System for detecting image abnormalities

Patent metadata

Field	Value
Publication number	US-10679331-B2
Application number	US-201916266852-A
Country	US
Kind code	B2
Filing date	Feb 4, 2019
Priority date	May 1, 2007
Publication date	Jun 9, 2020
Grant date	Jun 9, 2020

Abstract

Image capture systems including a moving platform; an image capture device having a sensor for capturing an image, the image having pixels, mounted on the moving platform; and a detection computer executing an abnormality detection algorithm for detecting an abnormality in the pixels of the image immediately after the image is captured by scanning the image utilizing predetermined parameters indicative of characteristics of the abnormality and then automatically and immediately causing a re-shoot of the image.

First claim

What is claimed is:

1. An image capture method, comprising:
capturing, with a sensor of an image capture device mounted on a moving platform, an aerial image having pixels; and
executing, with a detection computer, an abnormality detection algorithm for detecting an abnormality in the pixels of the aerial image immediately after the aerial image is captured by scanning the aerial image utilizing predetermined parameters indicative of characteristics of the abnormality and then automatically scheduling a re-shoot of the aerial image such that the re-shoot occurs prior to landing of the moving platform, wherein the abnormality detection algorithm causes the detection computer to scan the aerial image using pattern recognition techniques to detect the abnormality in the pixels of the aerial image.

2. The image capture method of claim 1 , wherein the moving platform is an unmanned airplane.

3. The image capture method of claim 1 , wherein the moving platform is a manned airplane.

4. The image capture method of claim 1 , wherein the moving platform is a robotic device.

5. The image capture method of claim 1 , wherein capturing the aerial image further comprises capturing the aerial image at a pre-determined time.

6. The image capture method of claim 1 , wherein capturing the aerial image further comprises capturing the aerial image at a pre-determined position of the moving platform.

7. The image capture method of claim 1 , wherein the aerial image is a first scheduled aerial image scheduled for capture before capture of a second scheduled aerial image, and wherein automatically scheduling the re-shoot of the first scheduled aerial image such that the re-shoot occurs prior to landing of the moving platform further comprises automatically scheduling the re-shoot of the first scheduled aerial image before the capture of the second scheduled aerial image.

8. The image capture method of claim 1 , wherein automatically scheduling the re-shoot of the aerial image such that the re-shoot occurs prior to landing of the moving platform further comprises automatically scheduling the re-shoot of the aerial image using multiple re-shoots until a re-shot image is captured that does not contain the abnormality.

9. The image capture method of claim 1 , wherein if the abnormality is detected, the aerial image is flagged as bad.

10. The image capture method of claim 1 , wherein the sensor is part of a digital camera.

11. The image capture method of claim 1 , further comprising capturing one or more re-shot aerial image having pixels.

12. The image capture method of claim 11 , further comprising combining one or more of the pixels of the aerial image with one or more of the pixels of the one or more re-shot aerial image.

Assignees

• Pictometry Int Corp

Inventors

• Giuffrida Frank
• Schultz Stephen

Classifications

• G06T7/0002 Primary

  Inspection of images, e.g. flaw detection · CPC title

• H04N7/183

  for receiving images from a single remote source · CPC title

• G06T2207/30168

  Image quality inspection · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• H04N5/23222

  Electricity · mapped topic