In order to estimate the camera pose from straight line segment correspondences in high precision, a direct least squares solution is proposed. A straight line segment distance measurement which integrates distance between endpoints，midpoints, angle and lengths of two line segments is proposed and used to transform the original problem into minimize a quadratic cost function of pose rotation matrix. A modified cost function based on the CGR parameters of rotation matrix is minimized, which the optimality conditions form a system of three third-order polynomial equations. Algebraic method is used to solve this system directly without requiring iterations, and the globally optimal solution of rotation matris is obtained. The complexity of proposed method is O(n). The efficiency and high precision are demonstrated by synthesized and real data experiments.