Robust and efficient line extraction algorithm has been widely used in space photogrammetry field such as target pose detection, tracking and skeleton reconstruction. A line segment detector based on local contrast of pixels and global false detection control was proposed. The method consists of four steps. Firstly, the gradient and local contrast of each pixel was calculated. Secondly, the pixels with similar orientations were clustered into the line support region which was approximated by a rectangle. After that the line support region was fitted into a line segment with the above one pixel width and the line parameters were estimated. Finally, the line segment candidates were validated and the false detection was controlled. The experimental results show that the proposed method is much more robust and efficient than the traditional methods in hash conditions, especially in complex illumination.