Image processing device and method of processing image
View Patent ↗To obtain an image processing device and a method of processing an image that improve distance accuracy and is capable of performing accurate distance even about an object at a greater distance than before, when a distance to an object is measured, one image object region 302 including an image of an object is extracted from one image of a pair of images imaged by a pair of imaging elements at the same time in the same direction. The degree of background that is likelihood of whether either an object image configuration part 304 or a background image configuration part 303 is calculated for each of a plurality of image configuration parts that configures the one image object region 302 . Then, the other image object region 503 having an image similar to the one image object region 302 is extracted from the other image 501 using the degree of background, and a parallax between the one image object region 302 and the other image object region 503 is calculated.
1. An image processing device that processes a pair of images imaged by a pair of imaging elements at the same time in the same direction, the device comprising:
one image object region extraction means configured to recognize an object, parallax information of which is to be acquired from one image, and to extract one image object region that is an imaged region including an image of the object in the one image;
the degree of background calculation means configured to calculate the degree of background that is likelihood of whether either an object image configuration part that configures an image of the object, or a background image configuration part that configures an image of a background other than the object with respect to a plurality of image configuration parts that configures the one image object region; and
a parallax calculation means configured to extract the other image object region having an image similar to the one image object region from the other image, and to calculate a parallax between the one image object region and the other image object region.
2. The image processing device according to claim 1 , further comprising:
the other image similar region extraction means configured to search the other image using the one image object region extracted by the one image object region extraction means, and to extract the other image similar region having an image similar to the one image vehicle region from the other image,
wherein the parallax calculation means searches a peripheral region having a predetermined size around the other image similar region in the other image.
3. The image processing device according to claim 1 , wherein the degree of background calculation means include at least one of the degree of background first calculation means configured to calculate the degree of background based on predetermined vehicle knowledge, and the degree of background second calculation means configured to calculate the degree of background based on a luminance difference between mutually corresponding image configuration parts when the one image object region and the other image object region are superposed.
4. The image processing device according to claim 1 , wherein the parallax calculation unit calculates a difference value of luminance values of image configuration parts mutually located at the same position when the one image object region is superposed on the other image for each image configuration part, performs weighting using the degree of background with respect to each difference value, and extracts the other image object region using each of the weighted difference values.
5. A method of processing a pair of images imaged by a pair of imaging elements at the same time in the same direction, the method comprising:
a step of recognizing an object, parallax information of which is to be acquired from one image, and extracting one image object region that is an imaged region including an image of the object in the one image;
a step of calculating the degree of background that is likelihood of whether either an object image configuration part that configures an image of the object, or a background image configuration part that configures an image of a background other than the object with respect to a plurality of image configuration parts that configures the one image object region; and
a step of extracting the other image object region having an image similar to the one image object region from the other image, and calculating a parallax between the one image object region and the other image object region.
6. The image processing device according to claim 2 wherein the degree of background calculation means include at least one of the degree of background first calculation means configured to calculate the degree of background based on predetermined vehicle knowledge, and the degree of background second calculation means configured to calculate the degree of background based on a luminance difference between mutually corresponding image configuration parts when the one image object region and the other image object region are superposed.
7. The image processing device according to claim 2 , wherein the parallax calculation unit calculates a difference value of luminance values of image configuration parts mutually located at the same position when the one image object region is superposed on the other image for each image configuration part, performs weighting using the degree of background with respect to each difference value, and extracts the other image object region using each of the weighted difference values.
8. The image processing device according to claim 3 , wherein the parallax calculation unit calculates a difference value of luminance values of image configuration parts mutually located at the same position when the one image object region is superposed on the other image for each image configuration part, performs weighting using the degree of background with respect to each difference value, and extracts the other image object region using each of the weighted difference values.