Chao Feng, Weike Liu, Xianhui Cao, Zhiwei Jia, Yujing Hu
In this paper, tests were carried out on the working state and the dischargestatus of the Unmanned Aerial Vehicles(UAV) motorwith different distances between the UAV and 110kV and 220kV live high-voltage wires. The results showed that the UAV could still keep regular operation when the distance between the 110kV wire and the UAV motor was 0.5m.It ran properly at a distance of 1m from the 220kV wire.The wire suddenly discharged electricity and punched through the UAV when it was boosted to 200kV at a distance of 0.5m from the UAV motor, but the UAV motor was not damaged.
{"title":"Discharge Test of Unmanned Aerial Vehicles and Live High-voltage Wires","authors":"Chao Feng, Weike Liu, Xianhui Cao, Zhiwei Jia, Yujing Hu","doi":"10.1145/3548608.3559287","DOIUrl":"https://doi.org/10.1145/3548608.3559287","url":null,"abstract":"In this paper, tests were carried out on the working state and the dischargestatus of the Unmanned Aerial Vehicles(UAV) motorwith different distances between the UAV and 110kV and 220kV live high-voltage wires. The results showed that the UAV could still keep regular operation when the distance between the 110kV wire and the UAV motor was 0.5m.It ran properly at a distance of 1m from the 220kV wire.The wire suddenly discharged electricity and punched through the UAV when it was boosted to 200kV at a distance of 0.5m from the UAV motor, but the UAV motor was not damaged.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115451412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose a prediction method for extreme weather events. In order to evaluate and forecast the intensity of extreme weather events, we first quantify the intensity of extreme weather, using the T-Year weather events concept from a mathematical point of view. On this basis, the grey model, which has an excellent performance in short-term prediction, is then used to predict the occurrence rate of extreme weather events with specific intensities. The effectiveness of the proposed method is verified through an illustrative example using hail weather data in the United States.
{"title":"Forecasting of Extreme Weather Intensity Based on Grey Model","authors":"Yong-hong Zhou, Xinyue Wang, Daozhong Zhang","doi":"10.1145/3548608.3559193","DOIUrl":"https://doi.org/10.1145/3548608.3559193","url":null,"abstract":"In this paper, we propose a prediction method for extreme weather events. In order to evaluate and forecast the intensity of extreme weather events, we first quantify the intensity of extreme weather, using the T-Year weather events concept from a mathematical point of view. On this basis, the grey model, which has an excellent performance in short-term prediction, is then used to predict the occurrence rate of extreme weather events with specific intensities. The effectiveness of the proposed method is verified through an illustrative example using hail weather data in the United States.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122114690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traffic congestion has become an inevitable and difficult disease in the process of urban development, and it has also brought harm and hidden dangers to citizens' travel and urban development. The emergence of GCN solves the problem of capturing the spatial characteristics of urban road traffic. Based on this, we propose a new method that considers the periodicity of traffic patterns and builds a neural network model with multiple time scales to capture more detailed features. And the experiment proves that our model is better in predicting traffic congestion.
{"title":"A deep learning urban traffic congestion forecast model blending the temporal continuity and periodicity","authors":"Bin Mu, Yuxi Huang","doi":"10.1145/3548608.3559271","DOIUrl":"https://doi.org/10.1145/3548608.3559271","url":null,"abstract":"Traffic congestion has become an inevitable and difficult disease in the process of urban development, and it has also brought harm and hidden dangers to citizens' travel and urban development. The emergence of GCN solves the problem of capturing the spatial characteristics of urban road traffic. Based on this, we propose a new method that considers the periodicity of traffic patterns and builds a neural network model with multiple time scales to capture more detailed features. And the experiment proves that our model is better in predicting traffic congestion.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129956733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aiming at the technical problems of communication equipment support, combined with the classification of communication elements and the extraction of eigenvalues, this paper uses the comprehensive evaluation method to evaluate the effectiveness of the comprehensive technical support capability of each element. Firstly, the analytic hierarchy process and entropy weight method are used to calculate the subjective and objective weights respectively, and then the characteristics are comprehensively weighted in combination with them. Finally, the grey correlation method is used to rank the element support effectiveness, the feasibility of the algorithm model is proved by simulation.
{"title":"Research on Technical Support Ability of Communication Equipment Based on Comprehensive Evaluation Method","authors":"Hua Qin, Haoyan Gong, Junlai Song, Deqin Wang","doi":"10.1145/3548608.3559217","DOIUrl":"https://doi.org/10.1145/3548608.3559217","url":null,"abstract":"Aiming at the technical problems of communication equipment support, combined with the classification of communication elements and the extraction of eigenvalues, this paper uses the comprehensive evaluation method to evaluate the effectiveness of the comprehensive technical support capability of each element. Firstly, the analytic hierarchy process and entropy weight method are used to calculate the subjective and objective weights respectively, and then the characteristics are comprehensively weighted in combination with them. Finally, the grey correlation method is used to rank the element support effectiveness, the feasibility of the algorithm model is proved by simulation.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128227722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a control flow anomaly detection model, which applies neural network to control flow anomaly detection and performs feature extraction and behavior modeling of control flow. At present, there is little research on the control flow anomaly detection of neural networks, and there is no in-depth research on the feature extraction of data. We studied the characteristics of control flow, used Intel Processor Trace to implement the extraction and processing of control flow, and designed a basic block vectorization method based on time series features and a basic block vectorization method based on structural features. The vectorization methods eliminate the manual amount of feature engineering. The anomaly detection model uses a bidirectional LSTM and it combines the idea of a classification plane. We perform corresponding evaluations based on the adobe reader software. Experimental results show that the model achieves a 98.74% recall rate and a 0.44% false positive rate for the corresponding control flow anomaly detection of Adobe Reader in an offline environment, effectively detects the exploit, and successfully distinguishes between benign and malicious control flow.
{"title":"Software Control Flow Anomaly Detection Technology Based On Neural Network","authors":"Xinda Xu, Jingling Zhao, Baojiang Cui","doi":"10.1145/3548608.3559263","DOIUrl":"https://doi.org/10.1145/3548608.3559263","url":null,"abstract":"This paper presents a control flow anomaly detection model, which applies neural network to control flow anomaly detection and performs feature extraction and behavior modeling of control flow. At present, there is little research on the control flow anomaly detection of neural networks, and there is no in-depth research on the feature extraction of data. We studied the characteristics of control flow, used Intel Processor Trace to implement the extraction and processing of control flow, and designed a basic block vectorization method based on time series features and a basic block vectorization method based on structural features. The vectorization methods eliminate the manual amount of feature engineering. The anomaly detection model uses a bidirectional LSTM and it combines the idea of a classification plane. We perform corresponding evaluations based on the adobe reader software. Experimental results show that the model achieves a 98.74% recall rate and a 0.44% false positive rate for the corresponding control flow anomaly detection of Adobe Reader in an offline environment, effectively detects the exploit, and successfully distinguishes between benign and malicious control flow.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115954580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As the key technology of automatic driving perception module, vehicle detection in complex scenes requires real-time and accurate acquisition of the position and distance information of surrounding vehicles, so as to ensure the safety of passengers. Centernet algorithm performs well in vehicle detection, achieving a trade-off between accuracy and speed, but the network only extracts features of the target at the last layer of the feature map, leading to the problem of missed and false detections during detection. Therefore, this paper proposes a Vehicle-CenterNet detection model, which obtains more detailed information by modifying the original ResNet, constructing layered connections within a single residual block, and increasing the perceptual field size of each layer by stacking convolution operators. In addition, the Mish activation function is used instead of the ReLU activation function, and the smoothed activation function allows better information penetration into the neural network, resulting in better accuracy and generalization. The normalization-based attention module (NAM) is also incorporated to suppress non-target features and further improve the detection accuracy of the model. Experimental results on VOC dataset and KITTI dataset show that the mean average precision (mAP) and F1 Score of the proposed method are improved to different degrees, and the comprehensive performance is better than the original CenterNet algorithm.
{"title":"Vehicle detection algorithm based on multi-scale features and normalization attention model","authors":"Yu-Shuai Duan, Huarong Xu, Lifen Weng","doi":"10.1145/3548608.3559196","DOIUrl":"https://doi.org/10.1145/3548608.3559196","url":null,"abstract":"As the key technology of automatic driving perception module, vehicle detection in complex scenes requires real-time and accurate acquisition of the position and distance information of surrounding vehicles, so as to ensure the safety of passengers. Centernet algorithm performs well in vehicle detection, achieving a trade-off between accuracy and speed, but the network only extracts features of the target at the last layer of the feature map, leading to the problem of missed and false detections during detection. Therefore, this paper proposes a Vehicle-CenterNet detection model, which obtains more detailed information by modifying the original ResNet, constructing layered connections within a single residual block, and increasing the perceptual field size of each layer by stacking convolution operators. In addition, the Mish activation function is used instead of the ReLU activation function, and the smoothed activation function allows better information penetration into the neural network, resulting in better accuracy and generalization. The normalization-based attention module (NAM) is also incorporated to suppress non-target features and further improve the detection accuracy of the model. Experimental results on VOC dataset and KITTI dataset show that the mean average precision (mAP) and F1 Score of the proposed method are improved to different degrees, and the comprehensive performance is better than the original CenterNet algorithm.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126466257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid economic development, motor vehicles are becoming more popular, and artificial intelligence applications on the road are emerging in endlessly. In current road vehicle detection algorithms, most of them use single-frame image information intercepted from video sequences for vehicle detection. This method does not take into account that the difference between frames in the video sequence is mainly the motion background information. Aiming at this design limitation, this paper proposes a target detection method based on IFFF (Inter-Frame Feature Fusion). In the input part of the model, in addition to adding the picture of the current frame, the feature map output of the previous frame will be added to enrich the information of the current frame and improve the detection performance of the current frame. At the same time, a spatial pyramid pooling structure is added to the network to further integrate local and global features to improve the ability to detect vehicles. Experiments show that the method proposed in this paper can improve the detection effect of vehicles in road scenes. Compared with the original CenterNet detection network, the mAP index is improved by 4.3%.
{"title":"Road Vehicle Detection Based on Feature Fusion Between Frames","authors":"Xinbo Ai, Fu Gong, Yingjian Wang, Yanjun Guo","doi":"10.1145/3548608.3559277","DOIUrl":"https://doi.org/10.1145/3548608.3559277","url":null,"abstract":"With the rapid economic development, motor vehicles are becoming more popular, and artificial intelligence applications on the road are emerging in endlessly. In current road vehicle detection algorithms, most of them use single-frame image information intercepted from video sequences for vehicle detection. This method does not take into account that the difference between frames in the video sequence is mainly the motion background information. Aiming at this design limitation, this paper proposes a target detection method based on IFFF (Inter-Frame Feature Fusion). In the input part of the model, in addition to adding the picture of the current frame, the feature map output of the previous frame will be added to enrich the information of the current frame and improve the detection performance of the current frame. At the same time, a spatial pyramid pooling structure is added to the network to further integrate local and global features to improve the ability to detect vehicles. Experiments show that the method proposed in this paper can improve the detection effect of vehicles in road scenes. Compared with the original CenterNet detection network, the mAP index is improved by 4.3%.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127475181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cancers of the digestive tract include esophageal tumors, gastric tumors, and intestinal tumors. Radiation oncologists try to deliver high doses of radiation using X-rays directed at the tumor while avoiding the stomach and intestine, but the complex manual labeling of the gut is time-consuming and inaccurate. Using deep learning can help automate the segmentation process, and this method of segmenting the stomach and intestine will lead to faster treatment. It will allow more patients to be treated more effectively. Thus, we propose a network model for GI segmentation that uses a residual network with a fused channel attention mechanism as an encoder for the U-Net model, combined with a U-Net decoder and a feature fusion architecture to achieve pixel-level classification and segmentation of images. In our experiments, we choose IOU as the model evaluation index, and the higher the IOU, the better the performance of the model. The experimental results show that the IOU of our model is improved by 1.8% to 2.5% compared with other models, which outperforms other models in the GI segmentation task.
{"title":"SER-UNet: A Network for Gastrointestinal Image Segmentation","authors":"Hongwei Niu, Yutong Lin","doi":"10.1145/3548608.3559197","DOIUrl":"https://doi.org/10.1145/3548608.3559197","url":null,"abstract":"Cancers of the digestive tract include esophageal tumors, gastric tumors, and intestinal tumors. Radiation oncologists try to deliver high doses of radiation using X-rays directed at the tumor while avoiding the stomach and intestine, but the complex manual labeling of the gut is time-consuming and inaccurate. Using deep learning can help automate the segmentation process, and this method of segmenting the stomach and intestine will lead to faster treatment. It will allow more patients to be treated more effectively. Thus, we propose a network model for GI segmentation that uses a residual network with a fused channel attention mechanism as an encoder for the U-Net model, combined with a U-Net decoder and a feature fusion architecture to achieve pixel-level classification and segmentation of images. In our experiments, we choose IOU as the model evaluation index, and the higher the IOU, the better the performance of the model. The experimental results show that the IOU of our model is improved by 1.8% to 2.5% compared with other models, which outperforms other models in the GI segmentation task.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131394436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Human-computer interaction system based on computer vision is an important research direction in the field of human-computer interaction, which has broad application prospects in natural human-computer interaction, sign language recognition, virtual reality, smart home, somatosensory games and other fields. In this paper, an interactive visual perception method is proposed, which uses human experience to guide the computer to quickly build the visual perception model. By analyzing the difference between the predicted image and the actual image read by the camera, the area with large reflectivity change on the projection screen is found as the user area. This method can find the position of real human hand correctly even if the projection image contains human hand. Three-dimensional coordinates of fingertips are obtained by stereo matching principle, and Kalman filtering tracking algorithm is used to smooth the trajectory of fingertips and narrow the detection range of the next frame.
{"title":"Research on fingertip positioning and human-computer interaction technology based on stereo vision","authors":"Guoquan Cong","doi":"10.1145/3548608.3559178","DOIUrl":"https://doi.org/10.1145/3548608.3559178","url":null,"abstract":"Human-computer interaction system based on computer vision is an important research direction in the field of human-computer interaction, which has broad application prospects in natural human-computer interaction, sign language recognition, virtual reality, smart home, somatosensory games and other fields. In this paper, an interactive visual perception method is proposed, which uses human experience to guide the computer to quickly build the visual perception model. By analyzing the difference between the predicted image and the actual image read by the camera, the area with large reflectivity change on the projection screen is found as the user area. This method can find the position of real human hand correctly even if the projection image contains human hand. Three-dimensional coordinates of fingertips are obtained by stereo matching principle, and Kalman filtering tracking algorithm is used to smooth the trajectory of fingertips and narrow the detection range of the next frame.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128092393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Waste classification has attracted more and more attention in recent years, which is an important part of building an eco-friendly city. Traditional manual garbage classification has poor efficiency and accuracy. In this paper, based on deep learning, the garbage classification algorithm I-ResNet50 is proposed to improve the ResNet50 network, and the geometric transformation of the original data is performed. The test set results show that the I-ResNet50 algorithm can achieve a classification accuracy of 62.6%, which is a substantial improvement in accuracy compared with the original method.
{"title":"Deep learning based recyclable waste classification","authors":"Yulong He, Tianjian Li, Jianchao Huang, Zejun Zhang, Zhuangzhuang Wang, Zhiming Cai","doi":"10.1145/3548608.3559190","DOIUrl":"https://doi.org/10.1145/3548608.3559190","url":null,"abstract":"Waste classification has attracted more and more attention in recent years, which is an important part of building an eco-friendly city. Traditional manual garbage classification has poor efficiency and accuracy. In this paper, based on deep learning, the garbage classification algorithm I-ResNet50 is proposed to improve the ResNet50 network, and the geometric transformation of the original data is performed. The test set results show that the I-ResNet50 algorithm can achieve a classification accuracy of 62.6%, which is a substantial improvement in accuracy compared with the original method.","PeriodicalId":201434,"journal":{"name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134332382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：