To achieve needle steering and guide a flexible needle, it is necessary to localize it first. In the case of 3D ultrasound (US) in B-mode, the poor imaging quality and artefacts make it difficult to determine the needle pose. Needle localization issues specific to needle steering are reviewed in [1]. In [2], we proposed an observer of the needle tip pose. In [3], we detailed a machine learning approach for needle localization in 3D US volumes. In this paper, we describe the interconnection of both methods for precise curved needle localization in the context of needle steering.