IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0793049
(2010-06-03)
|
등록번호 |
US-8264400
(2012-09-11)
|
발명자
/ 주소 |
- Yapa, Nadeeka D.
- Norman, Rachel B.
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
6 인용 특허 :
35 |
초록
▼
Described are computer-based methods and apparatuses, including computer program products, for signature matching. In some examples, the method for signature matching includes receiving a first target profile associated with a first data signal, the first data signal associated with a first target o
Described are computer-based methods and apparatuses, including computer program products, for signature matching. In some examples, the method for signature matching includes receiving a first target profile associated with a first data signal, the first data signal associated with a first target object; receiving a second target profile associated with a second data signal, the second data signal associated with the first target object or a second target object; generating a comparison distance utilizing a comparison distance function and based on a comparison of one or more data points associated with the first target profile and one or more data points associated with the second target profile; and determining a signature matching score based on the comparison distance.
대표청구항
▼
1. A method for signature matching, the method comprising: receiving, via one or more processors, a first target profile associated with a first data signal, the first data signal associated with a first target object;receiving, via the one or more processors, a second target profile associated with
1. A method for signature matching, the method comprising: receiving, via one or more processors, a first target profile associated with a first data signal, the first data signal associated with a first target object;receiving, via the one or more processors, a second target profile associated with a second data signal, the second data signal associated with the first target object or a second target object;generating, via the one or more processors, a comparison distance utilizing a comparison distance function and based on a comparison of one or more data points associated with the first target profile and one or more data points associated with the second target profile;determining, via the one or more processors, a signature matching score based on the comparison distance, wherein determining the signature matching score further comprises: generating a ratio based on the comparison distance,selecting a likelihood ratio based on the ratio determined from the comparison distance, wherein the likelihood ratio associated with a match probability density function and a mis-match probability density function, andwherein the determining the signature matching score based on the comparison distance further comprising determining the signature matching score based on the comparison distance and the selected likelihood ratio. 2. The method of claim 1, wherein the selected likelihood ratio is calculated in accordance with equation: LR(d)=g∑(d)gΔ(d)wherein:gΣ is the match probability density function indicative of a match of the first target profile and the second target profile,gΔ is a mis-match probability density function indicative of a mis-match of the first target profile and the second target profile,d is the comparison distance, andLR is the likelihood ratio. 3. The method of claim 1, further comprising: for each set of two target profiles in a plurality of target profiles, determining, via the one or more processors, a set of match distances between the two target profiles,generating, via the one or more processors, a match probability density function based on the comparison distance function and the set of match distances;determining, via the one or more processors, a set of mis-match distances between the two target profiles;generating, via the one or more processors, a mis-match probability density function based on the comparison distance function and the set of mis-match distances;generating, via the one or more processors, a scoring function based on the match probability density function and the mis-match probability density function, andstoring, via the one or more processors, the scoring function as a set of comparison likelihood ratios, the comparison ratio being indicative of a likelihood of a match or mis-match between the two target profiles. 4. The method of claim 3, further comprising: determining, via the one or more processors, a data collection angle for a first target profile in the plurality of target profiles; andselecting a second target profile in the plurality of target profiles based on the data collection angle. 5. The method of claim 3, further comprising generating the match probability density function based on at least a histogram, a kernel density estimation, or any combination thereof. 6. The method of claim 1, further comprising generating, via the one or more processors, the first or the second target profile of the first or the second data signal based on one or more features of the first or the second target object associated with the first or the second data signal. 7. The method of claim 1, further comprising associating, via the one or more processors, the first data signal with a previously identified track associated with the second target object based on the signature matching score. 8. The method of claim 1, further comprising: determining, via the one or more processors, a data collection angle for the first target profile; andselecting the second data signal from one or more data signals based on the data collection angle. 9. A computer program product for execution by a processor, the computer program product tangibly embodied in an information carrier comprising a machine-readable storage device, the computer program product including instructions being operable to cause a data processing apparatus to: receive a first target profile associated with a first data signal, the first data signal associated with a first target object;receive a second target profile associated with a second data signal, the second data signal associated with the first target object or a second target object;generate a comparison distance utilizing a comparison distance function and based on a comparison of one or more data points associated with the first target profile and one or more data points associated with the second target profile; anddetermine a signature matching score based on the comparison distance, wherein determining the signature matching score further comprises: generating a ratio based on the comparison distance,selecting a likelihood ratio based on the ratio determined from the comparison distance, wherein the likelihood ratio associated with a match probability density function and a mis-match probability density function,wherein the determining the signature matching score based on the comparison distance further comprising determining the signature matching score based on the comparison distance and the selected likelihood ratio. 10. A system for signature matching, the system comprising: a communication module configured to: receive a first target profile associated with a first data signal, the first data signal associated with a first target object, andreceive a second target profile associated with a second data signal, the second data signal associated with the first target object or a second target object;a distance comparison module configured to generate a comparison distance utilizing a comparison distance function and based on a comparison of one or more data points associated with the first target profile and one or more data points associated with the second target profile;a signature matching score module configured to determine a signature matching score based on the comparison distance, wherein the signature matching score module is further configured to generate a ratio based on the comparison distance function; anda likelihood ratio generation module configured to select a likelihood ratio based on the ratio determined from the comparison distance, wherein the likelihood ratio associated with a match probability density function and a mis-match probability density function,wherein the signature matching score module further configured to determine the signature matching score based on the comparison distance function and the selected likelihood ratio. 11. The system of claim 10 wherein the first data signal comprising a first high range resolution radar data signal, the first target object associated with a first ground track, and the second data signal comprising a second high range resolution radar data signal. 12. The system of claim 10, wherein the signature matching score being indicative of a match or mis-match between the first target profile and the second target profile. 13. The system of claim 10, further comprising: a distance comparison module configured to: determine a set of match distances between two target profiles in a plurality of target profiles;determine a set of mis-match distances between the two target profiles;a probability density generation module configured to:generate a match probability density function based on the comparison distance function and the set of match distances;generate a mis-match probability density function based on the comparison distance function and the set of mis-match distances;the distance comparison module further configured to generate a scoring function based on the match probability density function and the mis-match probability density function, anda storage device configured to store the scoring function as a set of comparison likelihood ratios, the comparison ratio being indicative of a likelihood of a match or mis-match between the two target profiles. 14. The system of claim 13 further comprising: an angle selection module configured to: determine a data collection angle for a first target profile in the plurality of target profiles; andselect a second target profile in the plurality of target profiles based on the data collection angle. 15. The system of claim 10 further comprising: a target profile generation module configured to generate the first or the second target profile of the first or the second data signal based on one or more features of the first or the second target object associated with the first or the second data signal. 16. The system of claim 10, further comprising: the signature matching score module configured to associate the first data signal with a previously identified track associated with the second target object based on the signature matching score. 17. The system of claim 10, further comprising: an angle selection module configured to: determine a data collection angle for the first target profile; andselect the second data signal from one or more data signals based on the data collection angle. 18. A system for signature matching, the system comprising: means for receiving a first target profile associated with a first data signal, the first data signal associated with a first target object;means for receiving a second target profile associated with a second data signal, the second data signal associated with the first target object or a second target object;means for generating a comparison distance utilizing a comparison distance function and based on a comparison of one or more data points associated with the first target profile and one or more data points associated with the second target profile; andmeans for determining a signature matching score based on the comparison distance, wherein determining the signature matching score further comprises: generating a ratio based on the comparison distance,selecting a likelihood ratio based on the ratio determined from the comparison distance, wherein the likelihood ratio associated with a match probability density function and a mis-match probability density function, andwherein the determining the signature matching score based on the comparison distance further comprising determining the signature matching score based on the comparison distance and the selected likelihood ratio.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.