Search

Ubiquitous deployment of networked cameras has boosted the prevalence of video analytics. Leveraging machines to automatically analyze captured videos has become the driving force behind a variety of contemporary applications. However, it is known to be resource-hungry with highly dynamic demands, which mismatches the existing monolithic cloud service deployment with coarse-grained resource allocation. Recent advances in serverless computing, which offers ultra-fast and fine-grained autoscaling, would become a game-changer. This article closely examines the potential and challenges of serverless computing in building modern video analytics applications. We accordingly present an integrated framework with geo-distributed resources, and identify the critical design issues toward its implementation. We further discuss a series of promising research directions in this field. [ABSTRACT FROM AUTHOR]

Recent years have witnessed an explosive growth of online shopping, which has posted unprecedented pressure on the logistics industry, especially the last mile parcel delivery. Existing solutions mostly rely on dedicated couriers, which suffer from high cost and low elasticity when dealing with a massive amount of local addresses. Advances in the Internet of Things, however, have enabled vehicle information to be readily accessible anytime anywhere, forming an Internet of Vehicles (IoV), which further enables intelligent vehicle scheduling and management. New opportunities therefore arise toward efficient and elastic last mile delivery for smart cities. In this article, we seek novel solutions to improve the last mile parcel delivery with crowd intelligence. We first review the existing and emerging solutions for last mile parcel delivery. We then discuss the advances of the ride-sharing- based delivery mechanism, identifying the unique opportunities and challenges therein. We further present Car4Pac, an IoV-enabled intelligent ride-sharing-based delivery system for smart cities, and demonstrate its superiority with real trace-driven evaluations. [ABSTRACT FROM AUTHOR]