Visual Infrastructure based Accurate Object Recognition and Localization

摘要

Visual infrastructure, which consists of connected visual sensors, has been extensively deployed and is vital for various important applications, such as surveillance, tracking, and monitoring. However, there are still many problems regarding visual sensor deployment for optimal coverage and visual data processing technology. Challenges remain with the sectoral visual sensing model, the complexity of image processing, and these sensors' vulnerability to noisy environments. Solving these problems will improve the performance of visual infrastructure, which increases accuracy and efficiency for these applications. This dissertation focuses on visual-infrastructure-related technologies. In particular, we study the following problems.;First, we study visual infrastructure deployment. We propose local face-view barrier coverage (L-Faceview), a novel concept that achieves statistical barrier coverage in visual sensor networks leveraging mobile objects' trajectory information. We derive a rigorous probability bound for this coverage via a feasible deployment pattern. The proposed detection probability bound and deployment pattern can guide practical camera sensor deployments in visual infrastructure with limited budgets.;Second, we study visual-infrastructure-based object recognition. We design and implement R-Focus, a platform with visual sensors that detects and verifies a person holding a mobile phone nearby with the assistance of electronic sensors. R-Focus performs visual and electronic data collection and rotates based on the collected data. It uses the electronic identity information to gather visual identity information. R-Focus can serve as a component of visual infrastructure that performs object identity recognition.;Third, we study visual-infrastructure-based object localization. We design Flash-Loc, an accurate indoor localization system leveraging flashes of light to localize objects in areas with deployed visual infrastructure. An object emits a sequence of flashes that uniquely "represent" the object from the cameras' view. Flash-Loc develops three key mechanisms that distinguish objects while avoiding long irritating flashes: adaptive-length flash coding, pulse-width-modulation-based flash generation, and image-subtraction-based flash localization. Further, we design a system in which Flash-Loc cooperates with fingerprinting and dead reckoning for continuous localization. We implement Flash-Loc on commercial off-the-shelf (COTS) equipment. Our real-world experiments show that Flash-Loc achieves accurate indoor localization by itself and in cooperation with other localization technologies. In particular, Flash-Loc can localize an object 45m away from the camera with sub-meter accuracy.;This dissertation presents all of the above techniques in detail, along with the respective system implementation and solutions to practical challenges.