scispace - formally typeset
Search or ask a question
Topic

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.


Papers
More filters
Proceedings ArticleDOI
22 Oct 2007
TL;DR: A novel approach based on PCA-SIFT features and a vocabulary tree is presented, which works on spatially separated, un-calibrated, non-overlapping cameras, is highly scalable and solely based on appearance-based optical features.
Abstract: Object reacquisition or reidentification is the process of matching objects between images taken from separate cameras. In this paper, we present our work on feature based object reidentification performed on autonomous embedded smart cameras and applied to traffic scenarios. We present a novel approach based on PCA-SIFT features and a vocabulary tree. By building unique object signatures from visual features, reidentification can be done efficiently coevally minimizing the communication overhead between separate camera nodes. Applied to large-scale traffic scenarios, important parameters including travel time, travel time variability, section density, and partial dynamic origin/destination demands can be obtained. The proposed approach works on spatially separated, un-calibrated, non-overlapping cameras, is highly scalable and solely based on appearance-based optical features. The entire system is implemented and evaluated with regard to a typical embedded smart camera platform featuring one single Texas Instruments trade fixed-point DSP.

56 citations

Patent
26 Nov 1996
TL;DR: In this paper, a controller is provided for a terminal input apparatus which is connected by a communication network to a camera on the partner side and which has an image display apparatus with a multi-window display function for selecting and displaying the camera setting.
Abstract: In a video system of the invention, a controller is provided for a terminal input apparatus which is connected by a communication network to a camera on the partner side and which has an image display apparatus with a multi-window display function for selecting and displaying the camera setting. An image pickup operation which is required to operate the camera on the partner side, for example, the image pickup direction, focal distance, panning, exposure amount, white balance, automatic focusing, and the like of the designated camera are input by using an image display and a window display of the image display apparatus. The operation of the camera on the partner side and the operations of a tripod, a movable arm, and the like to hold the camera are controlled through a communicating device. A photographed image is displayed by the display apparatus.

55 citations

Patent
07 Jun 1995
TL;DR: In this paper, a video camera support device is proposed to teach the dependence on the individual skill and stamina of the operator in producing quality video recordings, by providing that all operator movements are isolated from the camera.
Abstract: A video camera support device that lessons the dependence on the individual skill and stamina of the operator in producing quality video recordings. The invention overcomes the problems of the prior art, by providing that all operator movements are isolated from the camera. The device includes a pivoting joint between a handle and the camera that allows the camera to tilt freely about the handle, except the pivoting joint does not allow for free rotation of the camera. The handle has a bearing member coupled to a panning control that turns the pivoting joint as a unit and the camera. Further, the device has a balancing assembly that includes struts that may be positioned outside the zone of the plane containing the handle and the camera to improve roll stability. A monitor is mounted for improved visibility to the operator, and a monopod pole may be used to support the weight of the device or to raise it overhead.

55 citations

Patent
18 Dec 2000
TL;DR: In this article, a security camera system is provided to provide an overlay image portion at transition regions of a displayed image, where each two cameras providing adjacent areas of coverage are operable to provide a target of interest.
Abstract: A security camera system is provided. Several video cameras operate in conjunction with an image display monitor, a user control and camera selector means whereby a target of interest may be followed. Each two cameras providing adjacent areas of coverage are operable to provide an overlay image portion at transition regions of a displayed image. Upon movement of the target of interest to a specified transition region of a currently displayed image provided by one video camera, the camera selection means is operable to select a second camera whereby to maintain target display continuity by the monitor.

55 citations

Journal Article
TL;DR: This paper identifies the principal shortcomings of existing techniques and proposes a set of objectives for research into automated camera planning, as well as reviewing the solution techniques and presenting a broad classification of existing approaches.
Abstract: Modelling, animation and rendering has dominated research computer graphics yielding increasingly rich and realistic virtual worlds. The complexity, richness and quality of the virtual worlds are viewed through a single media that is a virtual camera. In order to properly convey information, whether related to the characters in a scene, the aesthetics of the composition or the emotional impact of the lighting, particular attention must be given to how the camera is positioned and moved. This paper presents an overview of automated camera planning techniques. After analyzing the requirements with respect to shot properties, we review the solution techniques and present a broad classification of existing approaches. We identify the principal shortcomings of existing techniques and propose a set of objectives for research into automated camera planning.

55 citations


Network Information
Related Topics (5)
Feature (computer vision)
128.2K papers, 1.7M citations
88% related
Feature extraction
111.8K papers, 2.1M citations
88% related
Image processing
229.9K papers, 3.5M citations
87% related
Image segmentation
79.6K papers, 1.8M citations
87% related
Convolutional neural network
74.7K papers, 2M citations
85% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202323
202262
202173
2020142
2019161
2018158