Photogrammetric modeling of linear features with generalized point photogrammetry

Most current digital photogrammetric workstations are based on feature points. Curved features are quite difficult to be modeled because they cannot be treated as feature points. The focus of the paper is on the photogrammetric modeling of space linear features. In general, lines and curves can be represented by a series of connected points, so called, generalized points in the paper. Different from all existing models, only one collinearity equation is used for each point on the linear Curve, which makes the mathematical model very simple. Hereby, the key of generalized point photogrammetry is that all kinds of features are treated as generalized points to use either x or y collinearity equation. A significant difference between generalized point photogrammetry and conventional point photogrammetry is that image features are not necessarily exact conjugates. The exact conjugocy between image features and/or the correspondence between space and image feature are established during bundle block adjustment. Photogrammetric modeling of several space linear features is discussed. Sub-pixel precision has been achieved for both exterior orientation and 3D modeling of linear features, which verifies the correctness and effectiveness of the proposed approach.