Multiple exposure event determination

Patent metadata

Field	Value
Publication number	US-10885777-B2
Application number	US-201916723527-A
Country	US
Kind code	B2
Filing date	Dec 20, 2019
Priority date	Sep 29, 2017
Publication date	Jan 5, 2021
Grant date	Jan 5, 2021

Abstract

Systems, devices and methods provide, implement, and use vision-based methods of sequence inference for a device affixed to a vehicle.

First claim

What is claimed is:

1. A method comprising:
receiving, by at least one processor of a computing device, visual data captured by a camera mounted on or in a vehicle;
upon detecting, by the at least one processor, a position of a traffic light in a field of view of the camera, based on the visual data, determining, by the processor, that the traffic light applies to a left-turn lane;
upon determining, by the at least one processor based on the visual data in the field of view of the camera, a position of a lane boundary corresponding to a lane in which the driver is travelling, determining, by the at least one processor, that the driver is not travelling in the left-turn lane;
detecting, by the at least one processor, an intersection crossing by the vehicle; and
determining, by the at least one processor, that the detected traffic light does not apply to the intersection crossing by the vehicle, based at least in part on the detected position of the traffic light, the lane boundary, the determination that the driver is not travelling in the left-turn lane, and the detected intersection crossing.

2. The method of claim 1 , wherein the detected intersection crossing does not comprise the vehicle turning left at the intersection, and wherein the determination that the traffic light does not apply to the vehicle is further based on the determination that the traffic light applies to the left-turn lane.

3. The method of claim 1 , further comprising:
detecting, by the at least one processor, a second position of a second traffic light in the field of view of the camera, based on the visual data; wherein determining that the traffic light does not apply to the intersection crossing is further based on the detected second position.

4. The method of claim 3 , further comprising:
determining, by the at least one processor, that the position of the traffic light is to the left of the second position of the second traffic light, and wherein determining that the traffic light does not apply to the intersection crossing is further based on the determination that the position of the traffic light is to the left of the second position of the second traffic light.

5. The method of claim 3 , further comprising:
determining, by the at least one processor, a state of the traffic light, and
determining, by the at least one processor, a second state of the second traffic light; and
determining, by the at least one processor, that the state of the traffic light and the second state of the second traffic light are not the same; and wherein determining that the traffic light does not apply to the intersection crossing is further based on the determination that the state of the traffic light and the state of the second traffic light are not the same.

6. The method of claim 5 , wherein the state of the traffic light is red or red arrow;
and wherein the second state of the second traffic light is green.

7. A method comprising:
receiving, by at least one processor of a computing device, visual data captured by a camera mounted on or in a vehicle, wherein the visual data comprises a first frame and a second frame;
detecting, by the at least one processor, a second vehicle in the first frame, wherein the second vehicle is detected based on a view of a rear of the second vehicle in the first frame;
determining, by the at least one processor, a first bounding box for the second vehicle in the first frame;
detecting, by the at least one processor, the second vehicle in the second frame;
determining, by the at least one processor, a second bounding box for second vehicle in the second frame;
comparing, by the at least one processor, the first bounding box and the second bounding box;
determining, by the at least one processor, that the second vehicle is moving at nearly the same speed as the vehicle, based at least in part on the comparison of the first bounding box and the second bounding box;
detecting, by the at least one processor, a position of a traffic light in a field of view of the camera, based on the visual data;
detecting, by the at least one processor, an intersection crossing by the vehicle; and
determining, by the at least one processor, that the detected traffic light does not apply to the intersection crossing by the vehicle, based at least in part on the detected position of the traffic light and the detected intersection crossing, wherein determining that the detected traffic light does not apply to the intersection crossing is further based on the determination that the second vehicle is moving at nearly the same speed as the vehicle.

8. A method comprising:
receiving, by at least one processor of a computing device, visual data captured by a camera mounted on or in a vehicle, wherein the visual data comprises a plurality of frames;
detecting, by the at least one processor, a presence and a position of a traffic light in a field of view of the camera, based on the visual data;
determining, by the at least one processor, whether the traffic light is present in each frame of the plurality of frames;
determining, by the at least one processor, a state of the traffic light for each frame of the plurality of frames for which the traffic light is present;
detecting, by the at least one processor, an intersection crossing by the vehicle;
determining, by the at least one processor, that the traffic light was red during the intersection crossing, based on the determined state of the traffic light in a last frame of the plurality of frames for which the traffic light is present;
determining, by the at least one processor, that the detected traffic light applies to the intersection crossing by the vehicle, based at least in part on the detected position of the traffic light and the detected intersection crossing; and
transmitting, by the at least one processor, an observation data to a remote device, wherein the observation data comprises an indication that the vehicle crossed an intersection in the presence of an applicable traffic light, based on the determination that the traffic light applies to the intersection crossing.

9. The method of claim 8 , wherein the at least one processor that detects the presence and the position of the traffic light is on, in, or otherwise attached to the vehicle.

10. The method of claim 8 , wherein the detected intersection crossing by the driver of the vehicle is one of:
the driver drove straight through the intersection;
the driver turned left at the intersection;
the driver turned right at the intersection; or
the driver executed a U-turn.

11. The method of claim 8 , further comprising:
determining, by the at least one processor based on the visual data, a state of the traffic light, wherein the state of the traffic light is at least one of: red, yellow, green, off, blinking, green arrow, or red arrow; and
classifying, by the at least one processor based on the visual data, the intersection crossing as one of: a green-light crossing; a yellow-light crossing; a red-light crossing, wherein the red light turned red after the vehicle entered the intersection; or a red-light crossing, wherein the red light turned red before the vehicle entered the intersection, and wherein the transmitted observation data further comprises an indication of the classification.

12. The method of claim 8 , further comprising:
determining, by the at least one processor, a number of frames in which the traffic light was red, based on the determined state of the traffic light for each frame of the plurality of frames for which the traffic light is present;
comparing, by the at least one processor, the number of frames in which the traffic light wa

Assignees

• Netradyne Inc

Inventors

• Annapureddy Venkata Sreekanta Reddy
• Campos Michael
• Yedla Arvind
• Julian David Jonathan

Classifications

• B60W40/04 Primary

  Traffic conditions · CPC title

• G06V20/597

  Recognising the driver's state or behaviour, e.g. attention or drowsiness · CPC title

• G06V20/582

  of traffic signs · CPC title

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G08G1/04 Primary

  using optical or ultrasonic detectors · CPC title