Image processing method and image system for transportation

• US 10,192,287 B2
• Filed: 12/22/2016
• Issued: 01/29/2019
• Est. Priority Date: 11/29/2016
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Chan, Sheng-Wei, Lin, Che-Tsung
• Primary Examiner(s): Dunphy, David F
• Application Number:
  US15/388,124
• Publication Number:
  US 20180150939A1
• Time in Patent Office: 768 Days
• CPC Class Codes: G06F 18/211 Selection of the most significant subset of features
• CPC Class Codes: G06F 2218/08 Feature extraction
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 3/12 Panospheric to cylindrical image transformations
• CPC Class Codes: G06T 3/4038 Image mosaicing, e.g. composing plane images from plane sub-images
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/757 Matching configurations of points or features
• CPC Class Codes: G06V 10/771 Feature selection, e.g. selecting representative features from a multi-dimensional feature space
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G06V 30/228 of three-dimensional handwriting, e.g. writing in the air

Abstract

An image processing method is adapted to process images captured by at least two cameras in an image system. In an embodiment, the image processing method comprises: matching two corresponding feature points for two images, respectively, to become a feature point set; selecting at least five most suitable feature point sets, by using an iterative algorithm; calculating a most suitable radial distortion homography between the two images, according to the at least five most suitable feature point sets; and fusing the images captured by the at least two cameras at each of timing sequences, by using the most suitable radial distortion homography.

Claims

1. An image processing method for transportation adapted to process images captured by at least two cameras disposed on one vehicle in an image system, comprising:

matching two corresponding feature points for two images, respectively, to become a feature point set;

selecting at least five most suitable feature point sets, by using an iterative algorithm;

calculating a most suitable radial distortion homography between the two images, according to the at least five most suitable feature point sets; and

fusing the images captured by the at least two cameras at each of timing sequences, by using the most suitable radial distortion homography;

wherein before selecting the at least five most suitable feature point sets, randomly selecting at least five feature point sets;

iteratively calculating a plurality of radial distortion homographies before calculating the most suitable radial distortion homography between the two images; and

quantitatively assessing the plurality of radial distortion homographies;

wherein after iteratively calculating each of the plurality of radial distortion homographies for every iteration, the image processing method further comprises;

marking a ground truth point set between the two images;

transforming the ground truth point set into a transfer point set, respectively, according to each of the plurality of radial distortion homographies; and

calculating a distance difference value between the transfer point set and the ground truth point set.

2. The image processing method according to claim 1, wherein before matching the two corresponding feature points for the two images, respectively, to become the feature point set, the image processing method further comprises:

detecting a plurality of feature points of the two images.

3. The image processing method according to claim 1, wherein after fusing the images captured by the at least two cameras at each of the timing sequences, by using the most suitable radial distortion homography, the image processing method further comprises:

storing the most suitable radial distortion homography.

4. The image processing method according to claim 1, further comprising:

performing a transparency step on images of one of the at least two cameras; and

fusing the images performed by the transparency step at each of the timing sequences.

5. The image system according to claim 1, wherein the processor is configured to fuse the images of the at least two cameras, by using the most suitable radial distortion homography.

6. The image system according to claim 5, wherein the processor is configured to eliminate sight obstructions between the images captured by the at least two cameras.

7. An image system for transportation, the image system comprising:

at least two cameras disposed on one vehicle and configured to capture images;

a processor coupled to the at least two cameras, wherein the processor is configured to eliminate distortions of the at least two cameras so as to obtain fused images without distortions; and

a monitor coupled to the processor, wherein the monitor is configured to display the fused images without distortions;

wherein the processor is further configured to calculate a most suitable radial distortion homography, by using an iterative algorithm;

wherein the processor is further configured to iteratively calculate a plurality of radial distortion homographies before calculating the most suitable radial distortion homography between the two images and to quantitatively assess the plurality of radial distortion homographies;

wherein after iteratively calculating each of the plurality of radial distortion homographies for every iteration, the processor is further configured to;

mark a ground truth point set between the two images;

transform the ground truth point set into a transfer point set, respectively, according to each of the plurality of radial distortion homographies; and

calculate a distance difference value between the transfer point set and the ground truth point set.