We present RoarNet, a new approach for 3D object detection from 2D image and 3D Lidar point clouds. Based on two stage object detection framework ([1], [2]) with PointNet [3] as our backbone network, we suggest several novel ideas to improve 3D object detection performance.The first part of our method, RoarNet 2D, estimates the 3D poses of objects from a monocular image, which approximates where to examine further, and derives multiple candidates that are geometrically feasible. This step significantly narrows down feasible 3D regions, which otherwise requires demanding processing of 3D point clouds in a huge search space.Then the second part, RoarNet 3D, takes the candidate regions and conducts in-depth inferences to conclude final poses in a recursive manner. Inspired by PointNet, RoarNet 3D processes 3D point clouds directly without any loss of data, leading to precise detection.We evaluate our method in KITTI, a 3D object detection benchmark. Our result shows that RoarNet has superior performance to state-of-the-art methods that are publicly available. Remarkably, RoarNet also outperforms state-of-the-art methods even in settings where Lidar and camera are not time synchronized, which is practically important for actual driving environment.RoarNet is implemented in Tensorflow [4] and publicly available with pretrained models.
Concept clustering is an important element of the product development process. The process of reviewing multiple concepts provides a means of communicating concepts developed by individual team members and by the team as a whole. Clustering, however, can also require arduous iterations and the resulting clusters may not always be useful to the team. In this paper, we present a machine learning approach on natural language descriptions of concepts that enables an automatic means of clustering. Using data from over 1000 concepts generated by student teams in a graduate new product development class, we provide a comparison between the concept clustering performed manually by the student teams and the work automated by a machine learning algorithm. The goal of our machine learning tool is to support design teams in identifying possible areas of “over-clustering” and/or “under-clustering” in order to enhance divergent concept generation processes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.