Panoptes: Crowd-sourced Cars with a Cause

Abstract

There is no consolidated, integral, quantifiable, granular, updated source of information for the roads we traverse and the environment we live in everyday. This leads to ambiguity about road conditions, which is tolerable during normal conditions but extremely problematic in adverse conditions such as snow blockages, water-logging due to storms, degraded roads and potholes. Without such knowledge, city authorities cannot take effective action against such problems. Also, one only has knowledge about ones immediate surroundings in a car, and not what to expect further down the road. Our approach is to deploy a number of embedded modules capable of sensing, computing and reporting, each of which can simply be plugged into any vehicle. Hence this enables each vehicle's connectivity to the cloud and larger coverage as compared to static sensors. The data reported by each module itself might be prone to errors. Therefore, the cloud crowd sources the data from these modules and merges it to increase confidence in the information. Our work, Panoptes, demonstrates these aspects through crowdsourced pothole detection for city roads.

Pavement Management Utilizing Mobile Crowd Sensing

“…Additionally, some filters were utilized for collecting metadata, categorizing the data access patterns [78], directly measuring impulse patterns [79], and amplifying the acceleration signals [80]. e most popular filters in this topic included high-pass filter [81], low-pass filter [82,83], and moving average filter [84]. Giacomo Alessandroni et al [85] improved a fixed first-order low-pass filter by computing a prediction filter with the Levinson-Durbin recursion.…”