Artificially intelligent provision of post-vehicular-collision evidence
Systems/techniques that facilitate artificially intelligent provision of post-vehicular-collision evidence are provided. In various embodiments, a system can be onboard a vehicle and can capture, via one or more cameras or microphones of the vehicle, vicinity data associated with a vicinity of the vehicle. In various instances, the system can generate, via execution of a deep learning neural network on the vicinity data, a classification label indicating whether a vehicular collision not involving the vehicle has occurred in the vicinity of the vehicle. In various cases, the system can record, in response to the classification label indicating that the vehicular collision has occurred and via the one or more cameras or the one or more microphones, post-collision evidence associated with the vicinity of the vehicle. In various aspects, the system can broadcast the classification label and the post-collision evidence to an emergency service computing device.
1. A system of a first vehicle, the system comprising:
a memory that stores computer-executable components; and
a processor that executes at least one of the computer-executable components that:
captures, via at least one sensor of the first vehicle, vicinity data associated with a vicinity comprising a defined physical area adjacent to the first vehicle, wherein the at least one sensor comprises at least one of an image sensor or a sound sensor, and wherein the vicinity data comprises at least one of first image data or first audio data;
generates, via execution of a deep learning neural network on the vicinity data, a classification label indicating whether a vehicular collision has occurred in the vicinity of the first vehicle, wherein the vehicular collision involves at least one second vehicle, and does not involve the first vehicle;
records, in response to the classification label indicating that the vehicular collision has occurred and via the at least one sensor, post-collision evidence associated with the vicinity of the first vehicle, wherein the post-collision evidence comprises at least one of second image data or second audio data captured after the vicinity data has been captured; and
a broadcast component that broadcasts, in response to the classification label indicating that the vehicular collision has occurred, the classification label and the post-collision evidence to an emergency service computing device.
2. The system of claim 1 , wherein the classification label binomially indicates a presence or an absence of the vehicular collision.
3. The system of claim 1 , wherein the classification label indicates how many vehicles are involved in the vehicular collision.
4. The system of claim 1 , wherein the classification label indicates an impact type of the vehicular collision, and wherein the impact type of the vehicular collision is one from a group consisting of a rear-end collision, a head-on collision, a side-impact collision, and a side-swipe collision.
5. The system of claim 1 , wherein the classification label indicates whether the vehicular collision involves a roll-over.
6. The system of claim 1 , wherein the classification label indicates whether the vehicular collision involves at least one of flames or smoke.
7. The system of claim 1 , wherein the classification label indicates a severity of the vehicular collision.
8. A computer-implemented method, comprising:
capturing, by a system of a first vehicle, via at least one sensor of the first vehicle, vicinity data associated with a vicinity comprising a defined physical area adjacent to the first vehicle, wherein the at least one sensor comprises at least one of an image sensor or a sound sensor, and wherein the vicinity data comprises at least one of first image data or first audio data;
generating, by the system, via execution of a deep learning neural network on the vicinity data, a classification label indicating whether a vehicular collision has occurred in the vicinity of the first vehicle, wherein the vehicular collision involves at least one second vehicle, and does not involve the first vehicle;
recording, by the system, in response to the classification label indicating that the vehicular collision has occurred, and via the at least one sensor, post-collision evidence associated with the vicinity of the first vehicle, wherein the post-collision evidence comprises at least one of second image data or second audio data captured after the vicinity data has been captured; and
broadcasting, by system, in response to the classification label indicating that the vehicular collision has occurred, the classification label and the post-collision evidence to an emergency service computing device.
9. The computer-implemented method of claim 8 , wherein the classification label binomially indicates a presence or an absence of the vehicular collision.
10. The computer-implemented method of claim 8 , wherein the classification label indicates how many vehicles are involved in the vehicular collision.
11. The computer-implemented method of claim 8 , wherein the classification label indicates an impact type of the vehicular collision, and wherein the impact type of the vehicular collision is one from a group consisting of a rear-end collision, a head-on collision, a side-impact collision, and a side-swipe collision.
12. The computer-implemented method of claim 8 , wherein the classification label indicates whether the vehicular collision involves a roll-over.
13. The computer-implemented method of claim 8 , wherein the classification label indicates whether the vehicular collision involves at least one of flames or smoke.
14. The computer-implemented method of claim 8 , wherein the classification label indicates a severity of the vehicular collision.
15. A computer program product for facilitating artificially intelligent provision of post-vehicular-collision evidence, the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by a processor of a first vehicle to cause the processor to:
capture, via at least one sensor of the first vehicle, vicinity data associated with a vicinity comprising a defined physical area adjacent to the first vehicle, wherein the at least one sensor comprises at least one of an image sensor or a sound sensor, and wherein the vicinity data comprises at least one of first image data or first audio data;
generate, via execution of a deep learning neural network on the vicinity data, a classification label indicating whether a vehicular collision has occurred in the vicinity of the first vehicle, wherein the vehicular collision involves at least one second vehicle, and does not involve the first vehicle;
record, in response to the classification label indicating that the vehicular collision has occurred, and via the at least one sensor, post-collision evidence associated with the vicinity of the first vehicle, wherein the post-collision evidence comprises at least one of second image data or second audio data captured after the vicinity data has been captured; and
broadcast, in response to the classification label indicating that the vehicular collision has occurred, the classification label and the post-collision evidence to an emergency service computing device.
16. The computer program product of claim 15 , wherein the classification label binomially indicates a presence or an absence of the vehicular collision.
17. The computer program product of claim 15 , wherein the classification label indicates how many vehicles are involved in the vehicular collision.
18. The computer program product of claim 15 , wherein the classification label indicates an impact type of the vehicular collision, and wherein the impact type of the vehicular collision is one from a group consisting of a rear-end collision, a head-on collision, a side-impact collision, and a side-swipe collision.
19. The computer program product of claim 15 , wherein the classification label indicates whether the vehicular collision involves a roll-over.
20. The computer program product of claim 15 , wherein the classification label indicates whether the vehicular collision involves at least one of flames or smoke.