Abstract
In this paper, we investigate the problem of aligning multiple deployed camera into one united coordinate system for cross-camera information sharing and intercommunication. However, the difficulty is greatly increased when faced with large-scale scene under chaotic camera deployment. To address this problem, we propose a UAV-assisted wide area multi-camera space alignment approach based on spatiotemporal feature map. It employs the great global perception of Unmanned Aerial Vehicles (UAVs) to meet the challenge from wide-range environment. Concretely, we first present a novel spatiotemporal feature map construction approach to represent the input aerial and ground monitoring data. In this way, the motion consistency across view is well mined to overcome the great perspective gap between the UAV and ground cameras. To obtain the corresponding relationship between their pixels, we propose a cross-view spatiotemporal matching strategy. Through solving relative relationship with the above air-to-ground point correspondences, all ground cameras can be aligned into one surveillance space. The proposed approach was evaluated in both simulation and real environments qualitatively and quantitatively. Extensive experimental results demonstrate that our system can successfully align all ground cameras with very small pixel error. Additionally, the comparisons with other works on different test situations also verify its superior performance.
Highlights
The advance of imaging performance and decline of sensor price play a significant role in promoting the popularization and development of multi-camera systems
Following the above research route, we propose a novel Unmanned Aerial Vehicles (UAVs)-assisted multi-camera space alignment algorithm based on spatiotemporal feature map
We present a novel cross-view feature description algorithm, called spatiotemporal feature map, to overcome perspective gap between aerial-view images captured by UAV and street-view images collected by ground cameras
Summary
The advance of imaging performance and decline of sensor price play a significant role in promoting the popularization and development of multi-camera systems. With its advantages, such as complementary field of view, flexible structural arrangement and diverse acquisition forms, multi-camera systems have an increasingly important effect in the field of security surveillance [1,2], automatic controlling [3,4], intelligent transportation [5,6], etc. Camera space alignment, which is the foundation and difficulty for large-scale multi-camera systems, has gradually become one of the research focuses in recent years It aims to unify visual data from different cameras into one coordinate system which contributes to cross-camera information sharing and interconnection.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have