id: 05561411
dt: a
an: 05561411
au: Gallagher, Jonathan; Moses, Randolph; Ertin, Emre
ti: Distributed computation of likelihood maps for target tracking.
so: Krishnamachari, Bhaskar (ed.) et al., Distributed computing in sensor
    systems. 5th IEEE international conference, DCOSS 2009, Marina del Rey,
    CA, USA, June 8‒10, 2009. Proceedings. Berlin: Springer (ISBN
    978-3-642-02084-1/pbk). Lecture Notes in Computer Science 5516, 287-300
    (2009).
py: 2009
pu: Berlin: Springer
la: EN
cc: 
ut: 
ci: 
li: doi:10.1007/978-3-642-02085-8_21
ab: Summary: Using the Bayesian framework of measurement likelihood, sensor
    data can be combined in a rigorous manner to produce a concise summary
    of knowledge of a target’s location in the state-space. This
    framework allows sensor data to be fused across time, space and sensor
    modality. When target motion and sensor measurements are modeled
    correctly, these “likelihood maps” contain all the relevant
    information for making inferences about the underlying target state. By
    combining all data without thresholding for detections, targets with
    low signal to noise ratio (SNR) can be detected where standard
    detection algorithms may fail. As the calculation cost of computing
    likelihood maps over the entire state space is prohibitively high for
    most practical applications, we propose an approximation which is
    computed in a distributed fashion, locally at each sensor node. We
    analyze this approximation, and give cases where it agrees with the
    centrally calculated likelihood map. Detection and tracking examples
    using measured data from multi-modal sensors (Radar, EO, Seismic) are
    presented.
rv: