METHOD AND A SYSTEM FOR GENERATING A MACHINE LEARNING MODEL FOR REDUCING A LOCATION ERROR OF READINGS OF ROAD SIGNS SENSED BY CONNECTED VEHICLES
A method and a system for generating a machine learning model for reducing a location error of readings of road signs sensed by connected vehicles, said method comprising: obtaining an incoming stream of readings of road signs captured by connected vehicles traveling along roads, wherein each reading contains a location of a road sign and road sign metadata associated therewith; applying a clustering algorithm to group together readings associated with a common road sign in separate groups; comparing the locations of each group to respective tagged road-signs dataset associated with a correct location, to yield a correction vector for each cluster; and training a machine learning model to correct the location of the readings in each group by learning the correction vectors.
1 . A method of generating a machine learning model for reducing a location error of readings of road signs sensed by connected vehicle, said method comprising:
obtaining an incoming stream of readings of road signs captured by connected vehicles traveling along roads, wherein each reading contains a location of a road sign and road sign metadata associated therewith;
using a clustering algorithm to group together readings associated with a common road sign into clusters;
comparing the locations of the readings in each cluster to respective tagged road-signs dataset associated with a correct location of the road sign associated with the cluster, to yield a correction vector; and
training a machine learning model to correct the location of the readings in each group by learning the correction vector.
2 . The method according to claim 1 , further comprising running the machine learning model on the training dataset of readings.
3 . The method according to claim 1 , further comprising repeating: the clustering, the comparing, and the training until the machine learning model stops improving.
4 . The method according to claim 1 , further comprising using the trained machine learning model to repair the entire raw dataset.
5 . The method according to claim 1 , further comprising running the same clustering method to produce the location of signs from all over the raw dataset.
6 . A system for generating a machine learning model for reducing a location error of readings of road signs sensed by connected vehicle, said system comprising:
a data processing module configured to obtain an incoming stream of readings of road signs captured by connected vehicles traveling along roads, wherein each reading contains a location of a road sign and road sign metadata associated therewith;
a clustering module configured to use a clustering algorithm to group together readings associated with a common road sign in clusters;
a comparing module configured to compare the locations of each cluster to respective tagged road-signs dataset associated with a correct location, to yield a correction vector; and
a training module configured to train a machine learning model to correct the location of the readings in each group by learning the correction vectors.
7 . The system according to claim 6 , further comprising running the machine learning model on the training dataset of readings.
8 . The system according to claim 6 , further comprising repeating: the clustering, the comparing, and the training until the machine learning model stops improving.
9 . The system according to claim 6 , further comprising using the trained machine learning model to repair the entire raw dataset.
10 . The system according to claim 6 , further comprising running the same clustering method to produce the location of signs from all over the raw dataset.
11 . A non-transitory computer readable medium for generating a machine learning model for reducing a location error of readings of road signs sensed by connected vehicles, the computer readable medium comprising a set of instructions that when executed cause at least one computer processor to:
obtain an incoming stream of readings of road signs captured by connected vehicles traveling along roads, wherein each reading contains a location of a road sign and road sign metadata associated therewith;
apply a clustering algorithm to group together readings associated with a common road sign into groups;
compare the locations of each cluster to respective tagged road-signs dataset associated with a correct location of the road sign associated with the group, to yield a correction vector; and
train a machine learning model to correct the location of the readings in each cluster by learning the correction vectors.
12 . The non-transitory computer readable medium according to claim 11 , further comprising a set of instructions that when executed cause the at least one computer processor to run the machine learning model on the training dataset of readings.
13 . The non-transitory computer readable medium according to claim 11 , further comprising a set of instructions that when executed cause the at least one computer processor to repeat the clustering, the comparing, and the training until the machine learning model stops improving.
14 . The non-transitory computer readable medium according to claim 11 , further comprising a set of instructions that when executed cause the at least one computer processor to use the trained machine learning model to repair the entire raw dataset.
15 . The non-transitory computer readable medium according to claim 11 , further comprising a set of instructions that when executed cause the at least one computer processor to run the same clustering method to produce the location of signs from all over the raw dataset.