3D vehicle detection based on LiDAR-camera fusion is becoming an emerging research topic in autonomous driving.The algorithm based on the Camera-LiDAR object candidate fusion method(CLOCs)is currently considered to be...3D vehicle detection based on LiDAR-camera fusion is becoming an emerging research topic in autonomous driving.The algorithm based on the Camera-LiDAR object candidate fusion method(CLOCs)is currently considered to be a more effective decision-level fusion algorithm,but it does not fully utilize the extracted features of 3D and 2D.Therefore,we proposed a 3D vehicle detection algorithm based onmultimodal decision-level fusion.First,project the anchor point of the 3D detection bounding box into the 2D image,calculate the distance between 2D and 3D anchor points,and use this distance as a new fusion feature to enhance the feature redundancy of the network.Subsequently,add an attention module:squeeze-and-excitation networks,weight each feature channel to enhance the important features of the network,and suppress useless features.The experimental results show that the mean average precision of the algorithm in the KITTI dataset is 82.96%,which outperforms previous state-ofthe-art multimodal fusion-based methods,and the average accuracy in the Easy,Moderate and Hard evaluation indicators reaches 88.96%,82.60%,and 77.31%,respectively,which are higher compared to the original CLOCs model by 1.02%,2.29%,and 0.41%,respectively.Compared with the original CLOCs algorithm,our algorithm has higher accuracy and better performance in 3D vehicle detection.展开更多
In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection ...In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection will be affected by problems such as illumination changes,object occlusion,and object detection distance.To this purpose,we face these challenges by proposing a multimodal feature fusion network for 3D object detection(MFF-Net).In this research,this paper first uses the spatial transformation projection algorithm to map the image features into the feature space,so that the image features are in the same spatial dimension when fused with the point cloud features.Then,feature channel weighting is performed using an adaptive expression augmentation fusion network to enhance important network features,suppress useless features,and increase the directionality of the network to features.Finally,this paper increases the probability of false detection and missed detection in the non-maximum suppression algo-rithm by increasing the one-dimensional threshold.So far,this paper has constructed a complete 3D target detection network based on multimodal feature fusion.The experimental results show that the proposed achieves an average accuracy of 82.60%on the Karlsruhe Institute of Technology and Toyota Technological Institute(KITTI)dataset,outperforming previous state-of-the-art multimodal fusion networks.In Easy,Moderate,and hard evaluation indicators,the accuracy rate of this paper reaches 90.96%,81.46%,and 75.39%.This shows that the MFF-Net network has good performance in 3D object detection.展开更多
Low thermal expansion materials are mostly ceramics with low conductive property, which limits their applications in electronic devices. The poor conductive property of ceramic ZrV_2 O_7 could be improved by bi-substi...Low thermal expansion materials are mostly ceramics with low conductive property, which limits their applications in electronic devices. The poor conductive property of ceramic ZrV_2 O_7 could be improved by bi-substitution of Fe and Mo for Zr and V, accompanied with low thermal expansion. Zr_(0.1) Fe_(0.9) V_(1.1 )Mo_(0.9 )O_7 has electrical conductivity of 8.2× 10^(-5) S/cm and 9.41× 10^(-4) S/cm at 291 K and 623 K, respectively. From 291 K to 413 K, thermal excitation leads to the increase of carrier concentration, which causes the rapid decrease of resistance. At 413–533 K, the conductivity is unchanged due to high scattering probability and a slowing increase of carrier concentration. The conductivity rapidly increases again from533 K to 623 K due to the intrinsic thermal excitation. The thermal expansion coefficient of Zr_(0.1) Fe_(0.9) V_(1.1 )Mo_(0.9 )O_7 is as low as 0.72× 10^(-6 )K^(-1) at 140–700 K from the dilatometer measurement. These properties suggest that Zr_(0.1) Fe_(0.9) V_(1.1 )Mo_(0.9 )O_7 has attractive application in electronic components.展开更多
As a novel architecture,software-defined networking(SDN) is viewed as the key technology of future networking.The core idea of SDN is to decouple the control plane and the data plane,enabling centralized,flexible,and ...As a novel architecture,software-defined networking(SDN) is viewed as the key technology of future networking.The core idea of SDN is to decouple the control plane and the data plane,enabling centralized,flexible,and programmable network control.Although local area networks like data center networks have benefited from SDN,it is still a problem to deploy SDN in wide area networks(WANs) or large-scale networks.Existing works show that multiple controllers are required in WANs with each covering one small SDN domain.However,the problems of SDN domain partition and controller placement should be further addressed.Therefore,we propose the spectral clustering based partition and placement algorithms,by which we can partition a large network into several small SDN domains efficiently and effectively.In our algorithms,the matrix perturbation theory and eigengap are used to discover the stability of SDN domains and decide the optimal number of SDN domains automatically.To evaluate our algorithms,we develop a new experimental framework with the Internet2 topology and other available WAN topologies.The results show the effectiveness of our algorithm for the SDN domain partition and controller placement problems.展开更多
With the multi-tier pricing scheme provided by most of the cloud service providers (CSPs), the cloud userstypically select a high enough transmission service level to ensure the quality of service (QoS), due to th...With the multi-tier pricing scheme provided by most of the cloud service providers (CSPs), the cloud userstypically select a high enough transmission service level to ensure the quality of service (QoS), due to the severe penalty ofmissing the transmission deadline. This leads to the so-called over-provisioning problem, which increases the transmissioncost of the cloud user. Given the fact that cloud users may not be aware of their traffic demand before accessing the network,the over-provisioning problem becomes more serious. In this paper, we investigate how to reduce the transmission cost fromthe perspective of cloud users, especially when they are not aware of their traffic demand before the transmission deadline.The key idea is to split a long-term transmission request into several short ones. By selecting the most suitable transmissionservice level for each short-term request, a cost-efiqcient inter-datacenter transmission service level selection framework isobtained. We further formulate the transmission service level selection problem as a linear programming problem andresolve it in an on-line style with Lyapunov optimization. We evaluate the proposed approach with real traffic data. Theexperimental results show that our method can reduce the transmission cost by up to 65.04%.展开更多
All-inorganic cesium lead iodide(CsPbI_(3))perovskites with superior thermal stability are attractive candidates for perovskite solar cells(PSCs).Fabricating such inorganic PSCs in the ambient atmosphere is desirable ...All-inorganic cesium lead iodide(CsPbI_(3))perovskites with superior thermal stability are attractive candidates for perovskite solar cells(PSCs).Fabricating such inorganic PSCs in the ambient atmosphere is desirable for practical production,however,the challenge remains in inhibiting the phase transition of CsPbI_(3) in ambient air.Herein,we demonstrate a dual bulk and interface engineering using ionic liquid to stabilize CsPbI_(3) perovskite structure,thus enhancing the performance of ambient-processed inverted CsPbI_(3) PSCs.Such dual bulk and interface engineering is found effective not only in suppressing the bulk and interfacial charge carrier recombination and enhancing charge carrier transport and extraction,but also in protecting CsPbI_(3) crystal structure by leaving hydrophobic alkyl chains coverage at the boundary and surface to prevent phase transition caused by moisture from ambient air.The optimized device fully processed in the open air with relative humidity up to 55%exhibits remarkably enhanced efficiency and stability over the control device,with the efficiency increasing from 8.6%to 13.21%,and 92%efficiency maintaining after storage for 1680 h,which outperforms the control device with only 82%retaining after 648 h storage.We thus believe this work can provide an efficient alternative for the low-cost fabrication of ambient-processible PSCs.展开更多
基金supported by the Financial Support of the Key Research and Development Projects of Anhui (202104a05020003)the Natural Science Foundation of Anhui Province (2208085MF173)the Anhui Development and Reform Commission Supports R&D and Innovation Projects ([2020]479).
文摘3D vehicle detection based on LiDAR-camera fusion is becoming an emerging research topic in autonomous driving.The algorithm based on the Camera-LiDAR object candidate fusion method(CLOCs)is currently considered to be a more effective decision-level fusion algorithm,but it does not fully utilize the extracted features of 3D and 2D.Therefore,we proposed a 3D vehicle detection algorithm based onmultimodal decision-level fusion.First,project the anchor point of the 3D detection bounding box into the 2D image,calculate the distance between 2D and 3D anchor points,and use this distance as a new fusion feature to enhance the feature redundancy of the network.Subsequently,add an attention module:squeeze-and-excitation networks,weight each feature channel to enhance the important features of the network,and suppress useless features.The experimental results show that the mean average precision of the algorithm in the KITTI dataset is 82.96%,which outperforms previous state-ofthe-art multimodal fusion-based methods,and the average accuracy in the Easy,Moderate and Hard evaluation indicators reaches 88.96%,82.60%,and 77.31%,respectively,which are higher compared to the original CLOCs model by 1.02%,2.29%,and 0.41%,respectively.Compared with the original CLOCs algorithm,our algorithm has higher accuracy and better performance in 3D vehicle detection.
基金The authors would like to thank the financial support of Natural Science Foundation of Anhui Province(No.2208085MF173)the key research and development projects of Anhui(202104a05020003)+2 种基金the anhui development and reform commission supports R&D and innovation project([2020]479)the national natural science foundation of China(51575001)Anhui university scientific research platform innovation team building project(2016-2018).
文摘In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection will be affected by problems such as illumination changes,object occlusion,and object detection distance.To this purpose,we face these challenges by proposing a multimodal feature fusion network for 3D object detection(MFF-Net).In this research,this paper first uses the spatial transformation projection algorithm to map the image features into the feature space,so that the image features are in the same spatial dimension when fused with the point cloud features.Then,feature channel weighting is performed using an adaptive expression augmentation fusion network to enhance important network features,suppress useless features,and increase the directionality of the network to features.Finally,this paper increases the probability of false detection and missed detection in the non-maximum suppression algo-rithm by increasing the one-dimensional threshold.So far,this paper has constructed a complete 3D target detection network based on multimodal feature fusion.The experimental results show that the proposed achieves an average accuracy of 82.60%on the Karlsruhe Institute of Technology and Toyota Technological Institute(KITTI)dataset,outperforming previous state-of-the-art multimodal fusion networks.In Easy,Moderate,and hard evaluation indicators,the accuracy rate of this paper reaches 90.96%,81.46%,and 75.39%.This shows that the MFF-Net network has good performance in 3D object detection.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11574276,51702097,and 11574083)the Program for Innovative Research Team(in Science and Technology)in University of Henan Province,China(Grant No.16IRTSTHN017)Henan Science and Technology Development Project,China(Grant No.182102210241)
文摘Low thermal expansion materials are mostly ceramics with low conductive property, which limits their applications in electronic devices. The poor conductive property of ceramic ZrV_2 O_7 could be improved by bi-substitution of Fe and Mo for Zr and V, accompanied with low thermal expansion. Zr_(0.1) Fe_(0.9) V_(1.1 )Mo_(0.9 )O_7 has electrical conductivity of 8.2× 10^(-5) S/cm and 9.41× 10^(-4) S/cm at 291 K and 623 K, respectively. From 291 K to 413 K, thermal excitation leads to the increase of carrier concentration, which causes the rapid decrease of resistance. At 413–533 K, the conductivity is unchanged due to high scattering probability and a slowing increase of carrier concentration. The conductivity rapidly increases again from533 K to 623 K due to the intrinsic thermal excitation. The thermal expansion coefficient of Zr_(0.1) Fe_(0.9) V_(1.1 )Mo_(0.9 )O_7 is as low as 0.72× 10^(-6 )K^(-1) at 140–700 K from the dilatometer measurement. These properties suggest that Zr_(0.1) Fe_(0.9) V_(1.1 )Mo_(0.9 )O_7 has attractive application in electronic components.
基金supported by the National Natural Science Foundation of China(Nos.61432002,61370199,61370198,61300187,and 61402069)the Fundamental Research Funds for the Central Universities,China(Nos.DUT15QY20,DUT15TD29,and3132016029)the Prospective Research Project on Future Networks from Jiangsu Future Networks Innovation Institute,China
文摘As a novel architecture,software-defined networking(SDN) is viewed as the key technology of future networking.The core idea of SDN is to decouple the control plane and the data plane,enabling centralized,flexible,and programmable network control.Although local area networks like data center networks have benefited from SDN,it is still a problem to deploy SDN in wide area networks(WANs) or large-scale networks.Existing works show that multiple controllers are required in WANs with each covering one small SDN domain.However,the problems of SDN domain partition and controller placement should be further addressed.Therefore,we propose the spectral clustering based partition and placement algorithms,by which we can partition a large network into several small SDN domains efficiently and effectively.In our algorithms,the matrix perturbation theory and eigengap are used to discover the stability of SDN domains and decide the optimal number of SDN domains automatically.To evaluate our algorithms,we develop a new experimental framework with the Internet2 topology and other available WAN topologies.The results show the effectiveness of our algorithm for the SDN domain partition and controller placement problems.
基金This work is partially supported by the National Key Research and Development Program of China under Grant No. 2016YFB1000205, the State Key Program of National Natural Science Foundation of China under Grant No. 61432002, the National Natural Science Foundation of China-Guangdong Joint Fund under Grant No. U1701263, the National Natural Science Foundation of China under Grant Nos. 61702365, 61672379, and 61772112, the Natural Science Foundation of Tianjin under Grant Nos. 17JCQNJC00700 and 17JCYBJC15500, and the Special Program of Artificial Intelligence of Tianjin Municipal Science and Technology Commission under Grant No. 17ZXRGGX00150.
文摘With the multi-tier pricing scheme provided by most of the cloud service providers (CSPs), the cloud userstypically select a high enough transmission service level to ensure the quality of service (QoS), due to the severe penalty ofmissing the transmission deadline. This leads to the so-called over-provisioning problem, which increases the transmissioncost of the cloud user. Given the fact that cloud users may not be aware of their traffic demand before accessing the network,the over-provisioning problem becomes more serious. In this paper, we investigate how to reduce the transmission cost fromthe perspective of cloud users, especially when they are not aware of their traffic demand before the transmission deadline.The key idea is to split a long-term transmission request into several short ones. By selecting the most suitable transmissionservice level for each short-term request, a cost-efiqcient inter-datacenter transmission service level selection framework isobtained. We further formulate the transmission service level selection problem as a linear programming problem andresolve it in an on-line style with Lyapunov optimization. We evaluate the proposed approach with real traffic data. Theexperimental results show that our method can reduce the transmission cost by up to 65.04%.
基金financially supported by the Basic Research Programs of Taicang 2021 (No. TC2021JC22)the Guangdong Basic and Applied Basic Research Foundation (No. 2020A1515110727)+2 种基金the National Natural Science Foundation of China (No. 52002327, 62004169 and 51972272)the Fundamental Research Funds for the Central Universitiesthe Research Fund of the State Key Laboratory of Solidification Processing (NPU), China (No. 2019-QZ-03)
文摘All-inorganic cesium lead iodide(CsPbI_(3))perovskites with superior thermal stability are attractive candidates for perovskite solar cells(PSCs).Fabricating such inorganic PSCs in the ambient atmosphere is desirable for practical production,however,the challenge remains in inhibiting the phase transition of CsPbI_(3) in ambient air.Herein,we demonstrate a dual bulk and interface engineering using ionic liquid to stabilize CsPbI_(3) perovskite structure,thus enhancing the performance of ambient-processed inverted CsPbI_(3) PSCs.Such dual bulk and interface engineering is found effective not only in suppressing the bulk and interfacial charge carrier recombination and enhancing charge carrier transport and extraction,but also in protecting CsPbI_(3) crystal structure by leaving hydrophobic alkyl chains coverage at the boundary and surface to prevent phase transition caused by moisture from ambient air.The optimized device fully processed in the open air with relative humidity up to 55%exhibits remarkably enhanced efficiency and stability over the control device,with the efficiency increasing from 8.6%to 13.21%,and 92%efficiency maintaining after storage for 1680 h,which outperforms the control device with only 82%retaining after 648 h storage.We thus believe this work can provide an efficient alternative for the low-cost fabrication of ambient-processible PSCs.