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
25 Apr 2007
TL;DR: MeshEye is introduced, an energy-efficient smart camera mote architecture that has been designed with intelligent surveillance as the target application in mind and basic vision algorithms for object detection, acquisition, and tracking are described and illustrated on real- world data.
Abstract: Surveillance is one of the promising applications to which smart camera motes forming a vision-enabled network can add increasing levels of intelligence. We see a high degree of in-node processing in combination with distributed reasoning algorithms as the key enablers for such intelligent surveillance systems. To put these systems into practice still requires a considerable amount of research ranging from mote architectures, pixel-processing algorithms, up to distributed reasoning engines. This paper introduces MeshEye, an energy-efficient smart camera mote architecture that has been designed with intelligent surveillance as the target application in mind. Special attention is given to MeshEye's unique vision system: a low-resolution stereo vision system continuously determines position, range, and size of moving objects entering its field of view. This information triggers a color camera module to acquire a high-resolution image sub-array containing the object, which can be efficiently processed in subsequent stages. It offers reduced complexity, response time, and power consumption over conventional solutions. Basic vision algorithms for object detection, acquisition, and tracking are described and illustrated on real- world data. The paper also presents a basic power model that estimates lifetime of our smart camera mote in battery-powered operation for intelligent surveillance event processing.

276 citations

Patent
11 May 1999
TL;DR: In this paper, a communication device (10) for interconnecting a digital camera (12) to a communication network (16) for downloading data to a remote computer is described.
Abstract: A communication device (10) for interconnecting a digital camera (12) to a communication network (16) for downloading data to a remote computer. The device (10) has a network communication port (30) for establishing communication with a network (16) via a pre-defined protocol and communication mode, and has a camera communication port (20) such as a serial, parallel, SCSI, USB or Irda-port that imitates the back end application of a PC (14), for connection to a digital camera (12) for sending and receiving data to and from the camera (12). The camera communication port (20) is also used for input of programming and setup data to the communication device (10) from a PC (14). The device can be programmed to operate on the data directly, such as in the case of data for storage or operational direction, and/or direct the data to the camera. The device may also have a Smart card socket (34) into which a user can insert a card to input data, such as user and camera I.D., user authorization, image marking, camera operational parameters, remote computer/destination address, etc. The device can be programmed to perform encryption, authentication, watermarking and fingerprinting procedures, as well as structuring the data for transmission over a particular network, and to automatically perform operations, such as at specific times or in response to data input.

274 citations

Journal ArticleDOI
TL;DR: The paper proposes a decentralized and efficient solution for visual parking lot occupancy detection based on a deep Convolutional Neural Network specifically designed for smart cameras, and provides a new training/validation dataset for parking occupancy detection.
Abstract: We propose an effective CNN architecture for visual parking occupancy detectionThe CNN architecture is small enough to run on smart camerasThe proposed solution performs and generalizes better than other SotA approachesWe provide a new training/validation dataset for parking occupancy detection A smart camera is a vision system capable of extracting application-specific information from the captured images The paper proposes a decentralized and efficient solution for visual parking lot occupancy detection based on a deep Convolutional Neural Network (CNN) specifically designed for smart cameras This solution is compared with state-of-the-art approaches using two visual datasets: PKLot, already existing in literature, and CNRPark-EXT The former is an existing dataset, that allowed us to exhaustively compare with previous works The latter dataset has been created in the context of this research, accumulating data across various seasons of the year, to test our approach in particularly challenging situations, exhibiting occlusions, and diverse and difficult viewpoints This dataset is public available to the scientific community and is another contribution of our research Our experiments show that our solution outperforms and generalizes the best performing approaches on both datasets The performance of our proposed CNN architecture on the parking lot occupancy detection task, is comparable to the well-known AlexNet, which is three orders of magnitude larger

272 citations

Patent
10 Sep 1993
TL;DR: In this paper, the authors present a vision system including devices and methods of augmented reality wherein an image of some real scene is altered by a computer processor to include information from a data base having stored information of that scene in a storage location that is identified by the real time position and attitude of the vision system.
Abstract: The present invention is generally concerned with electronic vision devices and methods, and is specifically concerned with image augmentation in combination with navigation, position, and attitude devices. In the simplest form, devices of the invention can be envisioned to include six major components: A 1) camera to collect optical information about a real scene and present that information as an electronic signal to; a 2) computer processor; a 3) device to measure the position of the camera; and a 4) device to measure the attitude of the camera (direction of the optic axis), thus uniquely identifying the scene being viewed, and thus identifying a location in; a 5) data base where information associated with various scenes is stored, the computer processor combines the data from the camera and the data base and perfects a single image to be presented at; a 6) display whose image is continuously aligned to the real scene as it is viewed by the user. The present invention is a vision system including devices and methods of augmented reality wherein an image of some real scene is altered by a computer processor to include information from a data base having stored information of that scene in a storage location that is identified by the real time position and attitude of the vision system. It is a primary function of the vision system of the invention, and a contrast to the prior art, to present augmented real images and data that is continuously aligned with the real scene as that scene is naturally viewed by the user of the vision system. An augmented image is one that represents a real scene but has deletions, additions and supplements.

270 citations

Patent
12 Oct 1999
TL;DR: In this article, a system and method for enabling real-time off-site video image storage is described, where an offsite storage site is coupled to camera servers at client sites via a private network.
Abstract: A system and method for enabling real-time off-site video image storage is disclosed. An off-site storage site is coupled to camera servers at client sites via a private network. Each camera server is further coupled to one or more surveillance cameras. Video images captured by cameras located at the client sites are forwarded to an off-site server via a camera server. Video images received by the off-site server are produced for live viewing and/or archived in an image database. Users can retrieve live or archived video images through a client workstation that communicates with the off-site server over the public Internet. Retrieval of video images is based on a web-browser interface. Live viewing of video images is supplemented by real-time camera control functions that alter the pan-tilt-zoom (PTZ) position of the camera producing the live images. Commands for controlling the PTZ camera are encoded by the client workstation and transmitted to the off-site server. The off-site server converts the camera control codes into control strings that are recognizable by the particular camera.

269 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