The hydrostatic or confining pressure of deep rocks has a significant impact on the mechanical behavior of brittle materials.Especially when confining pressure is applied,the mechanical properties of rock materials will ...The hydrostatic or confining pressure of deep rocks has a significant impact on the mechanical behavior of brittle materials.Especially when confining pressure is applied,the mechanical properties of rock materials will undergo significant changes.Considering that the process of shale sample subjected to impact load is in a closed container in the dynamic triaxial SHPB test,the failure process of the sample cannot be observed.Meanwhile,the activation volume of the shale sample would be large and local failure would occur in the test under the high strain rate loading.Therefore,thefinite element model of shale considering the bedding effect under confining pressure was established in this study.Taking shale materials with different bedding dip angles as simulation objects,the dynamic failure characteristics of shale were studied using the dynamic analysis software ANSYS/LS‐DYNA from three aspects:stress‐strain curve,failure growth process,and failure morphology.The research results obtained can serve as the key technical parameters for deep resource extraction.展开更多
Panoramic images are widely used in many scenes,especially in virtual reality and street view capture.However,they are new for street furniture identification which is usually based on mobile laser scanning point clou...Panoramic images are widely used in many scenes,especially in virtual reality and street view capture.However,they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images.This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks(FCN).FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction.In this study,we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data.Then replace cross entropy loss function with focal loss function in the FCN model and train it again to produce the predictions.The results show that in all results from pre-trained model,fine-tuning,and FCN model with focal loss,the light poles and traffic signs are detected well and the transformed images have better performance than panoramic images in the prediction according to the Recall and IoU evaluation.展开更多
基金National Key Research and Development Project of China,Grant/Award Number:2020YFA0711800National Natural Science Foundation of China,Grant/Award Numbers:12072363,12372373。
文摘The hydrostatic or confining pressure of deep rocks has a significant impact on the mechanical behavior of brittle materials.Especially when confining pressure is applied,the mechanical properties of rock materials will undergo significant changes.Considering that the process of shale sample subjected to impact load is in a closed container in the dynamic triaxial SHPB test,the failure process of the sample cannot be observed.Meanwhile,the activation volume of the shale sample would be large and local failure would occur in the test under the high strain rate loading.Therefore,thefinite element model of shale considering the bedding effect under confining pressure was established in this study.Taking shale materials with different bedding dip angles as simulation objects,the dynamic failure characteristics of shale were studied using the dynamic analysis software ANSYS/LS‐DYNA from three aspects:stress‐strain curve,failure growth process,and failure morphology.The research results obtained can serve as the key technical parameters for deep resource extraction.
文摘Panoramic images are widely used in many scenes,especially in virtual reality and street view capture.However,they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images.This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks(FCN).FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction.In this study,we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data.Then replace cross entropy loss function with focal loss function in the FCN model and train it again to produce the predictions.The results show that in all results from pre-trained model,fine-tuning,and FCN model with focal loss,the light poles and traffic signs are detected well and the transformed images have better performance than panoramic images in the prediction according to the Recall and IoU evaluation.