Shung Han Cho

Association and Identification in Heterogeneous Sensors Environment with Coverage Uncertainty

In this paper, we present an approach for providing dynamic object association and identification in heterogeneous sensor networks where identification sensors have coverage uncertainty. Detection uncertainty of identifications by the coverage uncertainty is managed by grouping unassociated identifications. In the system, visual sensors find corresponding objects between cameras by using homographic lines and track them by using multi-camera localization scheme. Identification sensors (i.e., RFID system, fingerprint or iris recognition system) are incorporated into the tracking system for objects identification. This paper elaborates possible identification cases and necessary conditions with the coverage uncertainty of identification sensors. Finally, the proposed association method is evaluated with a realistic simulation.

Locally Initiating Line-Based Object Association in Large Scale Multiple Cameras Environment

Multiple object association is an important capability in visual surveillance system with multiple cameras. In this paper, we introduce locally initiating line-based object association with the parallel projection camera model, which can be applicable to the situation without the common (ground) plane. The parallel projection camera model supports the camera movement (i.e., panning, tilting and zooming) by using the simple table based compensation for non-ideal camera parameters. We propose the threshold distance based homographic line generation algorithm. This takes account of uncertain parameters such as transformation error, height uncertainty of objects and synchronization issue between cameras. Thus, the proposed algorithm associates multiple objects on demand in the surveillance system where the camera movement dynamically changes. We verify the proposed method with actual image frames. Finally, we discuss the strategy to improve the association performance by using the temporal and spatial redundancy.

Sector Based Scanning and Adaptive Active Tracking of Multiple Objects

This paper presents an adaptive active tracking system with sector based scanning for a single PTZ camera. Dividing sectors on an image reduces the search space to shorten selection time so that the system can cover many targets. Upon the selection of a target, the system estimates the target trajectory to predict the zooming location with a finite amount of time for camera movement. Advanced estimation techniques using probabilistic reason suffer from the unknown object dynamics and the inaccurate estimation compromises the zooming level to prevent tracking failure. The proposed system uses the simple piecewise estimation with a few frames to cope with fast moving objects and/or slow camera movements. The target is tracked in multiple steps and the zooming time for each step is determined by maximizing the zooming level within the expected variation of object velocity and detection. The number of zooming steps is adaptively determined according to target speed. In addition, the iterative estimation of a zooming location with camera movement time compensates for the target prediction error due to the difference between speeds of a target and a camera. The effectiveness of the proposed method is validated by simulations and real time experiments.

Local and Global Information Exchange for Enhancing Object Detection and Tracking

Object detection and tracking using visual sensors is a critical component of surveillance systems, which presents many challenges. This paper addresses the enhancement of object detection and tracking via the combination of multiple visual sensors. The enhancement method we introduce compensates for missed object detection based on the partial detection of objects by multiple visual sensors. When one detects an object or more visual sensors, the detected object’s local positions transformed into a global object position. Local and global information exchange allows a missed local object’s position to recover. However, the exchange of the information may degrade the detection and tracking performance by incorrectly recovering the local object position, which propagated by false object detection. Furthermore, local object positions corresponding to an identical object can transformed into nonequivalent global object positions because of detection uncertainty such as shadows or other artifacts. We improved the performance by preventing the propagation of false object detection. In addition, we present an evaluation method for the final global object position. The proposed method analyzed and evaluated using case studies.

Real-Time Target Detection Architecture Based on Reduced Complexity Hyperspectral Processing

This paper presents a real-time target detection architecture for hyperspectral image processing. The architecture is based on a reduced complexity algorithm for high-throughput applications.We propose an efficient pipelined processing element architecture and a scalable multiple-processing element architecture by exploiting data partitioning. We present a processing unit modeling based on the data reduction algorithm in hyperspectral image processing and propose computing structure, that is, to optimize memory usage and eliminates memory bottleneck. We investigate the interconnection topology for the multipleprocessing element architecture to improve the speed. The proposed architecture is designed and implemented in FPGA to illustrate the relationship between hardware complexity and execution throughput of hyperspectral image processing for target detection.

Object Association and Identification in Heterogeneous Sensors Environment

An approach for dynamic object association and identification is proposed for heterogeneous sensor network consisting of visual and identification sensors. Visual sensors track objects by a 2D localization, and identification sensors (i.e., RFID system, fingerprint, or iris recognition system) are incorporated into the system for object identification. This paper illustrates the feasibility and effectiveness of information association between the position of objects estimated by visual sensors and their simultaneous registration of multiple objects. The proposed approach utilizes the object dynamics of entering and leaving the coverage of identification sensors, where the location information of identification sensors and objects is available. We investigate necessary association conditions using set operations where the sets are defined by the dynamics of the objects. The coverage of identification sensor is approximately modeled by the maximum sensing coverage for a simple association strategy. The effect of the discrepancy between the actual and the approximated coverage is addressed in terms of the association performance. We also present a coverage adjustment scheme using the object dynamics for the association stability. Finally, the proposed method is evaluated with a realistic scenario. The simulation results demonstrate the stability of the proposed method against nonideal phenomena such as false detection, false tracking, and inaccurate coverage model.

Local Initiation Method for Multiple Object Association in Surveillance Environment with Multiple Cameras

Multiple object association is an important capability in visual surveillance system with multiple cameras. An association approach using the limits of field of View (FOV) of cameras is well accepted but this approach has to wait until the object crosses the limits for association. Also, FOV information has to be determined whenever the setup of camera is changed. Our approach is to dynamically generate the global homographic line whenever it is needed for multi-object association with the aim to work on dynamic camera environment, where the change of camera frequently occurs and objects move in a complicated fashion. We show that, with this approach, the system can initiate association procedure as needed and allow itself to actively adapt to the dynamic environment, while maintaining consistent states of the objects.

Passive sensor based dynamic object association method in wireless sensor networks

This paper proposes and presents a novel algorithm for dynamic data association in wireless sensor networks. The sensor node incorporates RFID reader and acoustic sensor where the signals are fused for tracking and associating multiple objects. The RFID tag is used for object identification and acoustic sensor is used for estimating object movement. The threshold based association algorithm is proposed and its performance is analyzed. The association performance under single node coverage and multiple node coverage is evaluated as a function of sampling time and the dynamic behavior. The algorithm minimizes the failed association and provides association recovery.

Multitarget association and tracking in 3-D space based on particle filter with joint multitarget probability density

This paper addresses the problem of 3-dimensional (3D) multitarget tracking using particle filter with the joint multitarget probability density (JMPD) technique. The estimation allows the nonlinear target motion with unlabeled measurement association as well as non-Gaussian target state densities. In addition, we decompose the 3D formulation into multiple 2D particle filters that operate on the 2D planes. Both selection and combining of the 2D particle filters for 3D tracking are presented and discussed. Finally, we analyze the tracking and association performance of the proposed approach especially in the cases of multitarget crossing and overlapping.

Homographic line generation and transformation technique for dynamic object association

Object association among multiple cameras is an important capability for maintaining consistent view of surroundings. This is necessary in many applications such as tracking and surveillance. In this paper, we present a dynamic homographic line generation technique supporting the camera movement for object association in the multiple visual sensors network. The conventional method uses the globally defined homographic lines or the feature based methods for the object association. However, these methods restrict the camera movement (i.e., panning, tilting and zooming) required for efficient and effective association in the autonomous surveillance system. The proposed method uses the table based compensation for non-ideal camera parameters to support the camera movement. Lastly, two possible application models are simulated with the proposed technique.