Abstract:
This research presents the development of an economical Level-of-Service (LOS) estimation
model using GPS data in a mixed traffic condition, with a specific focus on defining clusters
based on the categories within the existing Highway Capacity Manual (HCM) definitions of
motorised LOS, for practical application. The study aims to enhance the representation of Sri
Lankan traffic conditions, predominantly observed on 2-lane roads, particularly within the LOS
D and E categories where the majority of typical Sri Lankan traffic situations occur. The data
collection scope encompasses the entirety of Sri Lanka to ensure the generation of more
representative values for the defined clusters. As clusterisation parameters, Average Travel
Speed which is a reflection of mobility, Percentage Time Spent Following another vehicle and
the Percentage Free Flow Speed which is a ratio of current speed to the posted speed limit were
used in the same manner as HCM 2016 - 15-2.
It showcases the utilisation of two CNN based image processing models developed, one for
assessing the ‘following’ and ‘non-following’ states and the other to assess the types of road
(road classes), using the Google Colaboratory platform, for the analysis of geo-tagged video
collected through the Transcend DrivePro 250 and their combination with 1 Hz GPS data
collected by the Qtravel GPS device, which includes parameters such as speed, heading local
date and time. Additionally, application of unsupervised K means clustering, which finds k
centroids and then assigns each data point to the closest cluster while minimising the size of
the centroids, to define clusters corresponding to the HCM definitions. The proposed
methodology and model aim to provide an improved representation of LOS in Sri Lanka's
traffic conditions, considering the unique characteristics of the road network and the
predominant traffic scenarios observed in the country. The research findings, produce a table
containing parameters similar to HCM 15-2 (Motorised LOS parameters for 2 lane roads) but
in a practical sense instead of a planning tool.
PFFS exceeded 100% due to speed limit
choice (50 km/h) for class 03 roads and FCD
non-compliance. Cluster 5 needs to be
checked against road capacity levels.
Adjusting limits in the clustering model can
eliminate any potential issues. However, the
primary objective has been achieved for
representative LOS clusterisation from GPS
and geo-tagged video data.