| Digital photogrammetry aims to generate as autonomously as a promising intermediate process toward this ultimate goal, perceptual organization of surfaces is proposed. Here, perceptual organization is to group sensory primitives originating from the same object and has been emphasized as a robust intermediate-level grouping process toward object recognition in human and computer vision. Meanwhile, surfaces are inferred from sensory data toward reconstructing the object space, being primitively represented with irregularly distributed 3D points, which can be derived from aerial stereo-images, LIDAR data or InSAR data. Despite intensive research on 2D data, perceptual organization of 3D entities such as surfaces is still in its infancy, however. Therefore, the purpose of this research is to develop a robust approach for constructing perceptual organization particularly with irregularly distributed 3D surface points. The scope of perceptual organization presented in this paper is limited to signal, primitive and structural levels. At the signal level, we organize raw 3D points into spatially coherent patches. Then, at the primitive level, we merge the patches into co-parametric surfaces. Finally, at the structural level, we group the surfaces into perceptually meaningful surface clusters. We propose a conceptual framework, establish a novel approach under the framework, and implement the approach as an autonomous system. The system is analyzed in terms of parameter selection and computational complexity and evaluated with real LIDAR data by inspecting the quality of organized output and then applying the output to extracting bare-earth DEMs. The analysis and evaluation substantiate a promising performance of the system. Finally, it has been shown that the proposed perceptual organization system produces autonomously with moderate computation loads, robust, explicit, computationally efficient and hierarchical descriptions from raw surface points. Thus, the organized output serves as a valuable input to higher order perceptual processes, including the generation and validation of hypotheses in object recognition tasks. |
