TRAFFIC MONITORING FROM AIRBORNE LIDAR 
- FEASIBILITY, SIMULATION AND ANALYSIS 
W. Yao 3 *, S. Hinz 3 , U. Stilla” 
3 Remote Sensing Techbology, Technische Universitaet Muenchen, Arcisstr.21, 80290 Munich, Germany 
b Photogrammetry and Remote Sensing, Technische Universitaet Muenchen, Arcisstr.21, 80290 Munich, Germany 
- (wei.yao, stefan.hinz , uwe.stilla)@bv.tum.de 
Commission III, WG III/5 
KEY WORDS: Airborne LiDAR, traffic monitoring, vehicle model, feasibility, simulation 
ABSTRACT: 
Automatic acquisition and analysis of traffic-related data has already a long tradition in the remote sensing community. Similarly 
airborne laser scanning (ALS) has emerged as an efficient means to acquire the detailed 3D large-scale DSMs. The aim of this work 
is to initialize research work on using ALS to extract the traffic-flow information focusing on urban areas. The laser data acquisition 
configuration has firstly to be analyzed in order to obtain the optimal performance with respect to the reconstruction of traffic- 
related objects. Mutual relationships between various ALS parameters and vehicle modeling in the laser points are to be elaborated. 
Like other common tasks in object recognition, vehicle models for detection and motion indication from the laser data are presented; 
moreover, an ALS simulator is implemented to clarify and validate motion artifact in laser data. Finally, a concept for recognizing 
vehicles are proposed based on a vehicle and context model, which establishes a direct working flow simulating the human inference 
routine. 
1. INTRODUCTION 
Automatic traffic monitoring has evolved to an important and 
active research issue in the remote sensing community during 
the past years, as indicated by the special issue of ISPRS 
Journal in 2006 - “Airborne and spacebome traffic monitoring” 
(Hinz et al., 2006). Transportation represents a major segment 
of the economic activities of modem societies and has been 
keeping increase worldwide which leads to adverse impact on 
our environment and society, so that the increase of transport 
safety and efficiency, as well as the reduction of air and noise 
pollution are the main task to solve in the future. 
On the one hand, today’s road monitoring systems are mainly 
equipped by a series of sensors like induction loops, overhead 
radar sensors and stationery video cameras, etc. They all deliver 
accurate, reliable, timely, yet merely point-wise measurement. 
On the other hand spacebome and airborne sensors can 
complement the ground-based collection and give us synoptic 
views of complex traffic situations. With the recent advances in 
sensor technology, a number of approaches for automatically 
detecting vehicles, tracking vehicles and estimating velocity 
have recently been developed and intensively analyzed, using 
different air-and spacebome remote sensing platforms, e.g. 
Synthetic aperture radar (SAR), infrared(IR) cameras, frame 
and linear pushbroom optical cameras. However, so far there 
have been few works conducted in relation to traffic analysis 
from laser scanners. 
The most relevant and up-to-date research to our work is, 
according to our knowledge, from Toth & Grejner-Brzezinska 
(2006), Grejner-Brzezinska et al., (2004) and Toth et al., (2003). 
In this work an airborne laser scanner coupled with digital 
frame imaging sensor was adopted to analyze transportation 
corridors and acquire traffic flow information automatically. 
They have tried to extract traffic-related static and dynamical 
data as part of the regular topographic mapping. Vehicle 
velocity can be estimated either by analyzing motion artefacts 
in the laser data or by vehicle tracking in image sequences with 
reasonable acquisition rate. The experiences gained so far by 
their test flying-campaigns showed that the two sensors have 
different strengths and weakness for the various data processing 
tasks and, in most cases, they complement each other. It can be 
declared that the combination of airborne laser and imaging 
sensors can provide valuable traffic flow data that can 
effectively support traffic monitoring and management. But the 
extensive testing of this system is limited to highway, freeway 
and other heavily travelled roads where occlusions cast by 
buildings, vegetations and some other anomaly objects (e.g. 
guild rails) are rare in the image and laser data. 
Another important category of research field related to our 
scope is 3D object recognition from laser radar data, which is 
primarily dedicated to the military Automatic Target 
Recognition (ATR) application (Gronwall et al., 2007; Steinvall 
et al., 2004; Gronwall, 2006; Ahlberg et al., 2003). The scene 
can be scanned from different platforms and perspectives, such 
as terrestrial or airborne platforms. The biggest difference 
distinguishing the use of laser sensor for urban traffic analysis 
from for the military application lies in data coverage and the 
application objective. The military applications feature small 
field of view (FOV) and very high-resolution (very high density 
of laser points) of laser data recording. The data acquisition 
process is target-orientated and limited to a relative small 
coverage, the interest region or object is scanned with very high 
resolution and concentrated energy. Most of algorithms 
developed within this scope aim at recognition of the object 
type (e.g. classification of tank) and pose estimation (e.g. 
orientation of a tank); some even tried to detect fine sub 
structures of object (e.g. barrel and turret of a tank). Among 
these algorithms, model-based shape matching or fitting 
strategies have been most frequently applied to the laser data in 
order to find and recognize the corresponding object class and 
its status (Koksal et al., 1999; Zheng & Der, 2001; Johansson & 
Moe, 2005). 
* Corresponding author. 
593