Share this article

 Email

 Print

 

Republish this article

The text of this article by Futurity is licensed under a Creative Commons Attribution-No Derivatives License.

More
Science & Technology

Flyby radar maps Saturn’s Earth-like moon

To let graphene boost batteries, add boron

Earth’s iron core is not ‘rock solid’

Wait for it: Ants pick perfect time to forage

Cow blood prevents globs of nano gold

Inbreeding threatens India’s wild tigers

Earthquake sensors on seafloor track whale songs

‘Simple path’ from fish hips to 4-legged walk

Ape-like ear bones found in hominin skull

“Our prototype system has proved in many ways that a commercial-scale automated crack sealing system is viable,” says Jonathan Holmes, the Georgia Tech Research Institute research engineer currently leading the project, which began in 2003.

“We demonstrated solutions to technical challenges—including the high-speed firing of nozzles, automated crack detection, and navigation—in a real-time, limited-scale system.”

In addition to saving money on road maintenance, systems like the prototype could keep workers safe from traffic, say the developers. (Credit: Jonathan Holmes/Georgia Tech)

An automated crack sealing system would increase worker safety levels, require fewer personnel, and increase the amount of roadway covered per day. In addition, the system could save transportation departments money because sealing cracks extends the time before a roadway needs to be completely repaved.

The prototype system, which was mounted on a trailer, consists of a stereo camera, light-emitting diodes (LEDs) of two different colors, and an assembly to provide a continuous supply of sealant to longitudinal and transverse sealant distribution systems. The operation requires only one worker to drive the vehicle pulling the trailer.

As the system travels along a lane, the LEDs illuminate the road in two directions—parallel and perpendicular to the road—and the stereo camera takes two pictures of the road simultaneously, which are analyzed with algorithms.

Within 100 milliseconds of taking the images, the computer onboard the trailer generates a “crack map” specifying the location and shape of any cracks shown in the images.

Based on the cracks found in the image, the master controller instructs the sealant applicator valves when to fire. To fill longitudinal cracks, a single dispensing nozzle capable of continuous operation attaches to a linear servo axis. The transverse sealant distribution system consisted of 12 nozzles spaced evenly across one foot.

The developers believe the transverse and diagonal distribution prototype could be replicated and joined together to service a full-width roadway lane.

In multiple road tests, the prototype system proved to be a successful proof-of-concept for the automation of crack sealing operations.

Down the road

Before transportation departments can successfully implement a full-scale system, several issues must be addressed, according to Holmes. First, the crack-detection algorithm will need to be improved. In tests on more than 100,000 images, the program correctly identified more than 83 percent of the cracks.

“Our crack detection algorithm was limited because we used a vision-based system, which was confounded by regions of high contrast caused by features other than pavement cracks, including dark stains in the pavement, lane stripes, raised-pavement markers, crack sealant, and debris,” says Holmes.

“A full-scale system may require a fusion of multiple imaging sensors, such as a 3-D laser scanning system.”

Holmes also suggests changes will be necessary in the way the sealant is supplied to the longitudinal and transverse distribution systems before a full-scale system can be realized.

Additional researchers from the Georgia Department of Transportation Office of Materials and Research and the Georgia Tech Research Institute also worked on this project.

More news from Georgia Tech: www.gatech.edu/newsroom/