Comparison of two-sensor tracking methods based on state vector fusion and measurement fusion

Abstract

There are two approaches to the two-sensor track fusion problem. recently presented the state vector fusion method which combines the filtered state vectors from the two sensors to form a new estimate while taking into account the correlated process noise. The measurement fusion method or data compression [5] combines the measurements from the two sensors first and then uses this fused measurement to estimate the state vector. The two methods are compared and an example shows the amount of improvement in the uncertainty of the resulting estimate of the state vector with the measurement fusion method.

Improved Detection of Human Respiration Using Data Fusion Basedon a Multistatic UWB Radar

“…There have been two approaches for data fusion using Kalman filtering, namely measurement and state vector fusion [27,28]. The former one was used in this paper, where the detected waveforms (after the target association) from all receiving channels were directly integrated into an augmented measurement vector in a centralized scheme to achieve optimum performance [28].…”

“…The former one was used in this paper, where the detected waveforms (after the target association) from all receiving channels were directly integrated into an augmented measurement vector in a centralized scheme to achieve optimum performance [28]. In this way, the measurement vector is…”

Distributed Kalman Filtering

“…Some recent publications in this area are as follows. Track fusion measurement is given in [18]. Performance of various track-to-track fusion algorithms from aspects of fusion accuracy, feedback and process noises are treated in [263].…”

“…As for the performance of different algorithms, [404] shows that the performance of weighted covariance algorithm is consistently worse as compared to the measurement fusion method. Moreover, it has been pointed out in [405] that results of weighted covariance algorithm are showing the behavior to be a maximum likelihood estimate.…”

Distributed Kalman filtering

“…Perform track fusion optimally for a multiple-sensor system with a specific processing architecture is treated in [295]. Other work cited in Table 2.11 are [338], [15,22,23,24], [16], [17], [19], [21], [20], [71], [72], [73]- [74], [75]- [76], [77], [78]- [79], [124], [126], [260], [261,262], [264,265], [266], [296], [303], [305] and [306]. [266] • Perform track fusion optimally for a multiple-sensor system with a specific processing architecture [295] • Track-to-track fusion for multi-sensor data fusion [296] • Common process noise on the two-sensor fused-track covariance [303] • Track association and track fusion with non-deterministic target dynamics [305] • Comparison of two-sensor tracking methods based on state vector fusion and measurement fusion [306] 2.9.…”