Search

Modeling the hand-object (HO) interaction not only requires estimation of the HO pose, but also pays attention to the contact due to their interaction. Significant progress has been made in estimating hand and object separately with deep learning methods, simultaneous HO pose estimation and contact modeling has not yet been fully explored. In this paper, we present an explicit contact representation namely Contact Potential Field (CPF), and a learning-fitting hybrid framework namely MIHO to Modeling the Interaction of Hand and Object. In CPF, we treat each contacting HO vertex pair as a spring-mass system. Hence the whole system forms a potential field with minimal elastic energy at the grasp position. Extensive experiments on the two commonly used benchmarks have demonstrated that our method can achieve state-of-the-art in several reconstruction metrics, and allow us to produce more physically plausible HO pose even when the ground-truth exhibits severe interpenetration or disjointedness. Our code is available at https://github.com/lixiny/CPF., ICCV 2021, (reduce PDF file size)

Object handover is a common human collaboration behavior that attracts attention from researchers in Robotics and Cognitive Science. Though visual perception plays an important role in the object handover task, the whole handover process has been specifically explored. In this work, we propose a novel rich-annotated dataset, H2O, for visual analysis of human-human object handovers. The H2O, which contains 18K video clips involving 15 people who hand over 30 objects to each other, is a multi-purpose benchmark. It can support several vision-based tasks, from which, we specifically provide a baseline method, RGPNet, for a less-explored task named Receiver Grasp Prediction. Extensive experiments show that the RGPNet can produce plausible grasps based on the giver's hand-object states in the pre-handover phase. Besides, we also report the hand and object pose errors with existing baselines and show that the dataset can serve as the video demonstrations for robot imitation learning on the handover task. Dataset, model and code will be made public.

This paper is aimed at making diagnosis for turbine blades by processing data. In this paper three kinds of feature are extracted, using time-domain analysis, wavelet packet decomposition and fractal analysis respectively. K-means algorithm is improved to classify data. The method of improved ReliefF is taken to allocate weights of each feature. This article calculates combined feature center distance synthesized. Take the obtained centre distance as a threshold to diagnose faults. Comparison is made to verify that application of cluster analysis and weight allocation algorithm can reduce error rate in detecting diagnosing faults for turbine blades.

This study analyzes the internal control of electronic commerce enterprises in China. At first, the paper reveals some problems on the internal control of these enterprises such as the bad conditions, lacking risk management, the unsound supervision system and so on. And then, this paper suggests that e-commerce enterprises should improve corporation governance, actively evaluate operating risks and financial risks, and better the supervision system of the internal control.

Lots of researches have been done on computer animation of tree swaying in wind. Some of them employed artificial simplification methods which could not achieve faithful swaying motion, others adopted complicated physical principles which would involve vast computation and fail to get an appropriate rendering speed. This paper presents a series of convenient interactive physical based methods for animation of trees swaying in wind. We focus on both the faithful swaying motion and the appropriate rendering speed. Therefore, a lot of statistical curves, representing wind profile loaded in tree or stem displacement profile and so on, are introduced for swaying motion calculation. All those curves can be modified interactively to get best match with the researches of botanists and other experts. These methods can be adjusted quickly and conveniently to simulate the animation of faithful tree swaying in wind with proper engineering accuracy and effective computation.