Automatic identification of key points within objects is crucial in various application domains. This paper presents a novel framework for accurately estimating the key point within an object by leveraging deep neural network-based object detection. The proposed framework is built upon a training dataset annotated with four non-overlapping bounding boxes, one of which shares a coordinate with the key point. These bounding boxes collectively cover the entire object, enabling automatic annotation if region annotations around the key point exist. The trained object detector is then utilized to generate detection results, which are subsequently post-processed to estimate the key point. To validate the effectiveness of the framework, experiments were conducted using two distinct datasets: cross-sectional images of a parawood log and pupil images. The experimental results demonstrate that our proposed framework surpasses previously proposed approaches in terms of precision, recall, F1-score, and other domain-specific metrics. The improvement in performance can be attributed to the unique annotation strategy and the fusion of object detection and key point estimation within a unified deep learning framework. The contribution of this study lies in introducing a novel framework for closely estimating key points within objects based on deep neural network-based object detection. By leveraging annotated training data and post-processing techniques, our approach achieves superior performance compared to existing methods. This work fills a critical gap in the field by integrating object detection and key point estimation, which has received limited attention in previous research. Our framework provides valuable insights and advancements in key point estimation techniques, offering potential applications in precise object analysis and understanding. Doi: 10.28991/HIJ-2023-04-01-08 Full Text: PDF
This article examines numerically the behavior of prestressed reinforced concrete slabs strengthened with externally bonded reinforcement (EBR) consisting of fiber-reinforced polymer (FRP) sheets. The non-linear finite element (FE) program Abaqus® is used to model EBR FRP-strengthened prestressed concrete slabs tested previously in four-point bending. After the calibration of the computational models, a parametric study is then conducted to assess the influence of the FRP axial stiffness (thickness and modulus of elasticity) on the interfacial normal and shear stresses. The numerical analysis results show that increasing the thickness or the elastic modulus of the FRP strengthening affects the efficiency of the FRP bonding and makes it susceptible to earlier debonding failures. A tapering technique is proposed in wet lay-up applications since multiple FRP layers are often required. It is shown that by gradually decreasing the thickness of the FRP strengthening, the concentration of stress along the plate end can be reduced, and thus, the overall strengthening performance is maximized. The tapering is successful in reducing the bond stress concentrations by up to 15%, which can be sufficient to prevent concrete rip-off and peel-off debonding failure modes. This article contributes towards a better understanding of the debonding phenomena in FRP-strengthened elements in flexure and towards the development of more efficient computational tools to analyze such structures.
This article presents a case study on the thermal assessment of a reinforced concrete (RC) foundation exposed to low temperatures. The foundation supports a 19,500 m3-capacity tank with low-temperature (−89 °C) ethane. Icing and bubbling were observed on the tank’s surface soon after it started operations. Condensation was also observed at the bottom of the 0.8-m-depth RC slab, which raised concerns about the structural condition of the concrete. This study provides details of the field and analytical investigations conducted to assess the structural condition of the foundation. Heat transfer finite element (FE) analyses were performed to examine the concrete sections subjected to low temperatures. It was found that the ethane leakage produced a low temperature on the top side of the concrete foundation of +9.7 °C. Overall, the temperatures calculated by the FE analyses were in good agreement with actual field measurements, within a ±5% accuracy. The simplified heat transfer equation for porous media used in this study was sufficiently accurate to model the effects of the ethane leakage in the concrete foundation, provided that the ambient temperature at the site is taken into account in the analysis. The results also confirm that reinforcing bars can be neglected in the thermal analysis of massive concrete slabs. The results from the field measurements and FE analyses confirmed that the structural integrity of the RC foundation was never compromised. The approaches, methods and techniques discussed in this article are deemed suitable to solve the practical and scientific challenges involved in the thermal assessment and repairs of large special structures. Accordingly, they can serve as useful reference and guidance for engineers and practitioners working in the field of forensic engineering.
A gait recognition framework is proposed to tackle the challenge of unknown camera view angles as well as appearance changes in gait recognition. In the framework, camera view angles are firstly identified before gait recognition. Two compact images, gait energy image (GEI) and gait modified Gaussian image (GMGI), are used as the base gait feature images. Histogram of oriented gradients (HOG) is applied to the base gait feature images to generate feature descriptors, and then a final feature map after principal component analysis (PCA) operations on the descriptors are used to train support vector machine (SVM) models for individuals. A set of experiments are conducted on CASIA gait database B to investigate how appearance changes and unknown view angles affect the gait recognition accuracy under the proposed framework. The experimental results have shown that the framework is robust in dealing with unknown camera view angles, as well as appearance changes in gait recognition. In the unknown view angle testing, the recognition accuracy matches that of identical view angle testing in gait recognition. The proposed framework is specifically applicable in personal identification by gait in a small company/organization, where unintrusive personal identification is needed.
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.