2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC)最新文献_第2页

Super-Resolution Reconstruction Algorithm of Target Image Based on Learning Background 基于学习背景的目标图像超分辨率重建算法

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177444

Shuning Li, Huasheng Zhu, Kaiwen Zha, Wei Li

引用次数: 0

Bus Signal Priority Control Method Based on Video Detection Technology at Urban Intersection 基于视频检测技术的城市交叉口公交信号优先控制方法

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177475

Shan Li, Huizhi Xu, Zijun Liang, Chengyuan Mao

{"title":"Bus Signal Priority Control Method Based on Video Detection Technology at Urban Intersection","authors":"Shan Li, Huizhi Xu, Zijun Liang, Chengyuan Mao","doi":"10.1109/ICIVC50857.2020.9177475","DOIUrl":"https://doi.org/10.1109/ICIVC50857.2020.9177475","url":null,"abstract":"In order to improve the traffic efficiency of public transportation, alleviate the urban traffic congestion and improve the overall traffic efficiency. On the one hand, this paper proposed a method for identifying bus vehicles with signal priority based on video detectors, which solved the shortcomings of current GPS signal priority control methods such as inaccurate GPS positioning, unstable wireless communication transmission signals, and high construction costs. On the other hand, the algorithm logic of bus signal priority control was proposed. The algorithm took average passenger delay as the optimization index, realizes the signal priority of bus at urban intersections. At the same time, considered reducing the negative impact of public transport signal priority on non-priority social vehicles. Finally, the simulation test of actual urban intersection cases was carried out by using VISSIM micro simulation software. The simulation results showed that, compared with the traditional signal control method, considered the bus signal priority signal timing scheme can effectively reduce the average passenger delay and vehicle queue length, and further improve the traffic efficiency of the intersection.","PeriodicalId":6806,"journal":{"name":"2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC)","volume":"114 1","pages":"256-260"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88687652","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

A Technology for Automatically Counting Bus Passenger Based on YOLOv2 and MIL Algorithm 基于YOLOv2和MIL算法的公交车乘客自动计数技术

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177434

Leyuan Liu, Jian He, Yibin Hou, Cheng Zhang

引用次数: 2

EDLLIE-Net: Enhanced Deep Convolutional Networks for Low-Light Image Enhancement EDLLIE-Net:用于微光图像增强的增强深度卷积网络

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177454

Xue Ke, Wei Lin, Gaojie Chen, Quan Chen, Xianzhi Qi, Jie Ma

{"title":"EDLLIE-Net: Enhanced Deep Convolutional Networks for Low-Light Image Enhancement","authors":"Xue Ke, Wei Lin, Gaojie Chen, Quan Chen, Xianzhi Qi, Jie Ma","doi":"10.1109/ICIVC50857.2020.9177454","DOIUrl":"https://doi.org/10.1109/ICIVC50857.2020.9177454","url":null,"abstract":"Low-light image enhancement technology has been developed in recent years. However, most existing related methods need to adjust too many arguments or performs unstably when the environment differs greatly. In our paper, we propose a novel low-light image enhancement method named enhanced deep convolutional low-light image enhancement network (EDLLIE-Net) to address these problems. Firstly, our proposed method extracts multi-scale feature map, which can improve the utilization of context information. Subsequently, our proposed method rescales the feature map by attention mechanism to perceive the most useful information and characteristics. Finally, our proposed method uses encode-decode and residual-learning architecture to obtain the normal image from low-light image. To prove the effectiveness of our proposed model, we evaluate it from two aspects. On one hand, we show EDLLIE-Net can not only handle different dark scenes effectively but also achieve better performance than other representative methods by common metric judgement. On the other hand, a novel evaluation method by combining enhanced result and high-level vision task is proposed, we show our proposed method can gain the higher improvement degree for high-level vision tasks.","PeriodicalId":6806,"journal":{"name":"2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC)","volume":"111 1","pages":"59-68"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83557179","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: 8

Research on the Influence of Icon Shape Complexity and Composition on Visual Search Based on Military Geographic Intelligence System 基于军事地理情报系统的图标形状复杂度和组成对视觉搜索的影响研究

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177485

Xian Li, Haiyan Wang, Junkai Shao

{"title":"Research on the Influence of Icon Shape Complexity and Composition on Visual Search Based on Military Geographic Intelligence System","authors":"Xian Li, Haiyan Wang, Junkai Shao","doi":"10.1109/ICIVC50857.2020.9177485","DOIUrl":"https://doi.org/10.1109/ICIVC50857.2020.9177485","url":null,"abstract":"This article discusses the influence of icon shape complexity and composition on icon search in military geographical intelligence system. We designed an experiment to explore the influence of icon shape complexity and composition on icon search efficiency in military geographic intelligence system (GIS). The reaction time and accuracy are used in the experiment to reflect people's search efficiency under different experimental conditions. The experimental results provide a scientific reference for the design of military GIS interface by analyzing the effect of different icon shapes and icon presentation on the visual search performance of military GIS interface. Through experiments, it is found that when the icon shape complexity level is the highest or the lowest, it shows poor search performance; when the complexity level is H3, it shows the best search performance; the icon composition does not affect the search performance of the icon on the map background. Significant, but when the complexity level is H2 and H4, there is interaction between different icon composition. This design will provide a reference for the design of GIS interface icons. The experimental results provide a scientific reference for the design of military GIS interface.","PeriodicalId":6806,"journal":{"name":"2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC)","volume":"1 1","pages":"247-250"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89560672","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

Image Transmission via LoRa Networks – A Survey LoRa网络图像传输综述

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177489

Anestis Staikopoulos, V. Kanakaris, G. Papakostas

引用次数: 10

Human Fall Detection Algorithm Based on YOLOv3 基于YOLOv3的人体跌倒检测算法

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177447

Xiang Wang, Ke-bin Jia

引用次数: 21

Multi-frame Image Super-Resolution Algorithm Based on Small Amount of Data 基于小数据量的多帧图像超分辨率算法

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177476

Yuhang Jiang, Yuwei Lu, Lili Dong, Wenhai Xu

引用次数: 2

A-DFPN: Adversarial Learning and Deformation Feature Pyramid Networks for Object Detection A-DFPN:用于目标检测的对抗学习和变形特征金字塔网络

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177437

Miao Cheng, Jinpeng Su, Luyi Li, Xiangming Zhou

{"title":"A-DFPN: Adversarial Learning and Deformation Feature Pyramid Networks for Object Detection","authors":"Miao Cheng, Jinpeng Su, Luyi Li, Xiangming Zhou","doi":"10.1109/ICIVC50857.2020.9177437","DOIUrl":"https://doi.org/10.1109/ICIVC50857.2020.9177437","url":null,"abstract":"In order to weak the variation of the object instance caused by the scale, we innovatively propose an object detection detector based on adversarial learning and deformation feature pyramid: A-DFPN. Firstly, in the feature extraction stage, the concept of Deformation Feature Pyramid Module is proposed. The outstanding advantage is that it can fully extract object features from different convolution layers and objects of different scales. In addition, Two Stage Module is also proposed, it gradually perfects the adjusted anchors in the previous stage through multi-step regression, and locates the position and shape of the object in each RPN to make the location more accurate. At the same time, Mask Module increases the robustness of the detector by spatially blocking certain feature maps or by manipulating feature responses to generate difficult samples. Finally, the final bounding boxes is filtered by soft-NMS. Under the Resnet-101 network architecture, our algorithm achieves the mean average precision of 81.1034% on the Pascal VOC 2007 dataset and 73.52% on the DETRAC dataset, reaching the state-of-the-art detection level.","PeriodicalId":6806,"journal":{"name":"2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC)","volume":"40 1","pages":"11-18"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77176592","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

Support Vector Machine Based Spectrum Allocation Scheme for the Mobile Cognitive Radio Manhattan City Environments 基于支持向量机的移动认知无线电曼哈顿城市环境频谱分配方案

2020 IEEE 5th International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2020-07-01 DOI: 10.1109/ICIVC50857.2020.9177436

Yao Wang, Yi Zhang, Jiamei Chen, Yang Long, Yang Yang

引用次数: 0