6 3) 1 6 8 1 1) 8 6 (0) 1 6 Figure 1: One of the noteworthy features of OpenVSLAM: 3D scene mapping with various types of camera models.

We developed a robust object-level change detection method that could capture distinct scene changes in an image pair with viewpoint differences. To achieve this, we designed a network that could detect object-level changes in an image pair. In contrast to previous studies, we considered the change detection task as a graph matching problem for two object graphs that were extracted from each image. By virtue of this, the proposed network more robustly detected object-level changes with viewpoint differences than existing pixel-level approaches. In addition, the network did not require pixel-level change annotations, which have been required in previous studies. Specifically, the proposed network extracted the objects in each image using an object detection module and then constructed correspondences between the objects using an object matching module. Finally, the network detected objects that appeared or disappeared in a scene using the correspondences that were obtained between the objects. To verify the effectiveness of the proposed network, we created a synthetic dataset of images that contained object-level changes. In experiments on the created dataset, the proposed method improved the ${\mathrm{F}}_1$ score of conventional methods by more than 40%. Our synthetic dataset will be available publicly online.

We present an interactive route viewer system, 3DMovieMap, which generates and shows navigation movies walking through multi-level buildings, such as a science museum, airport, and university building. Movie map systems can provide users with visual cues by synthesizing navigation movies based on their inputs of routes. However, existing systems are limited to flat areas such as city areas. We aim to extend Movie Map to generate navigation movies for multi-level buildings. The 3DMovieMap system generates a movie map from an equirectangular movie via a visual Simultaneous Localization and Mapping technology. Users select waypoints on the floor maps. 3DMovieMap calculates the shortest path that visits these points and generates a navigation movie along the route. We created four movie maps of buildings and asked two participants to use our system and provide feedback for further improvements. We will be releasing an open dataset of equirectangular movies captured in a science museum.

This paper presents a novel semantic-based online extrinsic calibration approach, SOIC (so, I see), for Light Detection and Ranging (LiDAR) and camera sensors. Previous online calibration methods usually need prior knowledge of rough initial values for optimization. The proposed approach removes this limitation by converting the initialization problem to a Perspective-n-Point (PnP) problem with the introduction of semantic centroids (SCs). The closed-form solution of this PnP problem has been well researched and can be found with existing PnP methods. Since the semantic centroid of the point cloud usually does not accurately match with that of the corresponding image, the accuracy of parameters are not improved even after a nonlinear refinement process. Thus, a cost function based on the constraint of the correspondence between semantic elements from both point cloud and image data is formulated. Subsequently, optimal extrinsic parameters are estimated by minimizing the cost function. We evaluate the proposed method either with GT or predicted semantics on KITTI dataset. Experimental results and comparisons with the baseline method verify the feasibility of the initialization strategy and the accuracy of the calibration approach. In addition, we release the source code at https://github.com/--/SOIC.