Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter.
Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.
OCR for page 10
10
Project 4: Lane Change Field event), and a batch of 50 driver images spaced every 0.2 s for
Operational Study 5 min at the beginning of the trip and every 5 min thereafter.
In addition to the video data, roughly 400 separate data sig-
The main purpose of this VTTI study was to examine lane nals were collected, including data for vehicle and driver infor-
change behavior. The study monitored the commutes of mation, vehicle position, heading and motion, driver control
16 participants for approximately 1 month. Drivers commuted inputs, RDCWS driver displays, RDCWS intermediate values,
on Route 460 through the New River Valley or on Interstates roadway environment, RDCWS and subsystem diagnostic
81 and 581 in the Roanoke Valley. Commutes were 25 or more information, RDCWS radar data, and audio data.
miles in each direction to and from work. The data set has a valid time stamp that can be used to link
Data would begin recording when a vehicle reached 35 mph to weather data and to link valid GPS data to other environ-
and stopped recording when the vehicle slowed to 25 mph. In mental data, such as traffic count and work zones (7).
all, 24,000 vehicle miles of travel (VMT) data were collected.
More than 8,000 lane changes were identified in the full data
set and then classified by urgency and severity. Approximately Project 6: The 100-Car Study
500 of the more urgent lane change events were analyzed in The 100-Car Study was undertaken by VTTI, which collected
depth. large-scale naturalistic driving data from 100 vehicles in north-
Video data were recorded on five channels: driver's face, ern Virginia for approximately 18 months (12 to 13 months
forward roadway, rear view, and two side views. Data were per vehicle). Drivers were given no special instructions, and the
saved using 8-mm videotapes. Besides the video data, the vehi- majority (78 out of 100) drove their own vehicles. The result-
cle network information collected speed, accelerator, brake ing data set has 6.4 terabytes (TB) of approximately 2 million
pedal, steering wheel, and turn signal data, as well as lateral VMT from 241 primary and secondary driver participants with
acceleration, radar-collected information (one front and two a 12- to 13-month data collection period for each vehicle. The
rear sensors), and reduced data, such as eyeglance behavior and 8,295 incidents recorded included 15 police-reported crashes,
road type and geometry (6). 67 other crashes, and 761 near crashes. A variety of crash risk
factors were analyzed.
Project 5: Road Departure Continuous video was collected on four channels at 30 Hz:
Crash Warning System Field driver's face, instrument panel (over driver's right shoulder),
Operational Test forward roadway, and rear roadway. The final data set contains
43,000 h of video. Vehicle network information (speed, brake
The project was conducted under a cooperative agreement pedal, throttle, and turn signal); GPS (latitude, longitude, and
between U.S. DOT and the University of Michigan Trans- heading); and X, Y, and Z acceleration were also collected. For-
portation Research Institute (UMTRI) and its partners: Vis- ward radar and rear radar were used to collect surrounding
teon Corporation and AssistWare Technologies. This FOT was information. Data reduction generated other data, such as
designed to assess a Road Departure Crash Warning System driver status, traffic flow, vehicle status, seat belt usage, and road
(RDCWS). Two areas were assessed: safety-related changes in type and geometry.
driver performance that may have been attributed to the sys- Because of a malfunction in the GPS subsystem, the time data
tem and levels of driver acceptance in key areas. Testing are unreliable. Consequently, it is not possible to link some
involved 11 passenger sedans equipped with the RDCWS environmental data from external databases, such as work zone
and a DAS that collected performance, video, and audio data and traffic condition data. The weather variable that has
data. Seventy-eight drivers participated for 4 weeks each, and been coded in the reduced data set is available (89).
the resulting data set captured 83,000 mi of driving. Analysis
showed that drivers improved lane-keeping and reduced lane
Project 7: Drowsy Driver
excursions while the RDCWS was active. Driver acceptance of
Warning System Field
the system was relatively positive, especially for the lateral drift
Operational Test
component of the system.
Two video cameras were mounted on the vehicle's A-pillar: The Drowsy Driver Warning System (DDWS) study was con-
one forward-looking and one aimed at the driver. The inside ducted by VTTI. The main purpose was to examine the effec-
camera also had a set of infrared light-emitting diodes (LEDs) tiveness of a mechanism that alerted drivers that they were
that provided nighttime illumination of the driver's face. about to fall asleep (monitored using a PERCLOS meter).
The images of the driver's face camera were captured in three VTTI instrumented 34 trucks with an experimental warning
modes: at 0.5 Hz when the data system was on, during an system, video cameras, and a DAS. The final data set included
RDCWS alert captured for 8 s (4 s before and 4 s after the 2.3 million VMT, 12 TB of data, and 46,000 h of driving.
