Smart camera

About: Smart camera is a research topic. Over the lifetime, 5571 publications have been published within this topic receiving 93054 citations. The topic is also known as: intelligent camera.

Mobile camera-based adaptive viewing

Abstract: In this paper, we present an approach for facilitating user interaction on mobile devices, focusing on camera-enabled mobile phones. A user interacts with an application by moving their device. An on-board camera is used to capture incoming video and the scrolling direction and magnitude are estimated using a computer vision-based algorithm. The direction is used as the scroll direction in the application, and the magnitude is used to set the zoom level. The camera is treated as a pointing device and zoom level control in applications. Our approach generates mouse events, so any application that is mouse-driven can make use of this technique. The user is free to browse through large data sets on a limited size display with one hand, ideal for the mobile domain.

Video camera system and automatic tracking method therefor

Abstract: The invention provides a video camera system such as a supervisory system wherein the amount of calculation for motion detection is reduced to reduce the required capacity for hardware. An output of a video camera is sent to a data processing apparatus. In the data processing apparatus, an evaluation value calculation block extracts a video signal of each of a plurality of areas and calculates an evaluation value of the image for each of the areas. Further, a microcomputer calculates a reference value based on the evaluation value obtained in an ordinary state and stores the reference value, and then compares the reference value with a current evaluation value to detect motion of the image. Further, the microcomputer controls the position of the video camera so that the area in which the motion has been detected may be positioned at a central portion of the field of view of the video camera.

Real-Time Face Recognition on a Smart Camera.

Abstract: There is a rapidly growing demand for using cameras containing built-in intelligence for various purposes like surveillance and identication. Recently, face recognition is becoming an important application for these cameras. Face recognition requires lots of processing performance if real-time constraints are taken into account. The purpose of this paper is to demonstrate that by tuning the application algorithms, their implementation, and using a proper multi-processor architecture, face recognition can be performed real-time, up to faces per second, using a smart camera not bigger than a typical surveillance camera.

Methods and devices for producing an enhanced image

Abstract: Methods and devices for producing an enhanced image are described. In one example aspect, a method includes: providing a three-dimensional operating mode in which stereoscopic images are obtained using a first camera and a second camera; and providing a two-dimensional operating mode and while operating within the two-dimensional operating mode: receiving substantially simultaneously captured two-dimensional images from the first camera and the second camera; and merging the two-dimensional images to produce an enhanced two-dimensional image.

Distributed Metric Calibration of Large Camera Networks

Abstract: Motivated by applications in surveillance sensor networks, we present a distributed algorithm for the automatic, external, metric calibration of a network of cameras with no centralized processor. We model the set of uncalibrated cameras as nodes in a communication network, and propose a distributed algorithm in which each camera only communicates with other cameras that image some of the same scene points. Each node independently forms a neighborhood cluster on which the local calibration takes place, and calibrated nodes and scene points are incrementally merged into a common coordinate frame. The accurate performance of the algorithm is illustrated using examples that model real-world sensor networking situations.