In this paper, a decision support system is proposed to assist an analyst in updating the highway roadside asset inventory. The feasibility of the system is tested with assets along an 8 km section of the A27 highway on the south coast of England, UK. Survey data from a vehicle equipped with a single forward-facing camera and a GPS-enabled inertial measurement unit, aerial imagery of the highway, and the asset inventory are fused to develop the system. The camera on the vehicle is calibrated so that assets may be automatically located within the survey images. The assets are then classified by a state-of-the-art convolutional neural network. Therefore, those assets recorded correctly in the inventory and those needing further manual inspection are automatically identified. Three different asset types are considered (traffic signs, matrix signs, and reference marker posts), and overall 91% of the assets in a withheld test set are verified automatically. Thus the analyst is presented with a much smaller set of assets for which the inventory is incorrect and which require further inspection. We therefore demonstrate the value in fusing multiple data sources to develop decision support systems for transportation asset monitoring.

In this paper, we investigate the feasibility of using highway traffic officers (TOs) for transportation asset management (TAM) alongside their primary role of incident response. Asset data, typically captured via highway surveys on an annual basis, are unsuitable for those assets whose condition might rapidly change, such as vegetation, streetlights, guardrails, or drainage systems. Therefore, we considered as a proof-of-concept, whether data collected from dashboard cameras installed in TO vehicles might provide analysts with near real-time asset data across an entire highway network. We considered a case study of a dedicated TO fleet deployed on the strategic road network (SRN) in England, UK, and developed a simulation based on publicly available data sets. Within the simulation, TOs patrolled under two distinct regimes and responded to dynamically generated incidents. The first regime aimed to minimize the the fleet’s incident response time, and the second aimed to maximize the fleet’s coverage, with the aim of capturing asset data across the entire highway network. Overall, our simulations showed that the TOs deployed for TAM reduced the SRN junction-to-junction section intervisit time by around 1 h 45 min, whereas their incident response time only increased by about 4 min. Moreover, 17% of SRN sections were not visited at all when the TOs prioritized fast incident response, which was reduced to 2% when the TOs prioritized the capture of asset data.

No abstract