Dimensional measurement for hot forgings is a key factor to improve the level of forging technology in industry field. However, the high temperature, large size and hostile environment increase difficulties to guarantee the robustness and speed of the measurement. In this paper, a robust real-time image processing method based on laser-aided binocular machine vision system is proposed. Firstly, images with clear laser stipes are acquired using spectral selection method, by which the influences of thermal radiation and ambient light can be reduced. Then, to improve the speed of extraction and the robustness of matching, an extraction method based on the information consistency of the images acquired by the system and a matching method based on sequential consistency and epipolar constraints are presented. Dimensional reconstruction models for square and axial forgings are built. Finally, the image processing results are used to reconstruct the feature dimensions of a ceramic plate in the laboratory as well as forgings in a forge. Experiments show that, the root-mean-square error of the reconstructed points is 0.002mm and the relative error for width reconstruction is 0.638% in a cold state. Lengths and diameters of hot large forgings are reconstructed robustly and in real time. It is verified that the method proposed in this paper can satisfy the requirements of precision, speed and robustness for measurement of large hot forgings in industrial field.