w****y
发帖数: 2952 | 1 You have a system of N mobile sensors each transmitting GPS location,
estimated direction to a target and target intensity (counts). The
direction and intensity estimates are noisy.
Question 1: Given some history of sensor readings, what's the best approach
to estimate the true target location and intensity?
Question 2: With this new estimate, what the best approach to re-direct the
N sensors to confirm the location?
非常感谢 | a****l
发帖数: 8211 | 2 GPS又不是万灵丹,你的基准本来就飘移大,随便什么方法都不会有多少区别.
approach
the
【在 w****y 的大作中提到】
: You have a system of N mobile sensors each transmitting GPS location,
: estimated direction to a target and target intensity (counts). The
: direction and intensity estimates are noisy.
: Question 1: Given some history of sensor readings, what's the best approach
: to estimate the true target location and intensity?
: Question 2: With this new estimate, what the best approach to re-direct the
: N sensors to confirm the location?
: 非常感谢
| w****y
发帖数: 2952 | 3 麻烦你说一个方法，非常感谢。
【在 a****l 的大作中提到】
: GPS又不是万灵丹,你的基准本来就飘移大,随便什么方法都不会有多少区别.
:
: approach
: the
| c****e
发帖数: 7 | 4 My opinions:
Q1. Since your estimate is based on history of sensor readings, the best
approach is probably Maximum a Posteriori (MAP) estimate.
Q2. Maximum likelihood estimation (MLE) is very helpful and it picks the
values of the model parameters that make the data more likely than any other
values. MLE can be used to estimate the new location of sensors.
approach
the
【在 w****y 的大作中提到】
: You have a system of N mobile sensors each transmitting GPS location,
: estimated direction to a target and target intensity (counts). The
: direction and intensity estimates are noisy.
: Question 1: Given some history of sensor readings, what's the best approach
: to estimate the true target location and intensity?
: Question 2: With this new estimate, what the best approach to re-direct the
: N sensors to confirm the location?
: 非常感谢
|
|
