Collisions between vehicles leaving the road and unforgiving roadside objects such as trees, poles, road signs, etc. constitute a major road safety issue. On the Austrian road network, approximately 7.500 injury crashes occur every year due to run-off-road (ROR) manoeuvres (i.e. 20% of all injury crashes on public roads), contributing 35% to fatalities and 25% to serious injuries. Vehicle restraint systems (VRS) such as guardrails, concrete barriers, terminals or crash attenuators play a decisive role in mitigating the consequences of ROR crashes. Unfortunately, most national road administrations (NRA) do not have a centralized data management, while geo-referenced information on VRS and their safety-related attributes are also not available as digitized data. Researchers from the AIT have developed a novel approach to investigate, classify and evaluate VRS by means of image data processing, towards providing a comprehensive VRS inventory. The information obtained can be used for benefit-cost-analyses, road safety inspections and the evaluation of the effectiveness of different vehicle restraint systems.
Asset management, database, decision tree, geographical information system, inventory control, run-off-road crashes, traffic safety, vehicle restraint system.
 Thomson, R., Fagerlind, H., Martinez, A.V., Amengual, A., Naing, C.L., Lanner, G., Dupre, G., Bisson, O., Garcia, J., Lopez, F., Hallemann, B., Wink, W., Hoschopf, H., Valtonen, J., Gosse, U., Kelkka, M., Ridder, S.d., Hill, J., & Van der Horst, R., RISER –Roadside Infrastructure for Safer European Roads, Deliverable D06 – European Best Practice for Roadside Design: Guidelines for Roadside Infrastructure on New and Existing Roads, 2006.
 Tomasch, E., Sinz, W., Hoschopf, H., Gobald, M., Steffan, H., Nadler, B., Nadler, F., Strnad, B. & Schneider, F., Required length of guardrails before hazards. In Accident Analysis and Prevention, 43(6), pp. 2112–2120, 2011. https://doi.org/10.1016/j.aap.2011.05.034
 Stefan, C., Stütz, R., Tomasch, E., Luttenberger, P. & Klein, C., A risk-based methodology to assess run-off-road crashes on Austrian motorways – the RISKANT project. In International Journal of Safety and Security Engineering, 6(2), pp. 351–361, 2016.https://doi.org/10.2495/safe-v6-n2-351-361
 ASFINAG Service GmbH, Road Safety Programme 2020, Download-Link:https://www.asfinag.at/media/2970/asfinag_vsb2020_english_einseiter_web_100526.pdf,
(accessed 16 May 2019).
 OECD/International Transport Forum (ITF), Towards Zero – Ambitious Road Safety Targets and the Safe System Approach, Publisher: Joint Transport Research Centre, Download: https://www.itf-oecd.org/sites/default/files/docs/08towardszeroe.pdf, 2008 (accessed 03 May 2019).
 EN 1317-2, Road Restraint Systems – Part 2: Performance Classes, Impact Test Acceptance Criteria and Test Methods for Safety Barriers Including Vehicle Parapets, 2011.
 Austrian Standards Institute, Passive Safety of Support Structures for Road Equipment –Requirements and Test Methods, EN 12767, 2011.
 American Association of State Highway and Transport Officials (AASHTO), Manual for Assessing Safety Hardware, 2009.
 Conference of European Directors of Roads (CEDR), CEDR Transnational road research programme, call 2019 (safety: use of vehicle restraint systems), SAVeRS –Defining the Different Parameters Which Can Influence the Need and Selection of VRS,Deliverable D1.1, https://www.cedr.eu/strategic-plan-tasks/research/cedr-call-2012/call-2012-safety/savers-project-results/, September 2014 (accessed 22 May 2019).
 Conference of European Directors of Roads (CEDR), Forgiving Roadside Design Guide, November 2012. Download-Link:https://www.cedr.eu/download/Publications/2013/T10_Forgiving_roadsides.pdf
 Austrian Research Association for Roads, Railways and Transport (FSV), RVS 05.02.31– Vehicle Restraint Systems, Requirements and Installation, October 2011.
 Conference of European Directors of Roads (CEDR), CEDR Transnational Road Research Programme, Call 2019 (Safety: Use of Vehicle Restraint Systems), SAVeRS –Guideline for the Selection of the Most Appropriate Roadside Vehicle Restraint System, Deliverable D3. 1 July 2015.
 Cho, J. & Humenberger, M., Fast patchmatch stereo matching using cross-scale cost fusion for automotive applications. IEEE Intelligent Vehicles Symposium, IV 2015, Seoul, South Korea, IEEE, pp. 802–807, 2015.
 Zinner, C. & Humenberger, M., Distributed real-time stereo matching on smart cameras,Fourth ACM/IEEE International Conference on Distributed Smart Cameras, Atlanta, GA, USA - August 31–September 4, 2010, ACM, pp. 182–189, 2010.
 Fang, L., Yang, B., Chen, C. & Fu, H., Extraction 3d road boundaries from mobile laser scanning point clouds, 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services, ICSDM, pp. 162–165, 2015.
 Golovinskiy, A., Kim, V.G. & Funkhouser, T.A., Shape-Based recognition of 3d point clouds in urban environments, IEEE 12th International Conference on Computer Vision, pp. 2154–2161, 2009.
 Golparvar-Fard, M., Balali V. & de la Garza J.M., Segmentation and recognition of highway assets using image-based 3d point clouds and semantic texton forests. Journal of Computing in Civil Engineering, 29(1), p. 04014023, 2012. https://doi.org/10.1061/(asce)cp.1943-5487.0000283
 Shotton, J., Johnson, M. & Cipolla, R., Semantic texton forests for image categorization and segmentation. IEEE Conference on Computer Vision and Pattern Recognition,pp. 1–8, 2008. https://doi.org/10.1109/cvpr.2008.4587503
 Verma, B., Zhang, L. & Stockwell, D.R.B., Roadside Video Data Analysis: Deep Learning- Deep Learning, Springer, p. 711, 2017.
 Neuhold, G., Ollmann, T., Bulò, S.R. & Kontschieder, P., The mapillary vistas dataset for semantic understanding of street scenes. IEEE International Conference on Computer Vision, ICCV, pp. 5000–5009, 2017.
 Ordóñez, C., Cabo, C. & Sanz-Ablanedo, E., Automatic detection and classification of pole-like objects for urban cartography using mobile laser scanning data. Sensors,17(7), p. 1465, 2017. https://doi.org/10.3390/s17071465