05-05-2012, 01:32 PM
High-speed-camera Image Processing Based LED Traffic Light
Detection for Road-to-vehicle Visible Light Communication
[attachment=21382]
INTRODUCTION
Intelligent Transport System (ITS) has been introduced to
control the traffic problems such as traffic jams and traffic
accidents with the development of information technology.
We conduct research mainly on assistance for safe driving
as an area of ITS. On-vehicle cameras play a great
role in capturing the information of external environment
in many driver assistant systems. Some studies have been
conducted for detecting traffic signs, and signal lights so
on[1][2][3][4][8][9]. In this study, we propose a road-tovehicle
Visible Light Communication(VLC) system using an
on-vehicle high-speed camera as a receiver.
PROPOSED VLC SYSTEM
Figure 1 shows the structure of the proposed VLC system
using LED traffic light as a transmitter and high-speed
camera as a receiver. If the LEDs in the transmitter could
be recognized individually, it is possible to use each of them
as a separate transmitter communicating in parallel at the
same time. In other words, each LED transmits different
2010 IEEE Intelligent Vehicles Symposium
data in parallel and they are received at the same time. As a
result we can dramatically increase the communication speed
by modulating each LED individually. Moreover, we can
communicate with several transmitters and receive different
information in parallel.
Proposed transmitter tracking method
After finding the transmitter, it is tracked only searching
the corresponding cut out image area(Icut) in consecutive
frames. In this paper, at the emission sequence, all LEDs
emit light randomly(Fig. 10). But, when all the LEDs emit
light randomly, it is difficult to track transmitter, because,
the bounding of the transmitter is not appear properly(see
Fig. 9). We propose a new method for this tracking and it
includes two main steps as edge-based tracking and optical
flow-based tracking.
CONCLUSION
In this paper, new transmitter finding and tracking methods
were proposed utilizing high-speed camera image processing
for a road-to-vehicle Visible Light Communication system.
With the proposed methods, all LEDs in the transmitter
can be used for achieving continuous communication, which
was not possible with previous methods. According to the
experiments, new proposals are very effective in desired
finding and tracking. We plan to improve these methods to be
able to find and track traffic lights, when they are overlapped
with other light sources as future steps.
Detection for Road-to-vehicle Visible Light Communication
[attachment=21382]
INTRODUCTION
Intelligent Transport System (ITS) has been introduced to
control the traffic problems such as traffic jams and traffic
accidents with the development of information technology.
We conduct research mainly on assistance for safe driving
as an area of ITS. On-vehicle cameras play a great
role in capturing the information of external environment
in many driver assistant systems. Some studies have been
conducted for detecting traffic signs, and signal lights so
on[1][2][3][4][8][9]. In this study, we propose a road-tovehicle
Visible Light Communication(VLC) system using an
on-vehicle high-speed camera as a receiver.
PROPOSED VLC SYSTEM
Figure 1 shows the structure of the proposed VLC system
using LED traffic light as a transmitter and high-speed
camera as a receiver. If the LEDs in the transmitter could
be recognized individually, it is possible to use each of them
as a separate transmitter communicating in parallel at the
same time. In other words, each LED transmits different
2010 IEEE Intelligent Vehicles Symposium
data in parallel and they are received at the same time. As a
result we can dramatically increase the communication speed
by modulating each LED individually. Moreover, we can
communicate with several transmitters and receive different
information in parallel.
Proposed transmitter tracking method
After finding the transmitter, it is tracked only searching
the corresponding cut out image area(Icut) in consecutive
frames. In this paper, at the emission sequence, all LEDs
emit light randomly(Fig. 10). But, when all the LEDs emit
light randomly, it is difficult to track transmitter, because,
the bounding of the transmitter is not appear properly(see
Fig. 9). We propose a new method for this tracking and it
includes two main steps as edge-based tracking and optical
flow-based tracking.
CONCLUSION
In this paper, new transmitter finding and tracking methods
were proposed utilizing high-speed camera image processing
for a road-to-vehicle Visible Light Communication system.
With the proposed methods, all LEDs in the transmitter
can be used for achieving continuous communication, which
was not possible with previous methods. According to the
experiments, new proposals are very effective in desired
finding and tracking. We plan to improve these methods to be
able to find and track traffic lights, when they are overlapped
with other light sources as future steps.