracking method is designed to work on images with objects at low resolution and has two major contributions. First we propose a way ...
A new approach to camera hand-off without camera calibration for the general scene with non-planar ground
For robust continuous tracking across multiple views for the wide surveillance environment it is helpful to know the geometric relationship or a hand-off function in addition to photometric relationship between views. Previous works for camera hand-off ...
A multimodal approach for dynamic event capture of vehicles and pedestrians
This paper presents an overview of a novel multimodal system being developed at UC San Diego for vehicle and pedestrian detection, event capture, and analysis. A Distributed Multimodal Array (DiMMA) framework is presented for sensory data acquisition, ...
Reliable background suppression for complex scenes
This paper describes a system for motion detection based on background suppression,specifically conceived for working in complex scenes with vacillating background,camouflage, illumination changing, etc.. The system contains proper techniques for ...
A revaluation of frame difference in fast and robust motion detection
In this paper we propose a robust approach to detect moving objects for video surveillance applications. We demonstrate that a jointly use of frame by frame difference with a background subtraction algorithm allows us to have a strong and fast pixel ...
Cited By
-
Gehrmann P, Koller T, Klein J, Rettmann M and Siewerdsen J (2024). Towards optimal camera positioning for navigated surgery applications based on RGBD data Image-Guided Procedures, Robotic Interventions, and Modeling, 10.1117/12.3005665, 9781510671607, (14)
-
Al Mansoori A, Swamidoss I, Almarzooqi A, Sayadi S and Dijk J (2019). Analysis of different background subtraction methods applied on drone imagery under various weather conditions in the UAE region Artificial Intelligence and Machine Learning in Defense Applications, 10.1117/12.2534644, 9781510630413, (19)
-
Becker S, Scherer-Negenborn N, Thakkar P, Hübner W, Arens M, Burgess D, Owen G, Bouma H, Carlysle-Davies F, Stokes R and Yitzhaky Y (2016). The effects of camera jitter for background subtraction algorithms on fused infrared-visible video streams Optics and Photonics for Counterterrorism, Crime Fighting, and Defence, 10.1117/12.2239884, 9781510603943, (18)
-
Loce R, Saber E, Wood R, Reed D, Collins B and Irvine J (2014). Enhancing event detection in video using robust background and quality modeling IS&T/SPIE Electronic Imaging, 10.1117/12.2042585, , (902609), Online publication date: 5-Mar-2014.
- Vezzani R and Cucchiara R (2010). Video Surveillance Online Repository (ViSOR), Multimedia Tools and Applications, 50:2, (359-380), Online publication date: 1-Nov-2010.
Index Terms
- Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks