A target of interest measured by a high range resolution radar may be modelled by multiple dominant points of reflections referred to as dominant scatterers. In this paper a non-linear state space setting is used to model the states and measurements of a target moving in the down-and cross-range dimensions. A resample-move particle filter with simulated annealing is successfully used to jointly infer the locations of the dominant scatterers and the motion parameters of the target. A novel technique for the initialization of the particle filter for the given application is presented. The location estimates of scatterers using the particle filter method are compared to those obtained using standard range-Doppler inverse synthetic aperture radar (ISAR) imaging when using the same radar returns for both cases. The particle filter infers the location of scatterers more accurately than range-Doppler ISAR processing, and the processing can be performed online as opposed to ISAR processing, which requires batching. It is relatively straightforward to extend the method to perform localisation and tracking of scatterers in three dimensions, whereas such an extension is challenging in range-Doppler ISAR processing. However, several challenges need be addressed to make this algorithm suitable for practical implementation and these challenges are discussed. This method may be used to obtain very accurate estimates of target state, which may in turn be used for accurate ISAR motion compensation. Given enough computing resources this algorithm may in future become the basis of a new radar target imaging scheme.