Due to the capacity of pan-tilt-zoom (PTZ) cameras to simultaneously cover a panoramic area and maintain high resolution imagery, researches in automated surveillance systems with multiple PTZ cameras have become incr...
详细信息
Due to the capacity of pan-tilt-zoom (PTZ) cameras to simultaneously cover a panoramic area and maintain high resolution imagery, researches in automated surveillance systems with multiple PTZ cameras have become increasingly important. Most existing algorithms require the prior knowledge of intrinsic parameters of the PTZ camera to infer the relative positioning and orientation among multiple PTZ cameras. To overcome this limitation, we propose a novel mapping algorithm that derives the relative positioning and orientation between two PTZ cameras based on a unified polynomial model. This reduces the dependence on the knowledge of intrinsic parameters of PTZ camera and relative positions. Experimental results demonstrate that our proposed algorithm presents substantially reduced computational complexity and improved flexibility at the cost of slightly decreased pixel accuracy, as compared with the work of Chen and Wang. This slightly decreased pixel accuracy can be compensated by consistent labeling approaches without added cost for the application of automated surveillance systems along with changing configurations and a larger number of PTZ cameras.
Solving the problem of integrating several independent systems to work intelligently and autonomously together has been an important task for an area called System of Systems (SoS). Currently there are initiatives in ...
详细信息
Solving the problem of integrating several independent systems to work intelligently and autonomously together has been an important task for an area called System of Systems (SoS). Currently there are initiatives in large-scale systems utilizing a SoS approach, such as Internet and ballistic missile defense systems. In this work, a smaller, yet complex human tracking task by a mobile robot in a dynamic outdoor environment has been achieved by utilizing a SoS design approach. The detection of moving humans is performed using statistical background modeling and foreground detection on sequential images provided by a single fixed security camera in an outdoor location. The robot control is achieved through established communication formatted as XML messages containing positional data of a moving human target. A real world application of such a SoS architecture includes border thread detection, where humans crossing the border illegally can be tracked by autonomous border protection vehicles.
One of the serious problems in robotics applications is the estimation of the robot's pose. A lot of research effort has been put on finding the pose via inertial and proximity sensors. However, the last decades m...
详细信息
One of the serious problems in robotics applications is the estimation of the robot's pose. A lot of research effort has been put on finding the pose via inertial and proximity sensors. However, the last decades many systems adopt vision to estimate the pose, by using homographies and projection geometry. In this paper the pose estimation is achieved by the identification of a geometrically known platform from one camera and from the measurements of an inertial unit. The extended Kalman filter (EKF) is used for data fusion and error compensation. The novelty of this system is that the visual sensor and the inertial unit are mounted on different mobile systems. The proposed pose estimation system exhibits high accuracy in real-time.
In motion estimation, the sub-pixel matching technique involves the search of sub-sample positions as well as integer-sample positions between the image pairs, choosing the one that gives the best match. Based on this...
详细信息
In motion estimation, the sub-pixel matching technique involves the search of sub-sample positions as well as integer-sample positions between the image pairs, choosing the one that gives the best match. Based on this idea, the proposed disparity estimation algorithm performs a 2-D correspondence search using a hierarchical search pattern. The disparity value is then defined using the distance of the matching position. Therefore, the proposed algorithm can process non-rectified stereo image pairs, maintaining the computational load within reasonable levels.
A globally stabilizing decentralized output-feedback controller is proposed for a general class of nonlinear interconnected large-scale systems. The subsystem interconnections and the dynamics of each subsystem featur...
详细信息
ISBN:
(纸本)9781424445233
A globally stabilizing decentralized output-feedback controller is proposed for a general class of nonlinear interconnected large-scale systems. The subsystem interconnections and the dynamics of each subsystem feature both parametric and functional uncertainty. The controller design is based on a general high-gain scaling technique that utilizes arbitrary powers (instead of requiring successive powers) of the high-gain parameter with the powers chosen to satisfy certain inequalities depending on system nonlinearities. The scaling induces a weak-Cascading Upper Diagonal Dominance (w-CUDD) structure on the dynamics and allows relaxation of the cascading dominance assumption on upper diagonal terms. Disturbance attenuation properties of the proposed decentralized controller are also investigated.
In this paper, we propose a Maritime Underwater Navigation System (MUNS) for Unmanned Underwater Vehicles (UUVs). The proposed MUNS has a hierarchical architecture comprising of a Wide Area Planner (WAP) and a Local A...
详细信息
ISBN:
(纸本)9781424445233
In this paper, we propose a Maritime Underwater Navigation System (MUNS) for Unmanned Underwater Vehicles (UUVs). The proposed MUNS has a hierarchical architecture comprising of a Wide Area Planner (WAP) and a Local Area Planner (LAP). MUNS is intended to be a plug-and-play module to provide obstacle avoidance and path planning capabilities to existing UUV platforms thereby expanding operational capabilities in cluttered and littoral environments. MUNS is designed to be flexible and to support a variety of tasks including point-to-point moves, object inspection, contour tracking, and region scanning/searching. The performance of MUNS has been validated through extensive simulation studies.
Recent years have seen advances in the estimation of full 6 degree-of-freedom object pose from a single 2D image. These advances have often been presented as a result of, or together with, a new local image descriptor...
详细信息
Recent years have seen advances in the estimation of full 6 degree-of-freedom object pose from a single 2D image. These advances have often been presented as a result of, or together with, a new local image descriptor. This paper examines how the performance for such a system varies with choice of local descriptor. This is done by comparing the performance of a full 6 degree-of-freedom pose estimation system for fourteen types of local descriptors. The evaluation is done on a database with photos of complex objects with simple and complex backgrounds and varying lighting conditions. From the experiments we can conclude that duplet features, that use pairs of interest points, improve pose estimation accuracy, and that affine covariant features do not work well in current pose estimation frameworks. The data sets and their ground truth is available on the Web to allow future comparison with novel algorithms.
This paper presents a novel algorithm for line extraction from 2D laser range finder which has excellent precision to determine of line boundary, while having efficient speed and low complexity. This algorithm is more...
详细信息
This paper presents a novel algorithm for line extraction from 2D laser range finder which has excellent precision to determine of line boundary, while having efficient speed and low complexity. This algorithm is more robust in measurement noise and cluttered data and fit a line to a set of uncertain points via Hough transform and recursive split formalism. In this algorithm first the data from laser is segmented to separate regions by determining start and end points throw Hough transform. After removing noisy or sparse points lines are extracted with a fast recursive split algorithm. Furthermore, it has good real-time capability to integrate the information of laser scanner into the navigation algorithm of the mobile robot and it is implemented on NAJI V rescue robot platform.
AAAI was pleased to present the AAAI-08 Workshop Program, held Sunday and Monday, July 13-14, in Chicago, Illinois, USA. The program included the following 15 workshops: Advancements in POMDP Solvers;AI Education Work...
详细信息
Path planning together with the tuning and determination of controller parameters are major concerns in omnidirectional mobile robots. Defining appropriate controller parameters in acceleration and deceleration to rea...
详细信息
ISBN:
(纸本)9781424448081
Path planning together with the tuning and determination of controller parameters are major concerns in omnidirectional mobile robots. Defining appropriate controller parameters in acceleration and deceleration to reach far and near target points without slippage is one of critical issues since some troubles due to unregulated velocities may greatly affect the ability of robot for the specified path planning and attaining the mentioned targets. A robot accurate kinematic and dynamic modeling and simulation accompanied by velocity and acceleration filtering are mainly discussed in this paper. Major changes and improvements in motion analysis, simulation and accuracy for the newly presented model and its efficiency are discussed in comparison with the previous simple kinematic modeling. Employing the new approach for robot dynamic modeling, particularly acceleration filtering, results in to the more precise robot control and achieving appropriate results.
暂无评论