We apply seismic interferometry to traffic noise to retrieve both body waves and surface waves. Our preferred algorithm in the presence of highly variable and strong additive random noise uses cross-coherence, which uses normalization by the spectral amplitude of each of the traces, rather than cross-correlation or deconvolution. This normalization suppresses the influence of additive noise and overcomes problems resulting from amplitude variations among input traces. By using only the phase information and ignoring amplitude information, the method effectively removes the source signature from the extracted response and yields a stable structural reconstruction even in the presence of strong noise. This algorithm is particularly effective where the relative amplitude among the original traces is highly variable from trace to trace. We use the extracted reflected shear waves from the traffic noise data to construct a stacked and migrated image, and use the extracted surface waves (Love waves) to estimate the shear velocity as a function of depth. This shear-velocity profile agrees well with the interval velocity obtained from normal moveout of reflected shear waves constructed by seismic interferometry. These results are useful for a wide range of situations applicable in both geophysics and civil engineering.