Proceedings of the 3rd International Conference on Vision, Image and Signal Processing最新文献_第6页

Practical Issues in Contingency Planning for UAVs with Engine Failures 无人机发动机故障应急计划的实践问题

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387202

B. Ayhan, C. Kwan

{"title":"Practical Issues in Contingency Planning for UAVs with Engine Failures","authors":"B. Ayhan, C. Kwan","doi":"10.1145/3387168.3387202","DOIUrl":"https://doi.org/10.1145/3387168.3387202","url":null,"abstract":"Unmanned Air Vehicles (UAV), also known as Unmanned Air Systems (UAS), are gaining more attention in recent years. Some potential commercial applications with UAVs may include small cargo transport, search and rescue operations, drought and pest monitoring, etc. It is well-known that UAVs are less reliable as compared to manned aircraft. This is probably one of the consequential reasons that Federal Aviation Administration (FAA) is hesitant to open up the national airspace (NAS) and imposes tight restrictions to UAVs. Reliability of UAVs can be improved using engines and equipment with high quality and fault diagnostic algorithms using machine learning and artificial intelligence techniques, and robust and fault tolerant controllers. Despite the above measures, engine and equipment malfunctions may still appear in various applications. In this paper, we summarize some recent research results by us with respect to engine failures encountered in UAVs. Due to engine failure, there is limited hanging time and the mishap UAV needs to land preferably in an unpopulated area. In particular, we explicitly address some practical issues related to engine failures.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116383215","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}

引用次数: 0

Sliding Mode Control Design for a Two-Stage of Electro-Hydraulic Valve 两级电液阀滑模控制设计

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387231

Alper Esatoglu, M. U. Salamci

引用次数: 0

Far Point Algorithm: Active Semi-supervised Clustering for Rare Category Detection 远点算法:用于稀有类别检测的主动半监督聚类

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3389117

R. Loveland, Jonathan Amdahl

引用次数: 2

Development of Digital Platform for Social Media Creating in the Kyrgyz Republic 吉尔吉斯共和国社会媒体创作数位平台的发展

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387215

Bolotbek Biibosunov, Saltanat Biibosunova, Marat Kozhonov

引用次数: 2

Wired Sensors System for Monitoring of Landslide Events 滑坡事件监测有线传感器系统

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387229

M. Muttillo, G. Barile, A. Leoni, G. Ferri

{"title":"Wired Sensors System for Monitoring of Landslide Events","authors":"M. Muttillo, G. Barile, A. Leoni, G. Ferri","doi":"10.1145/3387168.3387229","DOIUrl":"https://doi.org/10.1145/3387168.3387229","url":null,"abstract":"Landslides are catastrophic events that change the territory making these events dangerous for buildings and people. Monitoring and alerting on a possible landslide can avoid disasters and can save lives. Thanks to a monitoring system it is possible to prevent and intervene in time before the situation gets worse. The aim of this work is the design of a wired sensor monitoring system for landslide events. The system is composed by one datalogger and many nodes, which measure the inclination, and communicate between each other through RS485. The datalogger is based on a microcontroller ATmega2560 which has the task of retrieving data from nodes and sending them to an FTP server. The nodes have an ATmega328p microcontroller that reads data from a digital accelerometer MMA8451 that is able to detect inclination variations up to 0.1 degrees. Furthermore, the nodes are able to go into sleep mode reducing power consumption. The system includes a calibration phase for the first installation on site to be monitored. The proposed system was tested in a real case and same preliminary data, obtained after a post processing done with Matlab, are here reported.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134327050","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}

引用次数: 1

Digital Watermarking Algorithm for 2D Vector Graphics 二维矢量图形的数字水印算法

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387186

Yue Ding, Jianrong Wang, Xiang Ying

引用次数: 0

Sparse-to-Dense Depth Completion in Precision Farming 精准农业中从稀疏到密集的深度完井

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387230

Sadaf Farkhani, M. Kragh, P. Christiansen, R. Jørgensen, H. Karstoft

{"title":"Sparse-to-Dense Depth Completion in Precision Farming","authors":"Sadaf Farkhani, M. Kragh, P. Christiansen, R. Jørgensen, H. Karstoft","doi":"10.1145/3387168.3387230","DOIUrl":"https://doi.org/10.1145/3387168.3387230","url":null,"abstract":"Autonomous driving in agriculture can be eased and be more safe if guided by dense depth maps, since dense depth maps outlines scene geometry. RGB monocular image has only naive information about depth and although LiDAR has accurate depth information, it can only provide sparse depth maps. By interpolating sparse LiDAR with aligned color image, reliable dense depth maps can be created. In this paper, we apply a deep regression model where an RGB monocular image was used for a sparse-to-dense LiDAR depth map completion. Our model is based on U-Net architecture presented in [9]. Training the model on the Fieldsafe dataset which is a multi-modal agricultural dataset, however, leads to overfitting. Therefore, we trained the model on the Kitti dataset with high image diversity and test it on the Fieldsafe. We produced an error map to analyze performance of the model for close or far distant objects in the Fieldsafe dataset. The error maps show the absolute difference between the depth ground truth and the predicted depth value. The model preforms 63.6% better on close distance objects than far objects in Fieldsafe. However, the model performs 10.96% better on far objects than close objects in the Kitti dataset.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123486236","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}

引用次数: 2

A Novel Method for Extending V2V System 一种扩展V2V系统的新方法

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387197

Qiang Zheng, Jian Wang

{"title":"A Novel Method for Extending V2V System","authors":"Qiang Zheng, Jian Wang","doi":"10.1145/3387168.3387197","DOIUrl":"https://doi.org/10.1145/3387168.3387197","url":null,"abstract":"Autonomous vehicles requires sufficient perception of the surrounding environment to make proper driving behavior. Vehicle-to-vehicle (V2V) is a technology that allow vehicles exchange location information (i.e. velocity, position) which can improve the perception capabilities of traditional on-board sensors. However, there are still obstacles preventing the roll-out of the V2X technology, mainly the fact that, unless almost the totality of the existing vehicles adopt it, its effectiveness is rather limited. We can't guarantee that all vehicles are V2V vehicles in real environment due to many reasons. In the traditional V2V system, only V2V vehicle have the ability to broadcast their own location information, but non-V2V vehicle can't. But, the situation is somewhat different in our V2V system. Although, non-V2V vehicles don't have the ability to broadcast their own location information, we can let V2V vehicle detect the location information of non-V2V vehicle and broadcast them out. Therefore, we can think that the non-V2V vehicle can also have the ability to broadcast its own location information in our V2V system. In this way, we extend the ability of traditional V2V system to a certain extent. The proposed method is validated under real-world conditions in urban area.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121414078","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}

引用次数: 1

EP GEO Propulsion Platform 地球同步推进平台

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387227

Jan-Patric Porst, Cyril Dietz, M. Abele

引用次数: 0

A Machine Learning Approach for Detection Plant Disease: Taking Orchid as Example 植物病害检测的机器学习方法——以兰花为例

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387238

Li-Hua Li, Yu-Sheng Chu, Jui-Yuan Chu, Shian-Hau Guo

{"title":"A Machine Learning Approach for Detection Plant Disease: Taking Orchid as Example","authors":"Li-Hua Li, Yu-Sheng Chu, Jui-Yuan Chu, Shian-Hau Guo","doi":"10.1145/3387168.3387238","DOIUrl":"https://doi.org/10.1145/3387168.3387238","url":null,"abstract":"The export value of flower production is very high in many countries. Among these export flowers, orchids are considered one of the most valuable flowers. In order to increase orchid production, it is important to take closely care of orchid in the cultivation period. Due to the plant diseases may cause the economic losses in agricultural industry, the daily inspection and early recognition of plant diseases are necessary. Detection and prevention of plant diseases are a worldwide agricultural problem. Many researchers have proposed biocontrol or IT technology to handle plant disease problems. Some researchers applied image recognition to find out leaf problems such as banana leaves, alfalfa leaves, and citrus leaves. However, these researches all focus on trees or fruits in the lab. They did not provide the long-distance leaf identification for orchid flowers. To help flower farmers and to enhance the quality of production, this research has proposed a machine learning method to capture the image of orchid leaf and to identify the leaf disease. This research analyzes the leaf image with feature space, i.e., HSI, RGB, and grayscale. We use histogram to analysis the leaf color and we analyze the green color threshold so that the image can be classified into various color zones. Based on the generated threshold, this research is able to segment the leaf image into healthy area and unhealthy area. Finally, we use the Artificial Neural Network (ANN) and Deep Learning ANN to learn the image patterns of orchid leaf. Our proposed method is then applied to identify the orchid leaves and to determine whether the orchid is healthy or sick. With our proposed model, the accuracy of recognizing the leaf disease can achieve 100% for training data and 90% for testing data. This research enables flower farmers to recognize the orchid disease and can prevent the disease in early stage. As a result, the farmer can take better care to the orchid plants and enhance the cultivation of orchid production.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125241808","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}

引用次数: 6