Search

In industrial countries, adults spend a considerable amount of time sedentary each day at work, driving and during activities of daily living. Characterizing the seated upper body human poses using mmWave radars is an important, yet under-studied topic with many applications in human-machine interaction, transportation and road safety. In this work, we devise SUPER, a framework for seated upper body human pose estimation that utilizes dual-mmWave radars in close proximity. A novel masking algorithm is proposed to coherently fuse data from the radars to generate intensity and Doppler point clouds with complementary information for high-motion but small radar cross section areas (e.g., upper extremities) and low-motion but large RCS areas (e.g. torso). A lightweight neural network extracts both global and local features of upper body and output pose parameters for the Skinned Multi-Person Linear (SMPL) model. Extensive leave-one-subject-out experiments on various motion sequences from multiple subjects show that SUPER outperforms a state-of-the-art baseline method by 30 -- 184%. We also demonstrate its utility in a simple downstream task for hand-object interaction.

Personal Data Stores (PDS) like SoLiD is an emerging data and knowledge management solution in recent years. They promise to give back ownership and control of data to the user, and provide protocols for developers to build applications using the data. However, existing Solid-based applications often focus on using a single-user's data. In this article, we use a simple but realistic calendar-and-meeting-scheduling scenario to demonstrate the feasibility and design considerations for enabling cooperative data-use across multiple users' SoLiD Pods. This scenario identifies the bottleneck for certain cooperative use cases, namely those involving offline-changing and synchronization of knowledge information. We demonstrate a viable approach to mediate this issue, introducing a long-living thin service, the orchestrator. We describe our implementation and discuss its applicability to other ecosystems. We conclude by discussing the implication of such services, in particular their risks and challenges for building decentralised applications., Comment: Accepted position paper in TrusDeKW, ESWC 2023

In this work, we propose a new method for multi-person pose estimation which combines the traditional bottom-up and the top-down methods. Specifically, we perform the network feed-forwarding in a bottom-up manner, and then parse the poses with bounding box constraints in a top-down manner. In contrast to the previous top-down methods, our method is robust to bounding box shift and tightness. We extract features from an original image by a residual network and train the network to learn both the confidence maps of joints and the connection relationships between joints. During testing, the predicted confidence maps, the connection relationships and the bounding boxes are used to parse the poses of all persons. The experimental results showed that our method learns more accurate human poses especially in challenging situations and gains better time performance, compared with the bottom-up and the top-down methods.