In response to the challenge of low detection accuracy and susceptibility to missed and false detections of small targets in unmanned aerial vehicles(UAVs)aerial images,an improved UAV image target detection algorithm...In response to the challenge of low detection accuracy and susceptibility to missed and false detections of small targets in unmanned aerial vehicles(UAVs)aerial images,an improved UAV image target detection algorithm based on YOLOv8 was proposed in this study.To begin with,the CoordAtt attention mechanism was employed to enhance the feature extraction capability of the backbone network,thereby reducing interference from backgrounds.Additionally,the BiFPN feature fusion network with an added small object detection layer was used to enhance the model's ability to perceive for small objects.Furthermore,a multi-level fusion module was designed and proposed to effectively integrate shallow and deep information.The use of an enhanced MPDIoU loss function further improved detection performance.The experimental results based on the publicly available VisDrone2019 dataset showed that the improved model outperformed the YOLOv8 baseline model,mAP@0.5 improved by 20%,and the improved method improved the detection accuracy of the model for small targets.展开更多
In this paper, for multi objective decision making, the defects on the commonly used interactive methods based on the satisfactoriness criterion is studied. Then a class of two stage interactive method based on the...In this paper, for multi objective decision making, the defects on the commonly used interactive methods based on the satisfactoriness criterion is studied. Then a class of two stage interactive method based on the satisfactoriness criterion is proposed for improvement with the satisfactoriness criterion being determined through the collection of the decision makers preference information. An application example is presented for illustration of applicability of the method.展开更多
To design retrieval algorithm of spatial relations for spatial objects with randomness in GIS,this paper builds up the membership functions based on set theory idea,used for determination of topological spatial relati...To design retrieval algorithm of spatial relations for spatial objects with randomness in GIS,this paper builds up the membership functions based on set theory idea,used for determination of topological spatial relations between random objects,such as between point and point,point and line or polygon,which provides theoretical basis for retrieving spatial relations between certain and random objects.Finally,this paper interprets detailed methods and steps of realizing them by means of some simple examples under the GIS’s environment.展开更多
In order to improve the accuracy of target intent recognition,a recognition method based on XGBoost(eXtreme Gradient Boosting)decision tree is proposed.This paper adopts relevant data and program of python to calculat...In order to improve the accuracy of target intent recognition,a recognition method based on XGBoost(eXtreme Gradient Boosting)decision tree is proposed.This paper adopts relevant data and program of python to calculate the probability of tactical intention.Then the sequence intention probability is obtained by applying Dempster-Shafer rule of combination.To verify the accuracy of recognition results,we compare the experimental results of this paper with the results in the literatures.The experiment shows that the probability of tactical intention recognition through this method is improved,so this method is feasible.展开更多
The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.I...The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.展开更多
The thesis aims to explain the functions of componential analysis to animal images in The Classic of Mountains and Seas. It serves as a treasure to the tremendous Chinese classics. However, as most of the animal image...The thesis aims to explain the functions of componential analysis to animal images in The Classic of Mountains and Seas. It serves as a treasure to the tremendous Chinese classics. However, as most of the animal images in the classic book are rarely seen in daily life, translation of animal images in the ancient Chinese book remains a hard nut to crack. In this case, explicit and accurate interpretation of these culture-loaded items is crucial to make readers understand. However, few previous studies touched upon this area. In this case, componential analysis serves as a solution. As an effective approach for analyzing semantic components, componential analysis is an effective way to break down semantic components of words and make them easily understood. In the previous studies, papers relating translation to componential analysis were not the majority. Among them, few papers are concerning application of componential analysis to the translation of literary works. In this essay, the analysis of animal images could be interpreted in lexical and textual level respectively. In this case, componential analysis bridges the gap for culture differences and enables readers of target language to savor the beauty. Therefore, readers of the target language can enjoy alien cultures of ancient China by reading this translated version.展开更多
Remote sensing image object detection is one of the core tasks of remote sensing image processing.In recent years,with the development of deep learning,great progress has been made in object detection in remote sensin...Remote sensing image object detection is one of the core tasks of remote sensing image processing.In recent years,with the development of deep learning,great progress has been made in object detection in remote sensing.However,the problems of dense small targets,complex backgrounds and poor target positioning accuracy in remote sensing images make the detection of remote sensing targets still difficult.In order to solve these problems,this research proposes a remote sensing image object detection algorithm based on improved YOLOX-S.Firstly,the Efficient Channel Attention(ECA)module is introduced to improve the network's ability to extract features in the image and suppress useless information such as background;Secondly,the loss function is optimized to improve the regression accuracy of the target bounding box.We evaluate the effectiveness of our algorithm on the NWPU VHR-10 remote sensing image dataset,the experimental results show that the detection accuracy of the algorithm can reach 95.5%,without increasing the amount of parameters.It is significantly improved compared with that of the original YOLOX-S network,and the detection performance is much better than that of some other mainstream remote sensing image detection methods.Besides,our method also shows good generalization detection performance in experiments on aircraft images in the RSOD dataset.展开更多
In order to make a decision in the face of multiple objectives, it is necessary to know the relative importance of the different objectives. Yet, it is often very difficult to specify a set of precise weights before p...In order to make a decision in the face of multiple objectives, it is necessary to know the relative importance of the different objectives. Yet, it is often very difficult to specify a set of precise weights before possible alternatives solutions are known. In this paper, we present an improved weighted method, which is based on a modified definition by the membership function of fuzzy theory; an interactive, iterative method for arriving at an acceptable solution. The decision maker gradually discerns what is achievable and adjusts his aspirations and implicitly the specification of weights and trade-offs between his objectives, in the light of what he learns. To aid the decision maker＇s cognition and to allow him to express his wishes in a natural way, we present decision maker with grey relational degree to select the best solution from the finite solutions.展开更多
文摘In response to the challenge of low detection accuracy and susceptibility to missed and false detections of small targets in unmanned aerial vehicles(UAVs)aerial images,an improved UAV image target detection algorithm based on YOLOv8 was proposed in this study.To begin with,the CoordAtt attention mechanism was employed to enhance the feature extraction capability of the backbone network,thereby reducing interference from backgrounds.Additionally,the BiFPN feature fusion network with an added small object detection layer was used to enhance the model's ability to perceive for small objects.Furthermore,a multi-level fusion module was designed and proposed to effectively integrate shallow and deep information.The use of an enhanced MPDIoU loss function further improved detection performance.The experimental results based on the publicly available VisDrone2019 dataset showed that the improved model outperformed the YOLOv8 baseline model,mAP@0.5 improved by 20%,and the improved method improved the detection accuracy of the model for small targets.
文摘In this paper, for multi objective decision making, the defects on the commonly used interactive methods based on the satisfactoriness criterion is studied. Then a class of two stage interactive method based on the satisfactoriness criterion is proposed for improvement with the satisfactoriness criterion being determined through the collection of the decision makers preference information. An application example is presented for illustration of applicability of the method.
文摘To design retrieval algorithm of spatial relations for spatial objects with randomness in GIS,this paper builds up the membership functions based on set theory idea,used for determination of topological spatial relations between random objects,such as between point and point,point and line or polygon,which provides theoretical basis for retrieving spatial relations between certain and random objects.Finally,this paper interprets detailed methods and steps of realizing them by means of some simple examples under the GIS’s environment.
文摘In order to improve the accuracy of target intent recognition,a recognition method based on XGBoost(eXtreme Gradient Boosting)decision tree is proposed.This paper adopts relevant data and program of python to calculate the probability of tactical intention.Then the sequence intention probability is obtained by applying Dempster-Shafer rule of combination.To verify the accuracy of recognition results,we compare the experimental results of this paper with the results in the literatures.The experiment shows that the probability of tactical intention recognition through this method is improved,so this method is feasible.
基金National Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)University Superior Discipline Construction Project of Jiangsu Province。
文摘The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.
文摘The thesis aims to explain the functions of componential analysis to animal images in The Classic of Mountains and Seas. It serves as a treasure to the tremendous Chinese classics. However, as most of the animal images in the classic book are rarely seen in daily life, translation of animal images in the ancient Chinese book remains a hard nut to crack. In this case, explicit and accurate interpretation of these culture-loaded items is crucial to make readers understand. However, few previous studies touched upon this area. In this case, componential analysis serves as a solution. As an effective approach for analyzing semantic components, componential analysis is an effective way to break down semantic components of words and make them easily understood. In the previous studies, papers relating translation to componential analysis were not the majority. Among them, few papers are concerning application of componential analysis to the translation of literary works. In this essay, the analysis of animal images could be interpreted in lexical and textual level respectively. In this case, componential analysis bridges the gap for culture differences and enables readers of target language to savor the beauty. Therefore, readers of the target language can enjoy alien cultures of ancient China by reading this translated version.
基金Supported by the National Natural Science Foundation of China (72174172, 71774134)the Fundamental Research Funds for Central University,Southwest Minzu University (2022NYXXS094)。
文摘Remote sensing image object detection is one of the core tasks of remote sensing image processing.In recent years,with the development of deep learning,great progress has been made in object detection in remote sensing.However,the problems of dense small targets,complex backgrounds and poor target positioning accuracy in remote sensing images make the detection of remote sensing targets still difficult.In order to solve these problems,this research proposes a remote sensing image object detection algorithm based on improved YOLOX-S.Firstly,the Efficient Channel Attention(ECA)module is introduced to improve the network's ability to extract features in the image and suppress useless information such as background;Secondly,the loss function is optimized to improve the regression accuracy of the target bounding box.We evaluate the effectiveness of our algorithm on the NWPU VHR-10 remote sensing image dataset,the experimental results show that the detection accuracy of the algorithm can reach 95.5%,without increasing the amount of parameters.It is significantly improved compared with that of the original YOLOX-S network,and the detection performance is much better than that of some other mainstream remote sensing image detection methods.Besides,our method also shows good generalization detection performance in experiments on aircraft images in the RSOD dataset.
基金This research is supported by National Natural Science Foundation of China（70471019）
文摘In order to make a decision in the face of multiple objectives, it is necessary to know the relative importance of the different objectives. Yet, it is often very difficult to specify a set of precise weights before possible alternatives solutions are known. In this paper, we present an improved weighted method, which is based on a modified definition by the membership function of fuzzy theory; an interactive, iterative method for arriving at an acceptable solution. The decision maker gradually discerns what is achievable and adjusts his aspirations and implicitly the specification of weights and trade-offs between his objectives, in the light of what he learns. To aid the decision maker＇s cognition and to allow him to express his wishes in a natural way, we present decision maker with grey relational degree to select the best solution from the finite solutions.
