Sensor planning method for visual tracking in 3D camera networks

Most sensors or cameras discussed in the sensor network community are usually 3D homogeneous, even though their2 D coverage areas in the ground plane are heterogeneous. Meanwhile, observed objects of camera networks are usually simplified as 2D points in previous literature. However in actual application scenes, not only cameras are always heterogeneous with different height and action radiuses, but also the observed objects are with 3D features（i.e., height）. This paper presents a sensor planning formulation addressing the efficiency enhancement of visual tracking in 3D heterogeneous camera networks that track and detect people traversing a region. The problem of sensor planning consists of three issues：（i） how to model the 3D heterogeneous cameras;（ii） how to rank the visibility, which ensures that the object of interest is visible in a camera＇s field of view;（iii） how to reconfigure the 3D viewing orientations of the cameras. This paper studies the geometric properties of 3D heterogeneous camera networks and addresses an evaluation formulation to rank the visibility of observed objects. Then a sensor planning method is proposed to improve the efficiency of visual tracking. Finally, the numerical results show that the proposed method can improve the tracking performance of the system compared to the conventional strategies.

Accurate 3D Target Positioning in Close Range Photogrammetry with Implicit Image Correction

Accurate three-dimensional （3D） target positioning is of great importance in many industrial applications. Although various methods for reconstructing 3D information from a set of images have been available in the literature, few of them pay enough attention to the indispensable procedures, such as target extraction from images and image correction having strong influences upon the 3D positioning accuracy. This article puts forward a high-precision ellipse center （target point） extraction method and a new image correction approach which has been integrated into the 3D reconstruction pipeline with a concise implicit model to accurately compensates for the image distortion. The methods are applied to a copyright-reserved close range photogrammetric system. Real measuring experiments and industrial applications have evidenced the proposed methods, which can significantly improve the 3D positioning accuracy.

Design and implementation of vision-based transport for a mobile robot via Kalman filter

A vision-based scheme for object recognition and transport with a mobile robot is proposed in this paper. First, camera calibration is experimentally performed with Zhenyou Zhang＇s method, and a distance measurement method with the monocular camera is presented and tested. Second, Kalman filtering algorithm is used to predict the movement of a target with HSI model as the input and the seed filling algorithm as the image segmentation approach. Finally, the motion control of the pan-tilt camera and mobile robot is designed to fulfill the tracking and transport task. The experiment results demonstrate the robust object recognition and fast tracking capabilities of the proposed scheme.