SCENE ANALYSIS METHOD AND VISUAL NAVIGATION DEVICE

• US 20190012549A1
• Filed: 10/31/2017
• Published: 01/10/2019
• Est. Priority Date: 07/10/2017
• Status: Active Grant

• Current Assignee: Nanjing Yuanjue Information And Technology Company
• Original Assignee: Nanjing Yuanjue Information And Technology Company
• Inventors: ZHENG, LIMING, Yu, Tao, Cui, Bingbing
• Granted Patent: US 10,614,323 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 10/62 relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
• 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 1/096725 where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 9/02 Anti-collision systems

Abstract

A scene analysis method is applied to a visual navigation device. The scene analysis method includes the steps of capturing scene information at different times based upon the field of view of an image capturing device; analyzing different targets existing in the captured scene information; comparing each one of the targets captured at different times to classify the target, wherein the target that is in a specific region in the field of view and moving toward the image capturing device is classified as a type A target; otherwise the target is classified as a type B target. When the visual navigation is installed on a vehicle, a protection procedure such as a procedure of avoiding an obstacle is initiated when a type A target is detected, so that the vehicle is automatically prevented from potential accidents.

Claims

1. A scene analysis method comprising the steps of:

capturing scene information at different times based upon a field of view of an image capturing device;

analyzing different targets existing in the scene information being captured;

comparing positions of the same one of the targets captured at different times, wherein the target that is in a specific region in the field of view and moving toward the image capturing device is classified as a type A target, otherwise, the target is classified as a type B target.

2. The method of claim 1, wherein the image capturing device is a monocular image capturing device.

3. The method of claim 2, wherein a center of the field of view is on an optical axis of an imaging system of the image capturing device.

4. The method of claim 1, wherein the scene information is analyzed using clustering identification to distinguish different targets in the scene information.

5. The method of claim 1, wherein a plurality of sampling points or grids in the scene information are extracted along a spiral curve having a starting point at the center of the field of view.

6. The method of claim 5, wherein the plurality of sampling points or grids are distributed along the spiral curve at an equal interval and are sequentially labeled with ascending numerals from the starting point of the spiral curve.

7. The method of claim 5, wherein the number of the plurality of sampling points or grids is the square of an odd number.

8. The method of claim 5, wherein the plurality of sampling points or grids are applied for analyzing the scene information captured at different times.

9. The method of claim 8, wherein the numbers of the sampling points or grids that enclose the profile of the same target captured at different times are used to determine whether the target is in the specific region and is moving toward the image capturing device.

10. The method of claim 8, wherein the numbers of the sampling points or grids occupied by the same target captured at different times are used to determine whether the target is in the specific region and is moving toward the image capturing device.

11. The method of claim 1, wherein a protection procedure is initiated when the target is classified as a type A target.

12. The method of claim 11, wherein the protection procedure is an obstacle avoiding procedure to dodge the type A target.

13. The method of claim 11, wherein the protection procedure is a braking procedure to stop moving toward the type A target.

14. The method of claim 11, wherein an alarm is activated when the protection procedure is initiated.

15. A visual navigation device using the method as claimed in claim 1, the device comprising:

a mobile carrier;

an image capturing device installed on the mobile carrier to capture scene information;

an image analyzing device connected to the image capturing device for receiving and analyzing the scene information;

a control module connected to the image analyzing device to obtain an analyzing result from the image analyzing device and controlling a motion of the mobile carrier based upon the analyzing result.

16. The visual navigation device of claim 15, wherein the image analyzing device analyzes the scene information captured by the image capturing device and determines whether a target appearing in the scene information is a type A target or a type B target, and the control module executes a protection procedure when the target is determined as the type A target.

17. The visual navigation device of claim 15, wherein the image analyzing device analyzes the scene information captured by the image capturing device and determines whether the mobile carrier deviates from a path based on relations between diagonal lines of the field of view and captured scenery appearing in the field of view, and a correction function is executed to make the mobile carrier move in a correct way when the mobile carrier deviates from the trajectory.

18. The visual navigation device of claim 15, wherein the mobile carrier is a vehicle and the image capturing device is installed at a lower position in front of the vehicle.

19. The visual navigation device of claim 15, wherein the carrier is an aircraft and the image capturing device is installed at a center in front of the aircraft.

20. The visual navigation device of claim 19, wherein the carrier has another image capturing device installed at a center of a bottom of the aircraft.