2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)最新文献_第2页

Low Effectiveness of Non-Geometric-Operation Data Augmentations for Lesion Segmentation with Fully Convolution Networks

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492891

Yuming Qiu, Xiaolin Qin, Ju Zhang

{"title":"Low Effectiveness of Non-Geometric-Operation Data Augmentations for Lesion Segmentation with Fully Convolution Networks","authors":"Yuming Qiu, Xiaolin Qin, Ju Zhang","doi":"10.1109/ICIVC.2018.8492891","DOIUrl":"https://doi.org/10.1109/ICIVC.2018.8492891","url":null,"abstract":"Data augmentation is a prevalent strategy to enlarge the training data in order to enhance the generalization of the model of deep convolutional neural networks (DCNNs). However, not all of augmentation schemes are always effective for all types of DCNNs models, especially for fully convolutional networks (FCNs) which greatly improved semantic segmentation by employing a skip architecture that fuses the feature hierarchy to combine deep, coarse, semantic information and shallow, fine, appearance information. In order to make the effectiveness of data augmentation clear, in this work, we propose to divide the augmentation schemes into two groups, geometric operations and non-geometric operations. Through analyzing the performance of them for lesion segmentation with FCNs, it is found that non-geometric-operation data augmentations are less effective in two dermoscopy datasets. Moreover, we further theoretically revealed that the skip architecture in FCNs is the main reason behind this finding. This work is of value on guiding the practice of data augmentation while using FCNs, and enlightening significance for analyzing other skip architecture deep neural networks.","PeriodicalId":173981,"journal":{"name":"2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124040908","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

Synthesizing Plausible Videos by Introducing Favorable Object Pose Using Trajectory Matching 利用轨迹匹配引入有利目标姿态合成可信视频

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492774

M. Seifelnasr, A. Ismail, Hongxing Guo

{"title":"Synthesizing Plausible Videos by Introducing Favorable Object Pose Using Trajectory Matching","authors":"M. Seifelnasr, A. Ismail, Hongxing Guo","doi":"10.1109/ICIVC.2018.8492774","DOIUrl":"https://doi.org/10.1109/ICIVC.2018.8492774","url":null,"abstract":"Video is a mean of keeping our memories in a chronological way. Due to the proliferation of handheld devices embedded with high-resolution camera, people became fond of filming themselves everywhere. Yet, not always, people are in their best appearance and mood. Sometimes, they come across scenery sites and they want to record this moment. However, due to the lack of filming experience and the sudden of the event, the output video is below the expectation. In this paper, we propose a workflow to produce a plausible video of the people. The workflow introduced the appearance and behavior depicted in another clip of the user into the recorded outing scenery clip. The workflow considered the variance in both the size and the trajectory of the user during a fixed-camera video. The validity of the workflow is demonstrated by conducting two experiments where the input videos are recorded with different cameras in different circumstances to produce a plausible video. The output video is composed of the background from the scenery video and the foreground object and behavior from the raw data video.","PeriodicalId":173981,"journal":{"name":"2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126247170","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

Methods for Long-Distance Crack Location and Detection of Concrete Bridge Structures 混凝土桥梁结构长距离裂缝定位与检测方法

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492764

Youfa Cai, Xing Fu, Y. Shang, Jingxin Shi

{"title":"Methods for Long-Distance Crack Location and Detection of Concrete Bridge Structures","authors":"Youfa Cai, Xing Fu, Y. Shang, Jingxin Shi","doi":"10.1109/ICIVC.2018.8492764","DOIUrl":"https://doi.org/10.1109/ICIVC.2018.8492764","url":null,"abstract":"In order to improve the efficiency of crack detection of concrete bridge structures, a new method based on computer vision technology and coordinate mapping is proposed. In this research, this crack measurement system is integrated mainly with a high magnification image acquisition system, a two-dimensional electric cradle head device and a laser ranging system. It has a set of observing coordinate system. Firstly, the marking points' image coordinates are mapped to the observation coordinates. Secondly, according to the marking points' observation coordinates, the measured crack's coordinates are mapped to a same world coordinates so as to realize the spatial location of the measured cracks regardless of different test cycles or instrument's setup positions, which is a great convenience for the review detection of surface cracks of concrete bridge structures. The experiments show that this method is efficient and convenient. It can automatically locate the measured cracks within 16 s, and the deviation is not more than ± 0.07 °. At a distance of 100 m, the measurement accuracy of crack width is better than ± 0.12 mm.","PeriodicalId":173981,"journal":{"name":"2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126210557","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: 9

Touching Objects Count with Progressive Erosion 触摸物体以渐进侵蚀计数

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492742

Jiye Qian, Jin Fu, Bin Fang, Xin Zhou, Hengjun Zhao, Jide Qian, Bangfei Deng, Haibing Zhang, Weiwen Zhang

引用次数: 0

Adaptive Blind Correction of TIADC Mismatch Based on Cyclic Autocorrelation 基于循环自相关的TIADC失配自适应盲校正

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492905

Maowei Yin, Z. Ye

引用次数: 1

Simulations of Ground Clutter Filter Design and Velocity Dealiasing of Dual-PRF Signals for X-Band Weather Radar x波段气象雷达地杂波滤波器设计与双prf信号速度去噪仿真

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492775

Xiao Liang, Tao Wang

引用次数: 0

Generalizing Integer Projected Graph Matching Algorithm for Outlier Problem 离群点问题的广义整数投影图匹配算法

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492896

Lei He, Xu Yang, Zhiyong Liu

引用次数: 1

A Deep Learning Framework Using Convolutional Neural Network for Multi-Class Object Recognition 基于卷积神经网络的多类物体识别深度学习框架

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492777

Shaukat Hayat, She Kun, Zuo Tengtao, Yue Yu, Tianyi Tu, Yan-ping Du

{"title":"A Deep Learning Framework Using Convolutional Neural Network for Multi-Class Object Recognition","authors":"Shaukat Hayat, She Kun, Zuo Tengtao, Yue Yu, Tianyi Tu, Yan-ping Du","doi":"10.1109/ICIVC.2018.8492777","DOIUrl":"https://doi.org/10.1109/ICIVC.2018.8492777","url":null,"abstract":"Object recognition is classic technique used to effectively recognize an object in the image. Technologies specifically in field of computer vision are expected to detect and recognize more complex tasks with help of local features detection methods. Over the last decade, there has been sustained increase in the number of researchers from various kind of disciplines i.e. academia, industry, security agencies and even from general public has caught an attention to explore the covered aspects of object detection and recognition concerned problems. It is further significantly amended by adopting deep learning model. In this paper, we applied deep learning to multi-class object recognition and explore convolutional neural network (CNN). The convolutional neural network is created with normalized standard initialization and trained with training set of sample images from 9 different object categories plus sample test images using widely varied dataset. All results are implemented in python tensorflow framework. We examine and compared CNN results with final feature vectors extracted from variant approaches of BOW based on linear L2-SVM classifier. Based on it, sufficient experiments verify our CNN model effectiveness and robustness with rate of 90.12% accuracy.","PeriodicalId":173981,"journal":{"name":"2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115345030","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: 29

An Efficient Way to Estimate the Focus of Expansion 一种估算扩张焦点的有效方法

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492881

Rui Huang, S. Ericson

引用次数: 1

A Robust Tracking Algorithm Based on Feature Fusion and Occlusion Judgment 一种基于特征融合和遮挡判断的鲁棒跟踪算法

2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) Pub Date : 2018-06-01 DOI: 10.1109/ICIVC.2018.8492748

Cheng-Gang Gu, Zhan-Li Sun, Xia Chen

引用次数: 0