Image processing device, image processing method, POI information creation system, warning system, and guidance system

• US 9,672,606 B2
• Filed: 06/18/2015
• Issued: 06/06/2017
• Est. Priority Date: 10/27/2014
• Status: Active Grant

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Izumi, Yoshifumi, Hattori, Hideharu
• Primary Examiner(s): GORADIA, SHEFALI DINESH
• Application Number:
  US14/743,614
• Publication Number:
  US 20160117848A1
• Time in Patent Office: 719 Days
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/92 based on global image properties
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof

Abstract

Even when the brightness of an image in a video changes, detection of an object in the background is realized by accurately separating the object in the background from the background of the image. An image processing device in accordance with the present invention executes a process of converting a color space of a processing target image and acquiring color information on the converted color space, a process of calculating, for the target image, an average value of the brightness of color information on a target region that contains an object to be detected, and a process of comparing, for the target region, the brightness of color information on each pixel with the calculated average value, a process of generating a corrected image with corrected brightness/darkness, and a process of extracting the object on the basis of the corrected image (See FIG. 1).

Claims

1. An image processing device comprising:

a processor configured to execute various programs for performing image processing on a target image; and

a memory that stores a result of the image processing, wherein

the processor is configured to execute

a process of converting a color space of the target image and acquiring color information on the converted color space,

a process of calculating, for the target image, a first average value indicating an average value of brightness of color information on a target region that contains an object to be detected,

a process of comparing, for the target region, brightness of color information on each pixel with the first average value to generate a corrected image with corrected brightness/darkness, and

a process of extracting the object on the basis of the corrected image,

wherein the processor is configured to, for a past image that has been captured prior to the target image, calculate a second average value indicating an average value of brightness of color information on a region corresponding to the target region of the target image, and generate the corrected image by taking into consideration a ratio between the first average value and the second average value.

2. The image processing device according to claim 1, wherein the processor is configured to extract the object by separating the object from a background of the corrected image.

3. The image processing device according to claim 1, wherein the processor is configured to identify the object by comparing a reference image prepared in advance with the extracted image.

4. The image processing device according to claim 3, wherein the processor is configured to identify the object by adjusting gray levels of the reference image in accordance with a bit rate of the target image and determining similarity between the adjusted reference image and an image of the object.

5. The image processing device according to claim 3, wherein the processor is configured to execute a process of accumulating positions of the identified object using positional information acquired when the target image was captured, and determine reliability of the identified object in accordance with a detection frequency obtained as a result of the accumulation.

6. The image processing device according to claim 1, wherein the processor is configured to, for the input target image, execute a process of correcting expansion of the target image by adjusting an aspect ratio of the image.

7. A Point of Interest (POI) information creation system comprising:

a mobile terminal device including an imaging device configured to capture image data; and

a server including the image processing device according to claim 1, wherein

the mobile terminal device is configured to transmit the image data to the server,

the server is configured to process the received image data with the image processing device, store an image of an extracted object in a memory, and transmit the image to the mobile terminal device, and

the mobile terminal device is configured to display a received image of the extracted object on a display device.

8. A warning system comprising:

a mobile terminal device including an imaging device configured to capture image data; and

a server including the image processing device according to claim 1, wherein

the mobile terminal device is configured to transmit the image data to the server,

the server is configured to process the received image data with the image processing device, store an image of an extracted object in a memory, and transmit the image of the extracted object and alert information to the mobile terminal device, and

the mobile terminal device is configured to display the received image of the extracted object on a display device, and output the alert information.

9. A guidance system comprising:

a mobile terminal device including an imaging device configured to capture image data; and

a server including the image processing device according to claim 1, wherein

the mobile terminal device is configured to transmit the image data to the server,

the server is configured to process the received image data with the image processing device to extract an image of a signpost, store the extracted image of the signpost in a memory, and transmit the extracted image of the signpost and guidance information to the mobile terminal device, and

the mobile terminal device is configured to display the received image of the extracted signpost on a display device and output the guidance information.

10. An image processing method for identifying a desired object in a target image, the method comprising the following steps executed by a processor, the processor being configured to execute various programs for performing image processing on the target image:

converting a color space of the target image and acquiring color information on the converted color space;

calculating, for the target image, a first average value indicating an average value of brightness of color information on a target region that contains an object to be detected;

comparing, for the target region, brightness of color information on each pixel with the first average value to generate a corrected image with corrected brightness/darkness;

extracting the object by separating the object from a background of the corrected image, and comparing a reference image prepared in advance with the extracted object, thereby identifying the object; and

calculating, for a past image that has been captured prior to the target image, a second average value indicating an average value of brightness of color information on a region corresponding to the target region of the target image, and generating the corrected image by taking into consideration a ratio between the first average value and the second average value.

11. The image processing method according to claim 10, further comprising the following step performed by the processor:

identifying the object by adjusting gray levels of the reference image in accordance with a bit rate of the target image and determining similarity between the adjusted reference image and the image of the object.

12. The image processing method according to claim 10, further comprising the following step performed by the processor:

accumulating positions of the identified object using positional information acquired when the target image was captured, and determining reliability of the identified object in accordance with a detection frequency obtained as a result of the accumulation.

13. The image processing method according to claim 10, further comprising the following step performed by the processor:

correcting, for the input target image, expansion of the target image by adjusting an aspect ratio of the image.