Line length estimation
View Patent ↗A solution for monitoring an area is provided. At least one image of a physical area corresponding to a line is obtained and a set of hypotheses are evaluated based on the image(s). For one or more hypotheses, an estimated length of the line is extracted, and an estimated line length is generated based on the estimated length(s) and the corresponding evaluation(s) of the set of hypotheses. In this manner, a length of a line of people, customers, vehicles, and/or the like, can be estimated. The estimation can be stored for later use, utilized to generate one or more alerts, and/or the like. The invention also provides for the use of a single camera to monitor multiple lines and/or perform other monitoring functions.
1. A method of monitoring an area, the method comprising:
obtaining at least one image of a physical area corresponding to a line;
evaluating a set of hypotheses based on the at least one image;
extracting an estimated length from at least one of the set of hypotheses;
generating an estimated line length based on the extracted estimated lengths and the evaluating; and
storing the estimated line length.
2. The method of claim 1 , further comprising capturing each of the at least one image with a single camera, the single camera located above and at an angle with respect to the physical area.
3. The method of claim 2 , further comprising adjusting the single camera to capture an image of a second physical area corresponding to a second line, distinct from the first line.
4. The method of claim 1 , wherein a hypothesis in the set of hypotheses includes a set of proposals, each proposal in the set of proposals comprising a model of an object and a corresponding location of the object in the at least one image.
5. The method of claim 4 , wherein the hypothesis includes a plurality of proposals, and wherein at least one of the plurality of proposals includes relationship data between the at least one of the plurality of proposals and another one of the plurality of proposals.
6. The method of claim 4 , further comprising adjusting the set of proposals in the hypothesis using a Markov Chain Monte Carlo framework.
7. The method of claim 1 , further comprising generating a hypothesis in the set of hypotheses by adjusting a previous hypothesis based on the at least one image.
8. The method of claim 1 , the evaluating including:
projecting a hypothesis in the set of hypotheses into the at least one image;
comparing a set of visual characteristics for the hypothesis with a set of visual characteristics for each of the at least one image; and
calculating a match score based on the comparing.
9. The method of claim 1 , wherein the generating includes:
selecting a subset of the set of hypotheses having the highest match scores; and
generating the estimated line length from the estimated length of each hypotheses in the subset.
10. The method of claim 1 , further comprising obtaining non-image data corresponding to the line, wherein the evaluating is further based on the non-image data.
11. The method of claim 1 , further comprising processing the estimated line length.
12. A system comprising:
a computer system, including at least one computing device, for monitoring an area by performing a method comprising:
obtaining at least one image of a physical area corresponding to a line;
evaluating a set of hypotheses based on the at least one image;
extracting an estimated length from at least one of the set of hypotheses;
generating an estimated line length based on the extracted estimated lengths and the evaluating; and
storing the estimated line length.
13. The system of claim 12 , further comprising a camera for capturing each of the at least one image, the camera located above and at an angle with respect to the physical area.
14. The system of claim 13 , the method further comprising a adjusting the camera to capture an image of a second physical area corresponding to a second line, distinct from the first line.
15. The system of claim 12 , wherein a hypothesis in the set of hypotheses includes a set of proposals, each proposal in the set of proposals comprising a model of an object and a corresponding location of the object in the at least one image.
16. The system of claim 15 , wherein the hypothesis includes a plurality of proposals, and wherein at least one of the plurality of proposals includes relationship data between the at least one of the plurality of proposals and another one of the plurality of proposals.
17. The system of claim 15 , the method further comprising a adjusting the set of proposals in the hypothesis using a Markov Chain Monte Carlo framework.
18. The system of claim 12 , the method further comprising a generating a hypothesis in the set of hypotheses by adjusting a previous hypothesis based on the at least one image.
19. The system of claim 12 , the method further comprising a obtaining non-image data corresponding to the line, wherein the evaluating is further based on the non-image data.
20. A computer program comprising program code stored on a computer-readable device, which when executed, enables a computer system to implement a method for monitoring an area, the method including:
obtaining at least one image of a physical area corresponding to a line;
evaluating a set of hypotheses based on the at least one image;
extracting an estimated length from at least one of the set of hypotheses;
generating an estimated line length based on the extracted estimated lengths and the evaluating; and
storing the estimated line length.
21. The computer program of claim 20 , wherein a hypothesis in the set of hypotheses includes a set of proposals, each proposal in the set of proposals comprising a model of an object and a corresponding location of the object in the at least one image.
22. The computer program of claim 21 , wherein the hypothesis includes a plurality of proposals, and wherein at least one of the plurality of proposals includes relationship data between the at least one of the plurality of proposals and another one of the plurality of proposals.
23. The computer program of claim 21 , the method further comprising adjusting the set of proposals in the hypothesis using a Markov Chain Monte Carlo framework.
24. The computer program of claim 20 , the method further comprising obtaining non-image data corresponding to the line, wherein the evaluating is further based on the non-image data.
25. A method of generating a system for monitoring an area, the method comprising:
providing a computer system for monitoring the area by performing a method comprising:
obtaining at least one image of a physical area corresponding to a line;
evaluating a set of hypotheses based on the at least one image;
extracting an estimated length from at least one of the set of hypotheses;
generating an estimated line length based on the extracted estimated lengths and the evaluating; and
storing the estimated line length.