In this work, we propose a new method for multiperson pose estimation which combines the traditional bottomup 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.
Fructus Aurantii is a traditional medicated diet in East Asia. To determine the underlying chemical markers responsible for the quality and efficacy of Fructus Aurantii, a sensitive metabolomic method was applied to distinguish Fructus Aurantii in Jiangxi Province from other two geographical locations (Hunan Province and Chongqing City) in China. In the present study, multivariate analyses were adopted to compare chemical compositions in 21 batches of Fructus Aurantii samples. Among three geographical origins, 23 differential compounds were structurally identified. Serum pharmacochemistry exhibited that 22 components could be detected in rat serum. Six differential and absorbed components were selected as six potential markers. Statistical analysis revealed that the content of six markers varied widely in three origins of Fructus Aurantii. Six differential and absorbed components were evaluated further by biological activity. Neohesperidin, naringin, and meranzin showed inhibitory effect on acetylcholinesterase that regulates gastrointestinal motility in vitro and in silico, suggesting that these three components may be determined as the active biomarkers of Fructus Aurantii. These findings demonstrate the potential of biomarkers for identification and quality control of Fructus Aurantii.
We present a multiview method for markerless motion capture of multiple people. The main challenge in this problem is to determine cross-view correspondences for the 2D joints in the presence of noise. We propose a 3D hypothesis clustering technique to solve this problem. The core idea is to transform joint matching in 2D space into a clustering problem in a 3D hypothesis space. In this way, evidence from photometric appearance, multiview geometry, and bone length can be integrated to solve the clustering problem efficiently and robustly. Each cluster encodes a set of matched 2D joints for the same person across different views, from which the 3D joints can be effectively inferred. We then assemble the inferred 3D joints to form full-body skeletons for all persons in a bottom–up way. Our experiments demonstrate the robustness of our approach even in challenging cases with heavy occlusion, closely interacting people, and few cameras. We have evaluated our method on many datasets, and our results show that it has significantly lower estimation errors than many state-of-the-art methods.
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.