Abstract: A source number estimation using eigenspace is presented.The estimation projects covariance matrix estimate of array signal into signal eigen subspace and noise eigen subspace respectively.Due to the orthogonality between signal eigen subspace and noise eigen subspace,it is easy to differentiate the contribution of signal and noise by using the decision value,which is the magnitude of projection.Same as the direction of arrival (DOA) estimate algorithm,the estimation uses the eigenvalue decomposition of M×M order covariance matrix (M is the number of elements).Hence a lot of computer burden can save.The estimation can be realized using decomposition in real-valued space to reduce more computer burden progressively.In computer simulation,it demonstrates the distribution of decision value,and the performance when signal's power is equal or different and on the condition of space correlative color noise environment.The estimaion was also tested with the sonar data.All of those results show that this estimaion has good performances.