Main Content

Evaluate lane boundary models against ground truth

evaluates candidate lane boundary models, `numMatches`

= evaluateLaneBoundaries(`boundaries`

,`worldGroundTruthPoints`

,`threshold`

)`boundaries`

,
against lane boundaries formed by world coordinate ground truth points,
`worldGroundTruthPoints`

, and returns the total number of
matching lane boundaries, `numMatches`

. If all points within
a candidate boundary are within the lateral distance
`threshold`

of the ground truth lane boundary, then that
boundary is considered a valid match (true positive).

`[`

also returns
the total number of misses (false negatives) and false positives,
using the previous inputs.`numMatches`

,`numMissed`

,`numFalsePositives`

]
= evaluateLaneBoundaries(___)

`[___] = evaluateLaneBoundaries(___,`

specifies
the `xWorld`

)*x*-axis points at which to perform the comparisons.
Points specified in `worldGroundTruthPoints`

are
linearly interpolated at the given *x*-axis locations.

`[___] = evaluateLaneBoundaries(`

compares the boundaries against ground truth models that are specified in an
array of lane boundary objects or a cell array of arrays.`boundaries`

,`groundTruthBoundaries`

,`threshold`

)

`[___,`

also returns
the assignment indices that are specified in `assignments`

]
= evaluateLaneBoundaries(___)`groundTruthBoundaries`

.
Each boundary is matched to the corresponding class assignment in `groundTruthBoundaries`

.
The `k`

th boundary in `boundaries`

is
matched to the `assignments(k)`

element of `worldGroundTruthPoints`

.
Zero indicates a false positive (no match found).