NAVIGATION DEVICE WITH INTEGRATED CAMERA

• US 20160364621A1
• Filed: 06/26/2015
• Published: 12/15/2016
• Est. Priority Date: 06/11/2015
• Status: Abandoned Application

• Current Assignee: Garmin Switzerland GmbH (Garmin Limited)
• Original Assignee: Garmin Switzerland GmbH (Garmin Limited)
• Inventors: Hill, Kyle J., Bradi, Rares, Hill, Jeffrey M.
• Application Number:
  US14/751,258
• Publication Number:
  US 20160364621A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60Q 9/00 Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00 , e.g. haptic signalling
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: G01B 11/14 for measuring distance or clearance between spaced objects or spaced apertures G01B11/26 takes precedence; rangefinders G01C3/00
• CPC Class Codes: G01C 21/3647 Guidance involving output of stored or live camera images or video streams
• CPC Class Codes: G01S 11/12 using electromagnetic waves other than radio waves
• CPC Class Codes: G06T 2207/20048 Transform domain processing
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

Various embodiments are disclosed describing implementations of a navigational device with an integrated camera, which may record live video. A driving recorder is described that may store the live video data upon detection of a triggering event. A lane departure notification system is also described that determines whether a vehicle has crossed a road lane line, and cartographic data used by the navigational system may be leveraged such that the alert is issued when the vehicle is crossing into oncoming traffic but otherwise is suppressed. A collision notification system is also described, which identifies a vehicle by applying separate classification algorithms to the live video data based upon whether the video is recorded during the daytime or nighttime, and calculates a following distance. The navigational device may issue an alert when the following distance is below a recommended following distance threshold.

Claims

1. A navigational device, comprising:

a camera configured to capture live video in front of a first vehicle in which the navigational device is mounted and to generate live video data;

a location determining component configured to generate geographic location data indicative of a geographic location of the navigation device;

a memory configured to store a first training data model corresponding to a first range of video data metrics that identify a portion of a second vehicle is contained within the live video data during the daytime, and a second data training model corresponding to a second range of video data metrics that identify the portion of the second vehicle is contained within the live video data during the nighttime; and

a processor configured to;

determine whether it is daytime or nighttime based upon the geographic location data and a time of day,

classify the live video data according to the first model when it is daytime, and classify the live video data according to the second model when it is nighttime,

identify the second vehicle contained within the live video,

calculate an estimated distance from the navigational device to the second vehicle using the portion of the second vehicle contained within the live video data, and

selectively cause a first alert to be issued based upon the estimated distance.

2. The navigational device of claim 1, wherein the processor is further configured to calculate the estimated distance from the navigational device to the second vehicle by applying an inverse perspective transform to the live video data.

3. The navigational device of claim 2, wherein the processor is further configured to determine a speed of the first vehicle based on the geographic location data, calculate a recommended following distance (RFD) threshold based upon the speed of the first vehicle, and cause the first alert to be issued when the estimated distance from the navigational device to the second vehicle is less than the RFD threshold.

4. The navigational device of claim 3, wherein the processor is further configured to adjust the RFD threshold such that the RFD threshold is greater when it is nighttime than when it is daytime.

5. The navigational device of claim 1, wherein the location determining component is further configured to receive a global navigational satellite system (GNSS) signal, and

wherein the processor is further configured to determine the time of day based upon the GNSS signal.

6. The navigational device of claim 5, further comprising:

a memory configured to store cartographic data including an indication of road types, and

wherein the processor is further configured to determine a road type corresponding to the road lane in which the first vehicle is traveling by referencing the geographic location data to the cartographic data.

7. The navigational device of claim 6, wherein the processor is further configured to determine whether a road lane line is a solid or a dashed road lane line.

8. The navigational device of claim 7, wherein the processor is further configured to identify when the first vehicle has crossed the road lane line and cause a second alert to be issued when the first vehicle crosses a solid road lane line.

9. The navigational device of claim 8, wherein the processor is further configured to cause the second alert to be issued when the first vehicle crosses a dashed road lane line and the type of road indicates that the first vehicle is potentially crossing into oncoming vehicular traffic, and to otherwise suppress the second alert from being issued.

10. A navigational device, comprising:

a camera configured to capture live video in front of a first vehicle in which the navigational device is mounted and to generate live video data;

a location determining component configured to generate geographic location data indicative of a geographic location of the navigation device;

a memory configured to store cartographic data including an indication of road types; and

a processor configured to;

determine a type of road on which the first vehicle is traveling by referencing the geographic location data to the cartographic data,

identify when the first vehicle has crossed a road lane line,

determine whether the road lane line is a solid or a dashed road lane line,

cause a first alert to be issued when the first vehicle crosses a solid road lane line, and

cause the first alert to be issued when the first vehicle crosses a dashed road lane line and the type of road indicates that the first vehicle is potentially crossing into oncoming vehicular traffic, and to otherwise suppress the first alert from being issued.

11. The navigational device of claim 10, wherein the processor is configured to cause the first alert to be suppressed when the vehicle crosses the dashed road lane line and is entering a different lane in the same direction of travel.

12. The navigational device of claim 10, wherein the memory is further configured to store a first training data model corresponding to a first range of video data metrics that identify a portion of a second vehicle contained within the live video data during the daytime, and a second data training model corresponding to a second range of video data metrics that identify the portion of the second vehicle contained within the live video data during the nighttime, and

wherein the processor is further configured to:

determine whether it is daytime or nighttime based upon the geographic location data and a time of day,

classify the live video data according to the first model when it is daytime or classify the live video data according to the second model when it is nighttime,

calculate an estimated distance from the navigational device to the second vehicle using the portion of the second vehicle contained within the live video data, and

selectively cause a second alert to be issued based upon the estimated distance.

13. The navigational device of claim 12, wherein the processor is further configured to calculate the estimated distance from the navigational device to the second vehicle by applying an inverse perspective transform to the live video data.

14. The navigational device of claim 13, wherein the processor is further configured to determine a speed of the first vehicle based on the geographic location data, calculate a recommended following distance (RFD) threshold based upon the speed of the first vehicle, and cause the second alert to be issued when the estimated distance from the navigational device to the second vehicle is less than the RFD threshold.

15. The navigational device of claim 14, wherein the processor is further configured to adjust the RFD threshold such that the RFD threshold is greater when it is nighttime than when it is daytime.

16. The navigational device of claim 10, wherein the location determining component is further configured to receive a global navigational satellite system (GNSS) signal, and

wherein the processor is further configured to determine the time of day based upon the GNSS signal.

17. A computer-implemented method in a navigational device, comprising:

capturing, using one or more processors, live video in front of a first vehicle in which the navigational device is mounted;

generating, using the one or more processors, live video data based on the live video;

generating, using the one or more processors, geographic location data indicative of a geographic location of the navigation device;

storing, by one or more processors, a first training data model corresponding to a first range of video data metrics that identify a portion of a second vehicle contained within the live video data during the daytime, and a second data training model corresponding to a second range of video data metrics that identify the portion of the second vehicle contained within the live video data during the nighttime;

storing, using the one or more processors, cartographic data including an indication of road types;

determining, using the one or more processors, whether it is daytime or nighttime based upon the geographic location data and a time of day,

classifying, using the one or more processors, the live video data according to the first model when it is daytime,

classifying, using the one or more processors, the live video data according to the second model when it is nighttime,

identifying, using the one or more processors, a second vehicle contained within the live video data;

calculating, using the one or more processors, an estimated distance from the navigational device to the second vehicle using the portion of the second vehicle contained within the live video data,

selectively issuing, using the one or more processors, a first alert based upon the estimated distance from the navigational device to the second vehicle;

determining, using the one or more processors, a type of road on which the first vehicle is traveling by referencing the geographic location data to the cartographic data;

determining, using the one or more processors, whether a road lane line is a solid or a dashed road lane line;

identifying, using the one or more processors, when the first vehicle has crossed the road lane line;

issuing, using the one or more processors, a second alert when the first vehicle crosses a solid road lane line, and

issuing, using the one or more processors, the second alert when the first vehicle crosses a dashed road lane line and the type of road indicates that the first vehicle is potentially crossing into oncoming vehicular traffic, and otherwise suppressing the second alert.

18. The computer-implemented method of claim 17, wherein the act of calculating the estimated distance from the navigational device to the second vehicle comprises:

applying, by one or more processors, an inverse perspective transform to the live video data.

19. The computer-implemented method of claim 18, further comprising:

calculating, using the one or more processors, a speed of the first vehicle based on the geographic location data;

calculating, using the one or more processors, a recommended following distance (RFD) threshold based upon the speed of the first vehicle; and

adjusting, using the one or more processors, the RFD threshold such that the RFD threshold is greater when it is nighttime than when it is daytime, and wherein the act of issuing the first alert comprises;

issuing the first alert when the estimated distance from the navigational device to the second vehicle is less than the RFD threshold.

20. The computer-implemented method of claim 17, further comprising:

receiving, using the one or more processors, a global navigational satellite system (GNSS) signal, and

determining, using the one or more processors, the time of day based upon the GNSS signal.