Changing parameters of sequential video frames to detect different types of objects

• US 8,750,564 B2
• Filed: 12/08/2011
• Issued: 06/10/2014
• Est. Priority Date: 12/08/2011
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Maeda, Patrick Yasuo, Hoover, Martin Edward
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): SCHWARTZ, RAPHAEL M
• Application Number:
  US13/315,032
• Publication Number:
  US 20130148846A1
• Time in Patent Office: 915 Days
• Field of Search: None
• US Class Current: 382/103
• CPC Class Codes: G06V 10/141 Control of illumination
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• 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: G06V 20/625 License plates
• CPC Class Codes: G08G 1/0175 by photographing vehicles, e.g. when violating traffic rules

Abstract

First and second camera parameters are optimized for detecting a respective retroreflective and non-retroreflective object. A sequential series of first and second video frames are captured based on the first and second camera parameters, and the retroreflective and non-retroreflective object are detected in a camera scene based on the respective first and second video frames of the series.

Claims

1. A method comprising:

defining first and second camera parameters optimized for detecting a respective retroreflective and non-retroreflective object, wherein the first and second camera parameters each comprise an illumination time of a light source;

capturing a sequential series of first and second video frames based on the respective first and second camera parameters; and

facilitating detection of the retroreflective and non-retroreflective object in a camera scene based on the respective first and second video frames of the series.

2. The method of claim 1, wherein the first and second video frames are high resolution video frames.

3. The method of claim 2, wherein the high resolution video frames are greater than 300000 pixels.

4. The method of claim 1, wherein the sequential series of the first and second video frames are captured at a frame rate of less than 300 frames per second.

5. The method of claim 1, wherein the retroreflective object comprises a license plate, and the non-retroreflect object comprises a vehicle.

6. The method of claim 5, wherein the camera scene comprises multiple lanes of traffic.

7. The method of claim 1, wherein the first and second camera parameters each comprise one or more of integration time and camera gain.

8. A non-transitory computer readable medium configured with instructions for causing an apparatus to perform the method of claim 1.

9. An apparatus comprising:

a data interface capable of being coupled to a video camera; and

a processor configured to;

define first and second camera parameters optimized for detecting a respective retroreflective and non-retroreflective object; and

cause, via the data interface, the video camera to capture a sequential series of first and second video frames based on the respective first and second camera parameters, wherein the first and second camera parameters each comprise an illumination time of a light source, and wherein the retroreflective and non-retroreflective object are detected in a camera scene based on the respective first and second video frames of the series.

10. The apparatus of claim 9, wherein the sequential series of the first and second video frames are captured at a frame rate of less than 300 frames per second.

11. The apparatus of claim 10, wherein the first and second video frames are high resolution video frames.

12. The apparatus of claim 11, wherein the high resolution video frames are greater than 300000 pixels.

13. The apparatus of claim 9, wherein the retroreflective object comprises a license plate, and the non-retroreflect object comprises a vehicle.

14. The apparatus of claim 13, wherein the camera scene comprises multiple lanes of traffic.

15. The apparatus of claim 9, wherein the first and second camera parameters each comprise one or more of integration time and camera gain.

16. A system comprising:

at least one light source;

a video camera configured to capture a camera scene; and

a controller unit coupled to the video camera and the at least one light source, the controller unit configured to;

define first and second camera parameters optimized for detecting a respective retroreflective and non-retroreflective object in the camera scene;

cause the video camera to capture a sequential series of first and second video frames based on the respective first and second camera parameters; and

facilitate detecting the retroreflective and non-retroreflective object in the camera scene based on the respective first and second video frames of the series; and

vary an illumination time of the at least one light source in accordance with the first and second camera parameters.

17. The system of claim 16 further comprising an end user application configured to detect the retroreflective and non-retroreflective object in the camera scene.