Image processing apparatus, image processing system, and image processing method

Patent metadata

Field	Value
Publication number	US-2018173973-A1
Application number	US-201715817512-A
Country	US
Kind code	A1
Filing date	Nov 20, 2017
Priority date	Dec 15, 2016
Publication date	Jun 21, 2018
Grant date	—

Abstract

An image processing apparatus includes: a storage unit configured to store map information to which object information indicating an object and a position thereof is added, and a plurality of different classifiers for classifying an object in an image; an object detecting unit configured to detect an object in a target image; and an object recognizing unit configured to select any of the classifiers based on a photographing position that is a position at which the target image has been photographed and the object information added to the map information and, using the selected classifier, recognize the object detected by the object detecting unit.

First claim

What is claimed is:

1 . An image processing apparatus, comprising:
a storage unit configured to store map information to which object information indicating an object and a position thereof is added, and a plurality of different classifiers for classifying an object in an image; an object detecting unit configured to detect an object in a target image; and an object recognizing unit configured to select any of the classifiers based on a photographing position that is a position at which the target image has been photographed and the object information added to the map information and, using the selected classifier, recognize the object detected by the object detecting unit.

2 . The image processing apparatus according to claim 1 , wherein
the object recognizing unit is configured to extract, from among object information added to the map information, object information of an object present at a position calculated from the photographing position, and select a classifier suitable for classifying an object indicated in the extracted object information.

3 . The image processing apparatus according to claim 1 , wherein
the classifier is provided for each classification target, the classification target being each sign likely to be present in an image, and the classifier is configured to determine whether an object in the target image is a sign that is the classification target or a sign that is not the classification target.

4 . The image processing apparatus according to claim 1 , further comprising a contrast correcting unit configured to correct a pixel value of an image of a target region which is in the target image and in which an object may be present, so that the pixel value becomes darker by a prescribed amount when the pixel value is darker than a prescribed value but the pixel value becomes lighter by a prescribed amount when the pixel value is lighter than the prescribed value, and to supply an image after correction to the object detecting unit.

5 . The image processing apparatus according to claim 4 , wherein
the contrast correcting unit is configured to correct the pixel value of the image of the target region so that, with respect to an a value and a b value which indicate brightness of color in a Lab color space, the pixel value becomes darker by a prescribed amount when the pixel value is darker than an average value in the target region but the pixel value becomes lighter by a prescribed amount when the pixel value is lighter than the average value, and to supply an image after correction to the object detecting unit.

6 . The image processing apparatus according to claim 4 , wherein
the object recognizing unit is configured to classify, based on the image after correction from the contrast correcting unit, an object of which a type is distinguished based on a color and a shape of a pattern.

7 . The image processing apparatus according to claim 4 , wherein
the object recognizing unit is configured to recognize, based on the image after correction from the contrast correcting unit, a primary sign among road signs that are each the object.

8 . The image processing apparatus according to claim 4 , wherein
a plurality of images are consecutively photographed at prescribed time intervals, the contrast correcting unit is configured to calculate a third average value that blends, in a prescribed ratio, a first average value obtained by averaging pixel values of the target region in a previous image and a second average value obtained by averaging pixel values of the target region in a current image, and the object detecting unit is configured to detect an object from the target image using a threshold based on the third average value.

9 . The image processing apparatus according to claim 1 , further comprising a color analyzing unit configured to, with respect to each pixel in a target region which is in the target image and in which an object may be present, correct pixel values of all three primary colors of RGB to 0 when one or more absolute values of differences in pixel values among the primary colors exceed a prescribed threshold, and to supply an image after correction to the object detecting unit.

10 . The image processing apparatus according to claim 9 , wherein
the object recognizing unit is configured to recognize, based on the image after correction from the color analyzing unit, an object of which a type is distinguished based on characters or a shape of a symbol.

11 . The image processing apparatus according to claim 9 , wherein
the object recognizing unit is configured to recognize, based on the image after correction from the color analyzing unit, an auxiliary sign among road signs that are each the object.

12 . The image processing apparatus according to claim 1 , further comprising an updating unit configured to maintain the map information so that object information of an object with a highest detection frequency among objects having been recognized from previous to current target images and being present at a same position in the target images is added to the map information.

13 . An image processing system, comprising:
a terminal apparatus; and a server to which the terminal apparatus is coupled via a communication network, wherein the terminal apparatus is configured to photograph a target image and detect an object in the target image, and notify the server when the object is detected, and the server is configured to store, in advance, map information to which object information indicating an object and a position thereof is added, and a plurality of different classifiers for classifying an object in an image, and when notified from the terminal apparatus that the object has been detected, select any of the classifiers based on a photographing position that is a position at which the target image has been photographed and the object information added to the map information and, using the selected classifier, recognize the object detected by the terminal apparatus.

14 . An image processing method, comprising:
storing map information to which object information indicating an object and a position thereof is added, and a plurality of different classifiers for recognizing an object in an image; detecting an object in a target image; selecting any of the classifiers based on a photographing position that is a position at which the target image has been photographed and the object information added to the map information; and recognizing the detected object using the selected classifier.

15 . The image processing system according to claim 13 , wherein
the terminal apparatus is notified of object information recognized by the server, and the terminal apparatus is configured to display an image and information of the object received from the server and, at the same time, output information created by the server.

Assignees

• Hitachi Ltd

Inventors

• Hattori Hideharu
• Izumi Yoshifumi

Classifications

• G06F18/24

  Classification techniques · CPC title

• G06F18/253

  of extracted features · CPC title

• G06F18/285

  Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system · CPC title

• G06K9/54

  Physics · mapped topic

• G06K9/4652

  Physics · mapped topic