Bump alert

1. A method of bump alert generation for driving, the method comprises:

receiving, by a vehicle computerized system, a visual bump indicator that is visible before driving over a bump;

obtaining sensed information regarding an environment of a vehicle;

processing the sensed information, wherein the processing comprises:

processing, by applying a machine learning process using signatures generated at an iterative process, selected video information segments of the sensed information; and

searching, by the machine learning process, for a signature representing the visual bump indicator based on the processed selected video information segments;

determining whether the vehicle approaches the bump;

generating, based on the determining, a bump alert indication;

determining, in response to the generating, a recommended driving behavior by applying, at the machine learning process, a weighted sum of a top frequency of occurrences of driving behaviors of vehicles captured in video information and telemetric information obtained during driving sessions of the vehicles when approaching bumps; and

applying the recommended driving behavior, wherein the applying comprises controlling at least one of a speed and a direction of driving of the vehicle, wherein the recommended driving behavior is a weighted sum of two or more top frequency of occurrences driving behaviors of a plurality of driving behaviors of vehicles when approaching bumps, the driving behaviors are captured in video information and telemetric information obtained during driving sessions of the vehicles,

wherein the recommended driving behavior is indicative of at least one of a controlled driving speed of the vehicle, and a direction of driving of the vehicle.

2. The method according to claim 1 , wherein a determining of the event that is suspected as involving driving over the bump comprises searching, in the telemetric information, for a mechanical indication that a front of the vehicle rose and then fell within a distance of less than a meter.

3. The method according to claim 1 , comprising determining, based on the telemetric information acquired before the event that is suspected as involving driving over the bump and in timing proximity to the event that is suspected as involving driving over the bump, the recommended driving behavior.

4. The method according to claim 1 , comprising determining the recommended driving behavior before reaching the event that is suspected as involving driving over the bump, wherein the determining is based on (a) telemetric information acquired during the event that is suspected as involving driving over the bump, and (b) telemetric information acquired before the event that is suspected as involving driving over the bump and in timing proximity to the event that is suspected as involving driving over the bump.

5. The method according to claim 4 , comprising generating a bump map that is indicative of a location of the bump and locations of other bumps of a bump class.

6. The method according to claim 1 , wherein the applying of the machine learning process comprises classifying bumps to bump classes.

7. The method according to claim 6 , wherein the visual bump indicator is used to identify the bump and any other bump that belongs to a same bump class as the bump.

8. The method according to claim 1 , comprising obtaining other video information segments of the video information; wherein the processing comprises processing the other video information segments and the selected video information segments to find the visual bump indicator.

9. The method according to claim 8 , wherein the processing comprises applying a machine learning process on the selected video information segments.

10. The method according to claim 1 , wherein the bump alert indication is a tactile bump alert indication.

11. A non-transitory computer readable medium that stores instructions that once executed by one or more processing circuits of a vehicle computerized system cause the one or more processing circuit to:

receive a visual bump indicator that is visible before driving over a bump;

obtain sensed information regarding an environment of a vehicle;

process the sensed information, wherein the processing comprises:

processing, by applying a machine learning process using signatures generated at an iterative process, selected video information segments of the sensed information; and

searching, by the machine learning process, for a signature representing the visual bump indicator based on the processed selected video information segments;

determining whether the vehicle approaches the bump;

generating, based on the determining, a bump alert indication;

determining, in response to the generating, a recommended driving behavior by applying, at the machine learning process, a weighted sum of a top frequency of occurrences of driving behaviors of vehicles captured in video information and telemetric information obtained during driving sessions of the vehicles when approaching bumps; and

applying the recommended driving behavior, wherein the applying comprises controlling at least one of a speed and a direction of driving of the vehicle, wherein the recommended driving behavior is a weighted sum of two or more top frequency of occurrences driving behaviors of a plurality of driving behaviors of vehicles when approaching bumps, the driving behaviors are captured in video information and telemetric information obtained during driving sessions of the vehicles;

wherein the recommended driving behavior is indicative of at least one of a controlled driving speed of the vehicle, and a direction of driving of the vehicle.

12. The non-transitory computer readable medium according to claim 11 , wherein the bump alert indication is a tactile bump alert indication.