With the continuous development of artificial intelligence and computer vision technology,numerous deep learning-based lane line detection methods have emerged.DeepLabv3+,as a classic semantic segmentation model,has f...With the continuous development of artificial intelligence and computer vision technology,numerous deep learning-based lane line detection methods have emerged.DeepLabv3+,as a classic semantic segmentation model,has found widespread application in the field of lane line detection.However,the accuracy of lane line segmentation is often compromised by factors such as changes in lighting conditions,occlusions,and wear and tear on the lane lines.Additionally,DeepLabv3+suffers from high memory consumption and challenges in deployment on embedded platforms.To address these issues,this paper proposes a lane line detection method for complex road scenes based on DeepLabv3+and MobileNetV4(MNv4).First,the lightweight MNv4 is adopted as the backbone network,and the standard convolutions in ASPP are replaced with depthwise separable convolutions.Second,a polarization attention mechanism is introduced after the ASPP module to enhance the model’s generalization capability.Finally,the Simple Linear Iterative Clustering(SLIC)superpixel segmentation algorithmis employed to preserve lane line edge information.MNv4-DeepLabv3+was tested on the TuSimple and CULane datasets.On the TuSimple dataset,theMean Intersection over Union(MIoU)and Mean Pixel Accuracy(mPA)improved by 1.01%and 7.49%,respectively.On the CULane dataset,MIoU andmPA increased by 3.33%and 7.74%,respectively.Thenumber of parameters decreased from 54.84 to 3.19 M.Experimental results demonstrate that MNv4-DeepLabv3+significantly optimizes model parameter count and enhances segmentation accuracy.展开更多
In response to the challenges presented by the unreliable identity of the master node,high communication overhead,and limited network support size within the Practical Byzantine Fault-Tolerant(PBFT)algorithm for conso...In response to the challenges presented by the unreliable identity of the master node,high communication overhead,and limited network support size within the Practical Byzantine Fault-Tolerant(PBFT)algorithm for consortium chains,we propose an improved PBFT algorithm based on XGBoost grouping called XG-PBFT in this paper.XG-PBFT constructs a dataset by training important parameters that affect node performance,which are used as classification indexes for nodes.The XGBoost algorithm then is employed to train the dataset,and nodes joining the system will be grouped according to the trained grouping model.Among them,the nodes with higher parameter indexes will be assigned to the consensus group to participate in the consensus,and the rest of the nodes will be assigned to the general group to receive the consensus results.In order to reduce the resource waste of the system,XG-PBFT optimizes the consensus protocol for the problem of high complexity of PBFT communication.Finally,we evaluate the performance of XG-PBFT.The experimental results show that XG-PBFT can significantly improve the performance of throughput,consensus delay and communication complexity compared to the original PBFT algorithm,and the performance enhancement is significant compared to other algorithms in the case of a larger number of nodes.The results demonstrate that the XG-PBFT algorithm is more suitable for large-scale consortium chains.展开更多
文摘With the continuous development of artificial intelligence and computer vision technology,numerous deep learning-based lane line detection methods have emerged.DeepLabv3+,as a classic semantic segmentation model,has found widespread application in the field of lane line detection.However,the accuracy of lane line segmentation is often compromised by factors such as changes in lighting conditions,occlusions,and wear and tear on the lane lines.Additionally,DeepLabv3+suffers from high memory consumption and challenges in deployment on embedded platforms.To address these issues,this paper proposes a lane line detection method for complex road scenes based on DeepLabv3+and MobileNetV4(MNv4).First,the lightweight MNv4 is adopted as the backbone network,and the standard convolutions in ASPP are replaced with depthwise separable convolutions.Second,a polarization attention mechanism is introduced after the ASPP module to enhance the model’s generalization capability.Finally,the Simple Linear Iterative Clustering(SLIC)superpixel segmentation algorithmis employed to preserve lane line edge information.MNv4-DeepLabv3+was tested on the TuSimple and CULane datasets.On the TuSimple dataset,theMean Intersection over Union(MIoU)and Mean Pixel Accuracy(mPA)improved by 1.01%and 7.49%,respectively.On the CULane dataset,MIoU andmPA increased by 3.33%and 7.74%,respectively.Thenumber of parameters decreased from 54.84 to 3.19 M.Experimental results demonstrate that MNv4-DeepLabv3+significantly optimizes model parameter count and enhances segmentation accuracy.
文摘In response to the challenges presented by the unreliable identity of the master node,high communication overhead,and limited network support size within the Practical Byzantine Fault-Tolerant(PBFT)algorithm for consortium chains,we propose an improved PBFT algorithm based on XGBoost grouping called XG-PBFT in this paper.XG-PBFT constructs a dataset by training important parameters that affect node performance,which are used as classification indexes for nodes.The XGBoost algorithm then is employed to train the dataset,and nodes joining the system will be grouped according to the trained grouping model.Among them,the nodes with higher parameter indexes will be assigned to the consensus group to participate in the consensus,and the rest of the nodes will be assigned to the general group to receive the consensus results.In order to reduce the resource waste of the system,XG-PBFT optimizes the consensus protocol for the problem of high complexity of PBFT communication.Finally,we evaluate the performance of XG-PBFT.The experimental results show that XG-PBFT can significantly improve the performance of throughput,consensus delay and communication complexity compared to the original PBFT algorithm,and the performance enhancement is significant compared to other algorithms in the case of a larger number of nodes.The results demonstrate that the XG-PBFT algorithm is more suitable for large-scale consortium chains.
