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.

Approximating Beyond the Processor: Exploring Full-System Energy-Accuracy Tradeoffs in a Smart Camera System

Abstract: The intrinsic error resilience exhibited by emerging application domains enables new avenues for energy optimization of computing systems, namely, the introduction of a small amount of approximations during system operation in exchange for substantial energy savings. Prior work in the area of approximate computing has focused on individual subsystems of a computing system, for example, the computational subsystem or the memory subsystem. Since they focus only on individual subsystems, these techniques are unable to exploit the large energy-saving opportunities that stem from adopting a full-system perspective and approximating multiple subsystems of a computing platform simultaneously in a coordinated manner. This paper proposes a systematic methodology to perform joint approximations across different subsystems, leading to significant energy benefits compared to approximating individual subsystems in isolation. We use the example of a smart camera system that executes various computer vision and image processing applications to illustrate how the sensing, memory, processing, and communication subsystems can all be approximated synergistically. We demonstrate our proposed methodology using two variants of a smart camera system: 1) a compute-intensive smart camera system, $\texttt {AxSYS}_{\texttt {comp}}$ , where the error-resilient application executes locally within the camera and produces the final application output, and 2) a communication-intensive smart camera system, $\texttt {AxSYS}_{\texttt {comp}}$ , that sends the captured image to a remote cloud server, where the error-resilient application is executed and the final output is generated. We have implemented such an approximate smart camera system using an Altera Stratix IV GX FPGA development board, a Terasic TRDB-D5M 5-Megapixel camera module, a Terasic RFS WiFi module, and a 1-GB DDR3 dynamic random access memory small outline dual in-line memory module (SODIMM). Experimental results obtained using six application benchmarks demonstrate significant energy savings (around $7.5\times $ for $\texttt {AxSYS}_{\texttt {comp}}$ and $4\times $ on average for $\texttt {AxSYS}_{\texttt {comp}}$ ) for minimal ( $3.5\times $ – $5.5\times $ (in the case of $\texttt {AxSYS}_{\texttt {comp}}$ ) and $1.8\times $ – $3.7\times $ (in the case of $\texttt {AxSYS}_{\texttt {comm}}$ ) on average for a minimal (<1%) application-level quality loss.

Systems and methods for acquiring and processing image data produced by camera arrays

Abstract: This disclosure is directed to camera systems including a camera array, data buses shared by the cameras, and one or more processors that process images captured by the camera array. In one aspect, a camera system (450) includes a camera array (452), a controller (454), a number of camera buses (458-465), and a computing device (456) connected to the controller. Each camera is connected to one or more adjacent cameras and includes one or more processors. Each camera bus connects a subset of cameras of the camera array to the controller. And each camera can be operated to send to the controller only the image data used by the computing device to generate virtual images and receive instructions from the controller over a camera bus.

Robot vision tracking system

Abstract: A system designed to test a tracking theory for finding the position of an object in a scene, even when it is entering or exiting, is described. The design of a servo system used to move the camera while tracking the object is proposed. The technique involves the fundamental frequency of the Fourier transform of the vertical and horizontal projections of the image. This technique will work with stationary or moving objects as well as with a stationary or moving camera. The objective is to apply this technique to find the line between the camera and the object, such that the robot arm could follow that line until it encountered the object, and then seize it. This technique may also be useful in performing camera calibration. >

On Automatic and Dynamic Camera Calibration based on Traffic Visual Surveillance

Abstract: This paper presents a novel automatic and dynamic camera calibration algorithm based on traffic visual surveillance. The algorithm can automatically calibrate the intrinsic and extrinsic parameters of camera, and offer enough guarantee to extract traffic real-time parameters. This paper firstly indicates the significance of applying automatic and dynamic calibration algorithm to intelligent transportation system, then establishes a mathematical model of calibration parameters between camera image and actual road. The algorithm is established from three view points, which are description, flow chart and algorithm description. Afterward this paper describes the experimental method and result based on this novel algorithm. Finally this paper indicates wide application foreground of this algorithm in intelligent transportation system.

Privacy-friendly photo capturing and sharing system

Abstract: The wide adoption of smart devices with onboard cameras facilitates photo capturing and sharing, but greatly increases people's concern on privacy infringement. Here we seek a solution to respect the privacy of persons being photographed in a smarter way that they can be automatically erased from photos captured by smart devices according to their requirements. To make this work, we need to address three challenges: 1) how to enable users explicitly express their privacy protection intentions without wearing any visible specialized tag, and 2) how to associate the intentions with persons in captured photos accurately and efficiently. Furthermore, 3) the association process itself should not cause portrait information leakage and should be accomplished in a privacy-preserving way. In this work, we design, develop, and evaluate a system, called COIN (Cloak Of INvisibility), that enables a user to flexibly express her privacy requirement and empowers the photo service provider (or image taker) to exert the privacy protection policy. Leveraging the visual distinguishability of people in the field-of-view and the dimension-order-independent property of vector similarity measurement, COIN achieves high accuracy and low overhead. We implement a prototype system, and our evaluation results on both the trace-driven and real-life experiments confirm the feasibility and efficiency of our system.