The loop closure detection (LCD) problem in simultaneous localization and mapping has been an important research topic to reconstruct three-dimensional environments and estimate a camera trajectory accurately. Although the bag-of-visual-word (BoVW) scheme has been used widely and has shown good results, it has several problems in some aspects, such as occlusion, deformation, illumination change, and viewpoint change. In order to tackle the challenges, we propose an LCD method using the BoVW method with a local patch descriptor obtained from the learning-based approach. We have trained a neural network model with a place-oriented dataset and extract the descriptors for the local patches from the trained neural network model. In addition, we have constructed the ground-truth label for the evaluation. Our experiment shows promising results, compared to the state-of-the-art LCD method. The implementation of the proposed deep convolutional generative adversarial network descriptor, as well as the evaluation toolbox, can be found online at https://github.com/JustWon/DCGAN_Descriptor.
Recently, many 3D contents production tools using multi-view system has been introduced: e.g., depth estimation, 3D reconstruction and so forth. However, there is color mismatch problem in multiview system and it can cause big differences for the final result. In this paper we propose a color correction method using 3D multi-view geometry. The propose method finds correspondences between source and target viewpoint and calculates a translation matrix by using a polynomial regression technique. An experiment is performed in CIELab color space which is designed to approximate an human visual system and proposed method properly corrected the color compare to conventional methods. Moreover, we applied the proposed color correction method to 3D object reconstruction and we acquired a consistent 3D model in terms of color.