How The System Is Designed

The system relies on a simple model of a road, based upon how people perceive what a road is. Simply put, a road is a smooth path largely consistently colored with a contrasting color from its surroundings or delineations. This means the important aspects of a road are its flatness and its color in that order.

Here is an example road:

A largely straight unmarked road through a lightly wooded area with a clearing to the immediate left on a cloudy afternoon with some snow on the edges of edges of the road where it was mounded from snowplows. Most of the unpacked snow has melted leaving some wet areas on the road surface.

Flatness

Flatness means there is no change in slope across a surface. One way a discretized surface can be modeled is by using unit vectors perpendicular to the surface known unit normal vectors. Where the surface is flat, difference between these vectors is zero

Using a 3D sensor, the depth is gathered then converted to a point cloud. The point cloud is then converted to a map of unit surface normal vectors. By taking the difference of the unit normal vectors to their neighbors, The rate of change of the surface is determined. If this rate exceeds the rate at which the vehicle at speed could travel over, it is excluded as eligible road surface.

This is the largest area directly in front of the vehicle that is sufficiently flat:

An area highlighted in red beginning about 2 meters in front of the vehicle extending beyond the width of the road in most areas along its length of approximately 30m, particularly along the left where a plowed snowbank maintains level with the road as the ground underneath forms a gully and along the right side where the curbing collapsed and sand has filled the area to be level with the road surface.

Color

Roadway surface is typically well defined and fairly uniform in color, however large amounts of variance exists due to inconsistent wear, repairs, shade, and dryness. This variance requires a solution that is adaptive to the local conditions of the surface.

Adaptation is accomplished by sampling the surface directly in front of the vehicle and the sampled region's variance is determined. As the model is based upon human perception and the variance in the road surface color is primarily in lightness, conversion to a color space more consistent with human perception is required.

This is the sampled area:

A small area roughly 2 to 3 meters in front of the vehicle and about 1 vehicle width wide highlighted in a red rectangle.

This is the areas of the image that closely match the color of the sampled road within allowed variance:

A monochrome image with the color matched areas shown in white. Most of the road has been color matched except for very wet areas near the vehicle and a very dry area about 15m in front of the vehicle. Mostly melted snow, especially on the nearby rise to the left of the road has also been matched as well as the edges of the trees where the sky shines through.

Putting Them Together

Since a road must be flat enough to travel on and must contrast with the surrounding areas if it is unmarked, the two filters can be combined in a logical and.

This is the largest flat area that closely matches the color of the sampled road:

An area beginning about 2 meters in front of the vehicle extending the whole width of the road in most areas along its length of approximately 30m with some areas extending beyond the width of the road and others not extending the full width of the road.

After some filtering, this area remains:

A similar image to the one above with a simplified perimeter. This has led to some artifacts extending beyond the width of the road on the left, but is has filled the voids in the shape.

Extracting the outside of the blob, the left and right edges of the road are determined shown in blue and red, respectively:

The same image to the one above with the top and bottom of the blob removed to denote the edges of the road.

Note the large outcrop on the right side line that extends beyond the edge of the road. This is due to the area being of similar color and flatness to the rest of the road. Also note the areas of outcrop on the left side line that extend into to the snowbank. This is due to the coarseness of the filtering pattern. These artifacts demonstrate the need for improved filtering in the prototypes.

Constraints

A few notes on the constraints

The "no obstacles to vision" constraint is for simplification in the early systems that is expected to be removed down the road.

There are few, if any, unmarked roads in America that have a speed limit over 40 mph (at least in my area). If this project is expanded to consider other countries where high speed unmarked roads are present (like the UK), this constraint will have to be adjusted. 60 mph would likely be a reasonable upper bound for the system.

The perception time of an attentive human driver sits around 500 ms and includes making a decision based on the stimulus. As this system was only concerned with the perception of the lines, there needed to be some time to compute potential commanded actions.


Citations

  1. Driver Reaction Time, Marc Green

© 2021 Unmarked Navigation
Inquiries