Method, electronic device, and system for detecting overspeeding
A method of detecting overspeeding for a vehicle, the method including obtaining historical trajectory data of a fleet of geographical areas from an electronic database; determining, by a microprocessor of a server, a distribution of speed of the historical trajectory data for each geographical area; based on the distribution of speed, determining, by a microprocessor of an electronic device associated with the vehicle, that a current speed of the vehicle is above a threshold speed corresponding to a pre-determined percentile of the distribution. A system and a computer-readable medium storing computer executable code for the method.
1. A mobile device associated with a vehicle, the mobile device comprising:
a processor;
a trajectory data acquisition module, configured to acquire current trajectory data of the vehicle;
a memory, coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to:
receive, from a remote server, data for a geographical area in which the vehicle is located, the data including, for each grid coordinate in the geographical area, a distribution of speed information associated with each grid coordinate, the distribution of speed information including at least one threshold value associated with the grid coordinate, wherein the at least one threshold value is calculated based on a selected percentile of the distribution of speed information associated with each grid coordinate;
identify, based on the current trajectory data, a current grid coordinate in the geographical area in which the vehicle is currently traveling;
determine, based on the current grid coordinate and a current speed of the vehicle, that the vehicle is one of (i) exceeding the at least one threshold value, and (ii) at risk of exceeding the at least one threshold value within a predetermined period of time; and
update a display of the mobile device to change an appearance of the display to display an alert.
2. The mobile device of claim 1 , wherein the distribution of speed information associated with the geographical area is generated by:
determining a historical distribution of speed of a set of historical trajectory data for the geographical area, the set of historical trajectory data received from a plurality of devices that have traveled in the geographical area; and
de-skewing the historical distribution of speed based on an inverse proportional relation to a speed associated with each of a plurality of datapoints of the historical distribution of speed to produce the distribution of speed information.
3. The mobile device of claim 1 , further comprising:
determining, based on the current trajectory data of the vehicle, a probability of the vehicle exceeding the at least one threshold value within a predetermined period of time; and
determining that the vehicle is at risk of exceeding the at least one threshold value if the determined probability exceeds a probability threshold.
4. The mobile device of claim 3 , wherein the determined probability is calculated by a trained classifier, the trained classifier trained based on the distribution of speed information.
5. The mobile device of claim 4 , wherein the classifier is trained on a remote training server and wherein pre-trained weights of the trained classifier are uploaded from the remote training server to the mobile device thereby providing the trained classifier on the mobile device.
6. The mobile device of claim 4 , wherein the trained classifier is further trained based on contextual data comprising contextual information, wherein determining that the vehicle is at risk of exceeding the at least one threshold value is further based on current contextual data associated with the vehicle.
7. The mobile device of claim 6 , wherein the contextual data comprises training weather data, and the current contextual data comprises current weather data.
8. The mobile device of claim 6 , wherein the contextual data comprises training driver profile data and the current contextual data comprises driver profile data of a driver associated with the vehicle, wherein each of the training driver profile data and the driver profile data comprises respective vehicle characteristics data and/or driver features.
9. The mobile device of claim 6 , wherein the contextual data and the current contextual data comprise one or more of: time of a day, a day of a week, and a public holiday data.
10. The mobile device of claim 6 , wherein the contextual data and the current contextual data comprise one or more of: a road condition data, a road characteristics data, a current traffic pattern, and a neighborhood type.
11. A method for operating a mobile device associated with a vehicle, the method comprising:
determining, based on a trajectory data acquisition module, current trajectory data of the vehicle;
receiving, from a remote server, data for a geographical area in which the vehicle is located, the data including, for each grid coordinate in the geographical area, a distribution of speed information associated with each grid coordinate, the distribution of speed information including at least one threshold value associated with the grid coordinate, wherein the at least one threshold value is calculated based on a selected percentile of the distribution of speed information associated with each grid coordinate;
identifying, based on the current trajectory data, a current grid coordinate in the geographical area in which the vehicle is currently traveling;
determining, based on the current grid coordinate and a current speed of the vehicle, that the vehicle is one of (i) exceeding the at least one threshold value, and (ii) at risk of exceeding the at least one threshold value within a predetermined period of time; and
alerting a user of the mobile device of an unsafe speeding condition.
12. The method of claim 11 , wherein alerting the user includes one of: (i) updating a display of the mobile device to display an alert, and (ii) causing the mobile device to issue an audible alert.
13. The method of claim 11 , wherein the distribution of speed information associated with the geographical area is generated by:
determining a historical distribution of speed of a set of historical trajectory data for the geographical area, the set of historical trajectory data received from a plurality of devices that have traveled in the geographical area; and
de-skewing the historical distribution of speed based on an inverse proportional relation to a speed associated with each of a plurality of datapoints of the historical distribution of speed to produce the distribution of speed information.
14. The method of claim 11 , further comprising:
determining, based on the current trajectory data of the vehicle, a probability of the vehicle exceeding the at least one threshold value within a predetermined period of time; and
determining that the vehicle is at risk of exceeding the at least one threshold value if the determined probability exceeds a probability threshold.
15. The method of claim 14 , wherein the determined probability is calculated by a trained classifier, the trained classifier trained based on the distribution of speed information.
16. The method of claim 15 , wherein the classifier is trained on a remote training server and wherein pre-trained weights of the trained classifier are uploaded from the remote training server to the mobile device thereby providing the trained classifier on the mobile device.
17. The method of claim 15 , wherein the trained classifier is further trained based on contextual data comprising contextual information, wherein determining that the vehicle is at risk of exceeding the at least one threshold value is further based on current contextual data associated with the vehicle.
18. The method of claim 17 , wherein the contextual data comprises training weather data, and the current contextual data comprises current weather data.