Abstract
Emerging visual-based driving assistance systems involve time-critical and data-intensive computational tasks, such as real-time object recognition and scene understanding. Due to the constraints on space and power capacity, it is not feasible to install extra computing devices on all the vehicles. To solve this problem, different scenarios of vehicular fog computing have been proposed, where computational tasks generated by vehicles can be sent to and processed at fog nodes located for example at 5G cell towers or moving buses. In this paper, we propose Chameleon, a novel solution for task offloading for visual-based assisted driving. Chameleon takes into account the spatiotemporal variation in service demand and supply, and provides latency and resolution aware task offloading strategies based on partially observable Markov decision process (POMDP). To evaluate the effectiveness of Chameleon, we simulate the availability of vehicular fog nodes at different times of day based on the bus trajectories collected in Helsinki, and use the real-world performance measurements of visual data transmission and processing. Compared with adaptive and random task offloading strategies, the POMDP-based offloading strategies provided by Chameleon shortens the average service latency of task offloading by up to 65% while increasing the average resolution level of processed images by up to 83%.
Highlights
E MERGING visual-based assisted driving applications, such as see-through and cooperative lane-change, involve time-critical and data-intensive computational tasks, such as real-time object recognition and scene understanding from images/video
From the analysis of real-world traffic message channel (TMC) data collected from [11], we find that the variation in the number of client vehicles which fall into the communication range of a specific fog node and the corresponding workload generated by these client vehicles changes on a weekly basis
To identify the workload pattern of vehicular fog nodes, we collected bus trajectories by using the open high-frequency positioning (HFP) API provided by HSL [19] in Helsinki region during the same period as mentioned previously
Summary
E MERGING visual-based assisted driving applications, such as see-through and cooperative lane-change, involve time-critical and data-intensive computational tasks, such as real-time object recognition and scene understanding from images/video. More computing power is required for processing images with higher resolution, which are expected for providing more accurate scene understanding To address these challenges, we propose Chameleon, a task offloading scheme that reduces service latency while increasing the supported quality levels of visual data to be processed within application specific latency constraints, taking into account the mobility of vehicles and the impact of data quality (e.g. resolution) on processing delay. To evaluate the effectiveness of Chameleon, we simulate the scenario of assisted driving in VFC using the real-world vehicular traffic data and applications of image-based object recognition. We develop Chameleon, a novel task offloading scheme that tries to process higher resolution images within application specific latency constraints, taking into account the spatiotemporal variation in vehicular traffic density and the r impact of image resolution on processing delay. Instead of energy consumption, we take a different aspect of task offloading in assisted driving to focus on the trade-off between service latency and quality of data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
