Results 1 - 10
of
80
P.: Multi-camera people tracking with a probabilistic occupancy map
- IEEE Transactions on Pattern Analysis and Machine Intelligence
, 2007
"... Given three or four synchronized videos taken at eye level and from different angles, we show that we can effectively combine a generative model with dynamic programming to accurately follow up to six individuals across thousands of frames in spite of significant occlusions and lighting changes. In ..."
Abstract
-
Cited by 150 (11 self)
- Add to MetaCart
(Show Context)
Given three or four synchronized videos taken at eye level and from different angles, we show that we can effectively combine a generative model with dynamic programming to accurately follow up to six individuals across thousands of frames in spite of significant occlusions and lighting changes. In addition, we also derive metrically accurate trajectories for each one of them. Our contribution is twofold. First, we demonstrate that our generative model 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. Second, we show that multi-person tracking can be reliably achieved by processing individual trajectories separately over long sequences, provided that a reasonable heuristic is used to rank these individuals and avoid confusing them with one another. Figure 1: Images from two indoor and two outdoor multi-camera video sequences we use for our experiments. At each time step, we draw a box around people we detect and assign to them an Id number that follows them throughout the sequence. 1
A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis
"... ..."
(Show Context)
S.: Counting crowded moving objects
, 2006
"... In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably with occlusions and therefore with crowding. When the objects are constrained to be of the same kind, however, partitioning ..."
Abstract
-
Cited by 81 (1 self)
- Add to MetaCart
(Show Context)
In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably with occlusions and therefore with crowding. When the objects are constrained to be of the same kind, however, partitioning of densely crowded semi-rigid objects can be accomplished by means of clustering tracked feature points. We base our approach on a highly parallelized version of the KLT tracker in order to process the video into a set of feature trajectories. While such a set of trajectories provides a substrate for motion analysis, their unequal lengths and fragmented nature present difficulties for subsequent processing. To address this, we propose a simple means of spatially and temporally conditioning the trajectories. Given this representation, we integrate it with a learned object descriptor to achieve a segmentation of the constituent motions. We present experimental results for the problem of estimating the number of moving objects in a dense crowd as a function of time. 1
A Survey of Visual Sensor Networks
, 2009
"... Visual sensor networks have emerged as an important class of sensor-based distributed intelligent systems, with unique performance, complexity, and quality of service challenges. Consisting of a large number of low-power camera nodes, visual sensor networks support a great number of novel vision-bas ..."
Abstract
-
Cited by 80 (0 self)
- Add to MetaCart
Visual sensor networks have emerged as an important class of sensor-based distributed intelligent systems, with unique performance, complexity, and quality of service challenges. Consisting of a large number of low-power camera nodes, visual sensor networks support a great number of novel vision-based applications. The camera nodes provide information from a monitored site, performing distributed and collaborative processing of their collected data. Using multiple cameras in the network provides different views of the scene, which enhances the reliability of the captured events. However, the large amount of image data produced by the cameras combined with the network’s resource constraints require exploring new means for data processing, communication, and sensor management. Meeting these challenges of visual sensor networks requires interdisciplinary approaches, utilizing vision processing, communications and networking, and embedded processing. In this paper, we provide an overview of the current state-of-the-art in the field of visual sensor networks, by exploring several relevant research directions. Our goal is to provide a better understanding of current research problems in the different research fields of visual sensor networks, and to show how these different research fields should interact to solve the many challenges of visual sensor networks.
Tracking Multiple Occluding People by Localizing on Multiple Scene Planes
"... Abstract—Occlusion and lack of visibility in crowded and cluttered scenes make it difficult to track individual people correctly and consistently, particularly in a single view. We present a multiview approach to solve this problem. In our approach, we neither detect nor track objects from any singl ..."
Abstract
-
Cited by 54 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Occlusion and lack of visibility in crowded and cluttered scenes make it difficult to track individual people correctly and consistently, particularly in a single view. We present a multiview approach to solve this problem. In our approach, we neither detect nor track objects from any single camera or camera pair; rather, evidence is gathered from all of the cameras into a synergistic framework and detection and tracking results are propagated back to each view. Unlike other multiview approaches that require fully calibrated views, our approach is purely image-based and uses only 2D constructs. To this end, we develop a planar homographic occupancy constraint that fuses foreground likelihood information from multiple views to resolve occlusions and localize people on a reference scene plane. For greater robustness, this process is extended to multiple planes parallel to the reference plane in the framework of plane to plane homologies. Our fusion methodology also models scene clutter using the Schmieder and Weathersby clutter measure, which acts as a confidence prior, to assign higher fusion weight to views with lesser clutter. Detection and tracking are performed simultaneously by graph cuts segmentation of tracks in the space-time occupancy likelihood data. Experimental results with detailed qualitative and quantitative analysis are demonstrated in challenging multiview crowded scenes. Index Terms—Tracking, sensor fusion, graph-theoretic methods. Ç 1
Development of a Mote for Wireless Image Sensor Networks’, Wireless Sensor Networks
- Laboratory, Department of Electrical Engineering ,Stanford University
, 2006
"... Abstract — This paper presents the design of a new mote for distributed image sensing applications in wireless sensor networks. The processing and memory limitations in current mote designs are analyzed and a simple but powerful new platform is developed. The mote is based on a 32-bit ARM7 micro-con ..."
Abstract
-
Cited by 35 (3 self)
- Add to MetaCart
(Show Context)
Abstract — This paper presents the design of a new mote for distributed image sensing applications in wireless sensor networks. The processing and memory limitations in current mote designs are analyzed and a simple but powerful new platform is developed. The mote is based on a 32-bit ARM7 micro-controller operating at clock frequencies of up to 48 MHz and accessing up to 64 KB of on-chip RAM. An expansion interface is provided to support multiple mid- and low-resolution image sensors concurrently as well as traditional sensors. Wire-less communication is provided by the Chipcon CC2420 radio which operates in the 2.4 GHz ISM band and is compliant with the IEEE 802.15.4 standard. An integrated USB and serial debug interface allows simple programming and debugging of applications. The additional requirements of an image sensor mote are discussed along with a discussion of possible applications and research areas. I.
Lightweight people counting and localizing in indoor spaces using camera sensor nodes
- Distributed Smart Cameras, 2007. ICDSC ’07. First ACM/IEEE International Conference on
, 2007
"... This paper presents a lightweight method for localizing and counting people in indoor spaces using motion and size criteria. A histogram designed to filter moving objects within a specified size range, can operate directly on frame difference output to localize human-sized moving entities in the fie ..."
Abstract
-
Cited by 27 (9 self)
- Add to MetaCart
(Show Context)
This paper presents a lightweight method for localizing and counting people in indoor spaces using motion and size criteria. A histogram designed to filter moving objects within a specified size range, can operate directly on frame difference output to localize human-sized moving entities in the field of view of each camera node. Our method targets a custom, ultra-low power imager architecture operating on address-event representation, aiming to implement the proposed algorithm on silicon. In this paper we describe the details of our design and experimentally determine suitable parameters for the proposed histogram. The resulting histogram and counting algorithm are implemented and tested on a set of iMote2 camera sensor nodes deployed in our lab. 1.
Counting Pedestrians in Crowds Using Viewpoint Invariant Training
"... This paper describes a learning-based method for counting people in crowds from a single camera. Our method takes into account feature normalization to deal with perspective projection and different camera orientation. Thus, our system is trained to be viewpoint invariant and can be deployed with mi ..."
Abstract
-
Cited by 22 (0 self)
- Add to MetaCart
(Show Context)
This paper describes a learning-based method for counting people in crowds from a single camera. Our method takes into account feature normalization to deal with perspective projection and different camera orientation. Thus, our system is trained to be viewpoint invariant and can be deployed with minimal setup for a new site. This is achieved by applying background subtraction and edge detection to each frame and extracting edge orientation and blob size histograms as features. A homography is computed between the ground plane and the image plane coordinates for the region of interest (ROI). A density map that measures the relative size of individuals and a global scale measuring camera orientation are also estimated and used for feature normalization. The relationship between the feature histograms and the number of pedestrians in the crowds is learned from labeled training data. The two training methods used in the current system are linear fitting and neural networks. Experimental results from different sites with different camera orientation demonstrate the performance and the potential of our method. 1
3D Surveillance – A Distributed Network of Smart Cameras for Real-Time Tracking and its Visualization in 3D
"... The demand for surveillance systems has increased extremely over recent times. We present a system consisting of a distributed network of cameras that allows for tracking and handover of multiple persons in real time. The intercamera tracking results are embedded as live textures in an integrated 3D ..."
Abstract
-
Cited by 15 (0 self)
- Add to MetaCart
(Show Context)
The demand for surveillance systems has increased extremely over recent times. We present a system consisting of a distributed network of cameras that allows for tracking and handover of multiple persons in real time. The intercamera tracking results are embedded as live textures in an integrated 3D world model which is available ubiquitously and can be viewed from arbitrary perspectives independent of the persons ’ movements. We mainly concentrate on our implementation of embedded camera nodes in the form of smart cameras and discuss the benefits of such a distributed surveillance network compared to a host centralized approach. We also briefly describe our way of hassle free 3D model acquisition to cover the complete system from setup to operation and finally show some results of both an indoor and an outdoor system in operation. 1.
Tracking Hidden Agents Through Shadow Information Spaces
, 2008
"... This paper addresses problems of inferring the locations of moving agents from combinatorial data extracted by robots that carry sensors. The agents move unpredictably and may be fully distinguishable, partially distinguishable, or completely indistinguishable. The key is to introduce information ..."
Abstract
-
Cited by 15 (9 self)
- Add to MetaCart
(Show Context)
This paper addresses problems of inferring the locations of moving agents from combinatorial data extracted by robots that carry sensors. The agents move unpredictably and may be fully distinguishable, partially distinguishable, or completely indistinguishable. The key is to introduce information spaces that extract and maintain combinatorial sensing information. This leads to monitoring the changes in connected components of the shadow region, which is the set of points not visible to any sensors at a given time. When used in combination with a path generator for the robots, the approach solves problems such as counting the number of agents, determining movements of teams of agents, and solving pursuit-evasion problems. An implementation with examples is presented.
