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, a structure shape of a structure at a first instance of time to pixels within an aerial image depicting the structure captured at a second instance of time; assess a degree of alignment between the structure shape and the pixels, so as to classify similarities between the structure depicted within the pixels and the structure shape 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 structure shape and the pixels within the aerial 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, a structure shape of a structure at a first instance of time to pixels within an aerial image depicting the structure, the aerial image captured at a second instance of time;
assess a degree of alignment between the structure shape and the pixels within the aerial image depicting the structure, so as to classify similarities between the structure depicted within the pixels of the aerial image and the structure shape 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 structure shape and the pixels within the aerial 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 structure shape further comprises:
creating the structure shape using an image of a structure captured at the first instance of time.
6. The non-transitory computer readable medium of claim 1 , wherein the alignment confidence score is determined by analyzing shape intersection between the structure shape and an outline of the structure depicted within the pixels of the aerial image.
7. The non-transitory computer readable medium of claim 1 , wherein the structure shape is a previously determined outline 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 structure shape further comprises:
detecting edges of the structure in the aerial image;
determining one or more shift distance between the structure shape and one or more edges of the detected edges of the structure in the aerial image; and
shifting the structure shape 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 structure shape and the pixels within the aerial image depicting the structure, after the structure shape is shifted by the shift distance.
12. A method, comprising:
aligning, automatically with one or more processor utilizing an image classifier model, a structure shape of a structure at a first instance of time to pixels within an aerial image depicting the structure, the aerial image captured at a second instance of time;
assessing, automatically with the one or more processor, a degree of alignment between the structure shape and the pixels within the aerial image depicting the structure, so as to classify similarities between the structure depicted within the pixels of the aerial image and the structure shape using a machine learning model to generate an alignment confidence score; and
determining, automatically with the one or more processor, 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 structure shape and the pixels within the aerial 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 processor, 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 structure shape further comprises:
creating, automatically with the one or more processor, the structure shape using an image of a structure captured at the first instance of time.
16. The method of claim 12 , wherein the alignment confidence score is determined by analyzing shape intersection between the structure shape and an outline of the structure depicted within the pixels of the aerial image.
17. The method of claim 12 , wherein the structure shape is a previously determined outline 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 structure shape further comprises:
detecting edges of the structure in the aerial image;
determining one or more shift distance between the structure shape and one or more edges of the detected edges of the structure in the aerial image; and
shifting the structure shape by the shift distance.
20. The method of claim 19 , further comprising:
determining, automatically with the one or more processor, a structural modification based on the existence of the change and on a comparison between the structure shape and the pixels within the aerial image depicting the structure, after the structure shape is shifted by the shift distance.