We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices. During inference, the network produces 33 body keypoints for a single person and runs at over 30 frames per second on a Pixel 2 phone. This makes it particularly suited to real-time use cases like fitness tracking and sign language recognition. Our main contributions include a novel body pose tracking solution and a lightweight body pose estimation neural network that uses both heatmaps and regression to keypoint coordinates.
We present a new algorithm for enforcing incompressibility for Smoothed Particle Hydrodynamics (SPH) by preserving uniform density across the domain. We propose a hybrid method that uses a Poisson solve on a coarse grid to enforce a divergence free velocity field, followed by a local density correction of the particles. This avoids typical grid artifacts and maintains the Lagrangian nature of SPH by directly transferring pressures onto particles. Our method can be easily integrated with existing SPH techniques such as the incompressible PCISPH method as well as weakly compressible SPH by adding an additional force term. We show that this hybrid method accelerates convergence towards uniform density and permits a significantly larger time step compared to earlier approaches while producing similar results. We demonstrate our approach in a variety of scenarios with significant pressure gradients such as splashing liquids.
Figure 1: Our method can quickly generate an entire family of fluid simulations from a small set of inputs. Here, we generate a large set of animations of liquid colliding with walls of varying shapes and locations. AbstractWe present a method for smoothly blending between existing liquid animations. We introduce a semi-automatic method for matching two existing liquid animations, which we use to create new fluid motion that plausibly interpolates the input. Our contributions include a new space-time non-rigid iterative closest point algorithm that incorporates user guidance, a subsampling technique for efficient registration of meshes with millions of vertices, and a fast surface extraction algorithm that produces 3D triangle meshes from a 4D space-time surface. Our technique can be used to instantly create hundreds of new simulations, or to interactively explore complex parameter spaces. Our method is guaranteed to produce output that does not deviate from the input animations, and it generalizes to multiple dimensions. Because our method runs at interactive rates after the initial precomputation step, it has potential applications in games and training simulations.
Abstract. Interactive media not only should enhance human-to-human communication, but also human-to-animal communication. We promote a new type of media interaction allowing human users to interact and play with their small pets (like hamsters) remotely via Internet through a mixed-reality-based game system "Metazoa Ludens". To examine the systems effectiveness: Firstly, the positive effects to the hamsters are established using Body Condition Score study. Secondly, the method of Duncan is used to assess the strength of preference of the hamsters towards Metazoa Ludens. Lastly, the effectiveness of this remote interaction, with respect to the human users as an interactive gaming system with their pet hamsters, is examined based on Csikszentmihalyi's Flow theory [1]. Results of these studies have shown positive remote interaction between human user and their pet friends. This paper provides specific experimental results on the implemented research system, and a framework for human-to-animal interactive media.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.