An Assignment Scheme to Control Multiple Pan/Tilt Cameras for 3D Video

نویسندگان

  • Sofiane Yous
  • Norimichi Ukita
  • Masatsugu Kidode
چکیده

— This paper presents an assignment scheme to control multiple Pan/Tilt (PT) cameras for 3D video of a moving object. The system combines static wide field of view (FOV) cameras and active Pan/Tilt (PT) cameras with narrow FOV within a networked platform. We consider the general case where the active cameras have as high resolution as they can capture only partial views of the object. The major issue is the automatic assignment of each active camera to an appropriate part of the object in order to get high-resolution images of the whole object. We propose an assignment scheme based on the analysis of a coarse 3D shape produced in a preprocessing step based on the wide-FOV images. For each high-resolution camera, we evaluate the visibility toward the different parts of the shape, corresponding to different orientations of the camera and with respect to its FOV. Then, we assign each camera to one orientation in order to get high visibility of the whole object. The continuously captured images are saved to be used offline in the reconstruction of the object. For a temporal extension of this scheme, we involve, in addition to the visibility analysis, the last camera orientation as an additional constraint. This allows smooth and optimized camera movements.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

PROACTIVE PTZ CAMERA CONTROL A Cognitive Sensor Network That Plans Ahead

We present a visual sensor network—comprising wide field-of-view (FOV) passive cameras and pan/tilt/zoom (PTZ) active cameras—capable of automatically capturing closeup video of selected pedestrians in a designated area. The passive cameras can track multiple pedestrians simultaneously and any PTZ camera can observe a single pedestrian at a time. We propose a strategy for proactive PTZ camera c...

متن کامل

Enhancement of 3D Capture of Room-Sized Dynamic Scenes with Pan-Tilt-Zoom Cameras

We present a method for augmenting the 3D reconstruction of a dynamic indoor scene using Pan-Tilt-Zoom cameras. The system combines Pan-Tilt-Zoom cameras with static wide field-of-view depth cameras within a networked platform. Traditionally, Pan-Tilt-Zoom cameras have been extensively used in surveillance applications, since their ability to pan, tilt and zoom in on an object allows them to co...

متن کامل

Assessing Control Modalities Designed for Pan-Tilt Surveillance Cameras

Many modern video surveillance systems encompass pan-tilt cameras due to the flexibility they provide in selecting the fields-of-view, as compared to using just fixed cameras. Although patent the great potential of using the pan-tilt cameras, one has to design pan and tilt controllers whose effectiveness directly impacts on the surveillance performance. In this work we propose a metric tuned to...

متن کامل

GlobeAll: Panoramic Video for an Intelligent Room

Choosing the appropriate type of video input is an important issue for any vision-based system and the right decision must take into account the specific requirements of the intended application. In the context of Intelligent Room systems, we establish several qualitative criteria to evaluate the video input component and we use them to compare three current solutions: mobile pan-tilt-zoom came...

متن کامل

Face Recognition : face in video , age invariance , and facial marks

Face Recognition: face in video, age invariance, and facial marks By Unsang Park Automatic face recognition has been extensively studied over the past decades in various domains (e.g., 2D, 3D, and video) resulting in a dramatic improvement. However, face recognition performance severely degrades under pose, lighting and expression variations, occlusion, and aging. Pose and lighting variations a...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Journal of Multimedia

دوره 2  شماره 

صفحات  -

تاریخ انتشار 2007