報告簡介:
Visual infrastructure, consisting of connected visual sensors, has been extensively deployed and serving various important applications, such as safety surveillance, health monitoring and mobile system navigation. However, there are still many remaining problems due to visual sensing model irregularity, image processing complexity, and environmental noise etc. In this talk, we focus on the following three related problems:
Visual infrastructure deployment: we propose local face-view barrier coverage, i.e. L-Faceview, a novel concept that achieves statistical barrier coverage in visual sensor networks leveraging mobile object's trajectory information. We derive a rigorous probability bound for this coverage via a feasible deployment pattern.
Visual infrastructure based object recognition: we design and implement R-Focus, a platform with visual sensors that can detect and verify a person holding a mobile phone in proximity with the assistance of electronic sensors. R-Focus performs visual and electronic data collection and rotates based on the collected data. It integrates both visual and electronic data for accurate object recognition.
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. Flash-Loc consists of 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.
This talk will discuss the above techniques along with the system implementation and solutions to practical challenges.
報告人簡介:
宣東(Dong Xuan):上海交通大學電子工程系學士和碩士、美國德克薩斯A&M大學博士;美國俄亥俄州立大學計算機科學和工程系教授;從事計算機網絡、實時通信、機器人感知和控制、傳感器網絡、無線定位、電子/運動/視頻信号融合和
信息安全等理論、技術研究和移動健康、電子視頻監控等應用系統研發;已發表論文150 餘篇,已有和正在申請相關專利10 餘項;領導或參與領導由多項中、美自然科學基金會、中國科技部和香港創新基金等資助的科研項目;擔任多個國際相關領域權威期刊編委和國際學術會議主席;曾獲美國自然科學基金會傑出青年職業獎(NSF CAREER)。