Systems and methods for automated detection of changes in extent of structures using imagery
Systems and methods for automated detection of changes in extent of structures using imagery are disclosed, including a non-transitory computer readable medium storing computer executable code that when executed by a processor cause the processor to: align, with an image classifier model, an outline of a structure at a first instance of time to pixels within an image depicting the structure captured at a second instance of time; assess a degree of alignment between the outline and the pixels depicting the structure, so as to classify similarities between the structure depicted within the pixels of the image and the outline using a machine learning model to generate an alignment confidence score; and determine an existence of a change in the structure based upon the alignment confidence score indicating a level of confidence below a predetermined threshold level of confidence that the outline and the pixels within the image are aligned.
1. A non-transitory computer readable medium storing computer executable code that when executed by a processor cause the processor to:
align, with an image classifier model, an outline of a structure at a first instance of time to pixels within an image depicting the structure, the image captured at a second instance of time;
assess a degree of alignment between the outline and the pixels within the image depicting the structure, so as to classify similarities between the structure depicted within the pixels of the image and the outline using a machine learning model to generate an alignment confidence score; and
determine an existence of a change in the structure based upon the alignment confidence score indicating a level of confidence below a predetermined threshold level of confidence that the outline and the pixels within the image are aligned.
2. The non-transitory computer readable medium of claim 1 , wherein the machine learning model is a convoluted neural network image classifier model.
3. The non-transitory computer readable medium of claim 1 , wherein the machine learning model is a generative adversarial network image classifier model.
4. The non-transitory computer readable medium of claim 1 , further comprising computer executable instructions that when executed by the processor cause the processor to:
identify a shape of the change in the structure using any one or more of: a point cloud estimate, a convolutional neural network, a generative adversarial network, and a feature detection technique.
5. The non-transitory computer readable medium of claim 1 , wherein aligning the outline further comprises:
creating the outline using an image of the structure captured at the first instance of time.
6. The non-transitory computer readable medium of claim 1 , wherein the outline is a first outline and wherein the alignment confidence score is determined by analyzing shape intersection between the first outline and a second outline of the structure depicted within the pixels of the image.
7. The non-transitory computer readable medium of claim 1 , wherein the outline is a vector boundary describing an extent of the structure at the first instance of time.
8. The non-transitory computer readable medium of claim 1 , wherein the first instance of time is before the second instance of time.
9. The non-transitory computer readable medium of claim 1 , wherein the first instance of time is after the second instance of time.
10. The non-transitory computer readable medium of claim 1 , wherein aligning the outline further comprises:
detecting edges of the structure in the image;
determining one or more shift distance between the outline and one or more edges of the detected edges of the structure in the image; and
shifting the outline by the shift distance.
11. The non-transitory computer readable medium of claim 10 , further comprising computer executable instructions that when executed by the processor cause the processor to:
determine a structural modification based on the existence of the change and on a comparison between the outline and the pixels within the image depicting the structure, after the outline is shifted by the shift distance.
12. A method, comprising:
aligning, automatically with one or more processors utilizing an image classifier model, an outline of a structure at a first instance of time to pixels within an image depicting the structure, the image captured at a second instance of time;
assessing, automatically with the one or more processors, a degree of alignment between the outline and the pixels within the image depicting the structure, so as to classify similarities between the structure depicted within the pixels of the image and the outline using a machine learning model to generate an alignment confidence score; and
determining, automatically with the one or more processors, an existence of a change in the structure based upon the alignment confidence score indicating a level of confidence below a predetermined threshold level of confidence that the outline and the pixels within the image are aligned.
13. The method of claim 12 , wherein the machine learning model is at least one of a convoluted neural network image classifier model and a generative adversarial network image classifier model.
14. The method of claim 12 , further comprising:
identifying, automatically with the one or more processors, a shape of the change in the structure using any one or more of: a point cloud estimate, a convolutional neural network, a generative adversarial network, and a feature detection technique.
15. The method of claim 12 , wherein aligning the outline further comprises:
creating, automatically with the one or more processors, the outline using an image of the structure captured at the first instance of time.
16. The method of claim 12 , wherein the outline is a first outline, and wherein the alignment confidence score is determined by analyzing shape intersection between the first outline and a second outline of the structure depicted within the pixels of the image.
17. The method of claim 12 , wherein the outline is a vector boundary describing an extend of the structure at the first instance of time.
18. The method of claim 12 , wherein the first instance of time is before the second instance of time or the first instance of time is after the second instance of time.
19. The method of claim 12 , wherein aligning the outline further comprises:
detecting edges of the structure in the image;
determining one or more shift distance between the outline and one or more edges of the detected edges of the structure in the image; and
shifting the outline by the shift distance.
20. The method of claim 19 , further comprising:
determining, automatically with the one or more processors, a structural modification based on the existence of the change and on a comparison between the outline and the pixels within the image depicting the structure, after the outline is shifted by the shift distance.