发布求助
文献互助 智能选刊 最新文献

2023 18th International Conference on Machine Vision and Applications (MVA)最新文献

筛选
英文 中文
Panoptic Segmentation of Galactic Structures in LSB Images LSB图像中星系结构的全视分割
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10216057
Felix Richards, A. Paiement, Xianghua Xie, Elisabeth Sola, P. Duc
{"title":"Panoptic Segmentation of Galactic Structures in LSB Images","authors":"Felix Richards, A. Paiement, Xianghua Xie, Elisabeth Sola, P. Duc","doi":"10.23919/MVA57639.2023.10216057","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10216057","url":null,"abstract":"We explore the use of deep learning to localise galactic structures in low surface brightness (LSB) images. LSB imaging reveals many interesting structures, though these are frequently confused with galactic dust contamination, due to a strong local visual similarity. We propose a novel unified approach to multi-class segmentation of galactic structures and of extended amorphous image contaminants. Our panoptic segmentation model combines Mask R-CNN with a contaminant specialised network and utilises an adaptive preprocessing layer to better capture the subtle features of LSB images. Further, a human-in-the-loop training scheme is employed to augment ground truth labels. These different approaches are evaluated in turn, and together greatly improve the detection of both galactic structures and contaminants in LSB images.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127934303","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
Mixed Distillation for Unsupervised Anomaly Detection 用于无监督异常检测的混合蒸馏
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10215597
Fuzhen Cai, Siyu Xia
{"title":"Mixed Distillation for Unsupervised Anomaly Detection","authors":"Fuzhen Cai, Siyu Xia","doi":"10.23919/MVA57639.2023.10215597","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215597","url":null,"abstract":"Anomaly detection is typically a class of unsupervised learning problems in which the model is trained with only normal samples. Knowledge distillation (KD) has shown promising results in the field of image anomaly detection, especially for texture images. However, the knowledge of the classical KD model is step-by-step transferred from the shallow layers to the deep, which causes the deep layers not to be well-fitted due to an incomplete match of the shallow layers of the student network. For this problem, we propose a skip distillation method, which allows the deep layers of the student network to learn directly from the shallow of the teacher, avoiding a worse deep fit. We also design a symmetric path that allows the shallow layers of the student network to learn directly from the deep of the teacher. These two paths encode sufficient information for the student network. We have done thorough experiments on the anomaly detection benchmark dataset MvtecAD, and the experimental results show that our model exceeds the current state-of-the-art anomaly detection methods in terms of texture classes.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133511811","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
Multi-Prior Based Multi-Scale Condition Network for Single-Image HDR Reconstruction 基于多先验的单图像HDR重构多尺度条件网络
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10216063
Haorong Jiang, Fengshan Zhao, Junda Liao, Qin Liu, T. Ikenaga
{"title":"Multi-Prior Based Multi-Scale Condition Network for Single-Image HDR Reconstruction","authors":"Haorong Jiang, Fengshan Zhao, Junda Liao, Qin Liu, T. Ikenaga","doi":"10.23919/MVA57639.2023.10216063","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10216063","url":null,"abstract":"High Dynamic Range (HDR) imaging aims to reconstruct the natural appearance of real-world scenes by expanding the bit depth of captured images. However, due to the imaging pipeline of off-the-shelf cameras, information loss in over-exposed areas and noise in under-exposed areas pose significant challenges for single-image HDR imaging. As a result, the key to success lies in restoring over-exposed regions and denoising under-exposed regions. In this paper, a multi-prior based multi-scale condition network is proposed to address this issue. (1) Three types of prior knowledge modulate the intermediate features in the reconstruction network from different perspectives, resulting in improved modulation effects. (2) Multi-scale fusion extracts and integrates deep semantic information from various priors. Experiments on the NTIRE HDR challenge dataset demonstrate that the proposed method achieves state-of-the-art quantitative results.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128020555","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
Safe height estimation of deformable objects for picking robots by detecting multiple potential contact points 基于多个潜在接触点的可变形物体拾取机器人安全高度估计
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10215690
Jaesung Yang, Daisuke Hagihara, Kiyoto Ito, Nobuhiro Chihara
{"title":"Safe height estimation of deformable objects for picking robots by detecting multiple potential contact points","authors":"Jaesung Yang, Daisuke Hagihara, Kiyoto Ito, Nobuhiro Chihara","doi":"10.23919/MVA57639.2023.10215690","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215690","url":null,"abstract":"Object sorting in logistics warehouses is still carried out manually, and there is a great need for automation with arm robots. It is desirable that target objects be carefully placed in situations where careful handling of products is important. We propose a method for estimating the height of picked object with a single depth camera to achieve precise placing of items such as stacking, especially for objects that are deformable, e.g., bags. The proposed method detects multiple potential contact points of a picked object to estimate the appropriate height to place the object using the point-cloud difference before and after picking. The validity of the proposed method was verified using 26 cases in which deformable objects were placed inside a container, and it was confirmed that object-height estimation is possible with an average error of 3.2 mm.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124094200","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
Video Anomaly Detection Using Encoder-Decoder Networks with Video Vision Transformer and Channel Attention Blocks 基于视频视觉变压器和信道注意块的编码器-解码器网络的视频异常检测
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10215921
Shimpei Kobayashi, A. Hizukuri, R. Nakayama
{"title":"Video Anomaly Detection Using Encoder-Decoder Networks with Video Vision Transformer and Channel Attention Blocks","authors":"Shimpei Kobayashi, A. Hizukuri, R. Nakayama","doi":"10.23919/MVA57639.2023.10215921","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215921","url":null,"abstract":"A surveillance camera has been introduced in various locations for public safety. However, security personnel who have to keep observing surveillance camera movies with few abnormal events would be boring. The purpose of this study is to develop a computerized anomaly detection method for the surveillance camera movies. Our database consisted of three public datasets for anomaly detection: UCSD Pedestrian 1, 2, and CUHK Avenue datasets. In the proposed network, channel attention blocks were introduced to TransAnomaly which is one of the anomaly detections to focus important channel information. The areas under the receiver operating characteristic curves (AUCs) with the proposed network were 0.827 for UCSD Pedestrian 1, 0.964 for UCSD Pedestrian 2, and 0.854 for CUHK Avenue, respectively. The AUCs for the proposed network were greater than those for a conventional TransAnomaly without channel attention blocks (0.767, 0.934, and 0.839).","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"161 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125656568","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
TinyPedSeg: A Tiny Pedestrian Segmentation Benchmark for Top-Down Drone Images TinyPedSeg:一个微小的行人分割基准自上而下无人机图像
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10215829
Y. Sahin, Elvin Abdinli, M. A. Aydin, Gozde Unal
{"title":"TinyPedSeg: A Tiny Pedestrian Segmentation Benchmark for Top-Down Drone Images","authors":"Y. Sahin, Elvin Abdinli, M. A. Aydin, Gozde Unal","doi":"10.23919/MVA57639.2023.10215829","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215829","url":null,"abstract":"The usage of Unmanned Aerial Vehicles (UAVs) has significantly increased in various fields such as surveillance, agriculture, transportation, and military operations. However, the integration of UAVs in these applications requires the ability to navigate autonomously and detect/segment objects in real-time, which can be achieved through the use of neural networks. Despite object detection for RGB images/videos obtained from UAVs are widely studied before, limited effort has been made for segmentation from top-down aerial images. Considering the case in which the UAV is extremely high from the ground, the task can be formed as tiny object segmentation. Thus, inspired from the TinyPerson dataset which focuses on person detection from UAVs, we present TinyPedSeg, which contains 2563 pedestrians in 320 images. Specialized only in pedestrian segmentation, our dataset presents more informativeness than other UAV segmentation datasets. The dataset and the baseline codes are available at https://github.com/ituvisionlab/tinypedseg","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132021178","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
Uncertainty Criteria in Active Transfer Learning for Efficient Video-Specific Human Pose Estimation 主动迁移学习中的不确定性准则用于高效视频特定人体姿态估计
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10215565
Hiromu Taketsugu, N. Ukita
{"title":"Uncertainty Criteria in Active Transfer Learning for Efficient Video-Specific Human Pose Estimation","authors":"Hiromu Taketsugu, N. Ukita","doi":"10.23919/MVA57639.2023.10215565","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215565","url":null,"abstract":"This paper presents a combination of Active Learning (AL) and Transfer Learning (TL) for efficiently adapting Human Pose (HP) estimators to individual videos. The proposed approach quantifies estimation uncertainty through the temporal changes and unnaturalness of estimated HPs. These uncertainty criteria are combined with clustering-based representativeness criterion to avoid the useless selection of similar samples. Experiments demonstrated that the proposed method achieves high learning efficiency and outperforms comparative methods.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114247722","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
QaQ: Robust 6D Pose Estimation via Quality-Assessed RGB-D Fusion QaQ:基于质量评估RGB-D融合的稳健6D姿态估计
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10216208
Théo Petitjean, Zongwei Wu, O. Laligant, C. Demonceaux
{"title":"QaQ: Robust 6D Pose Estimation via Quality-Assessed RGB-D Fusion","authors":"Théo Petitjean, Zongwei Wu, O. Laligant, C. Demonceaux","doi":"10.23919/MVA57639.2023.10216208","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10216208","url":null,"abstract":"RGB-D 6D pose estimation has recently drawn great research attention thanks to the complementary depth information. Whereas, the depth and the color image are often noisy in real industrial scenarios. Therefore, it becomes challenging for many existing methods that fuse equally RGB and depth features. In this paper, we present a novel fusion design to adaptively merge RGB-D cues. Specifically, we created a Quality-assessment block that estimates the global quality of the input modalities. This quality represented as an α parameter is then used to reinforce the fusion. We have thus found a simple and effective way to improve the robustness to low-quality inputs in terms of Depth and RGB. Extensive experiments on 6D pose estimation demonstrate the efficiency of our method, especially when noise is present in the input.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114518314","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
Generalization of pixel-wise phase estimation by CNN and improvement of phase-unwrapping by MRF optimization for one-shot 3D scan 基于CNN的逐像素相位估计泛化及基于MRF优化的单次三维扫描相位展开改进
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10215780
Hiroto Harada, M. Mikamo, Furukawa Ryo, R. Sagawa, Hiroshi Kawasaki
{"title":"Generalization of pixel-wise phase estimation by CNN and improvement of phase-unwrapping by MRF optimization for one-shot 3D scan","authors":"Hiroto Harada, M. Mikamo, Furukawa Ryo, R. Sagawa, Hiroshi Kawasaki","doi":"10.23919/MVA57639.2023.10215780","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10215780","url":null,"abstract":"Active stereo technique using single pattern projection, a.k.a. one-shot 3D scan, have drawn a wide attention from industry, medical purposes, etc. One severe drawback of one-shot 3D scan is sparse reconstruction. In addition, since spatial pattern becomes complicated for the purpose of efficient embedding, it is easily affected by noise, which results in unstable decoding. To solve the problems, we propose a pixel-wise interpolation technique for one-shot scan, which is applicable to any types of static pattern if the pattern is regular and periodic. This is achieved by U-net which is pre-trained by CG with efficient data augmentation algorithm. In the paper, to further overcome the decoding instability, we propose a robust correspondence finding algorithm based on Markov random field (MRF) optimization. We also propose a shape refinement algorithm based on b-spline and Gaussian kernel interpolation using explicitly detected laser curves. Experiments are conducted to show the effectiveness of the proposed method using real data with strong noises and textures.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122561657","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
LOTS: Litter On The Sand dataset for litter segmentation lot:用于凋落物分割的沙地上的凋落物数据集
2023 18th International Conference on Machine Vision and Applications (MVA) Pub Date : 2023-07-23 DOI: 10.23919/MVA57639.2023.10216220
Paola Barra, Alessia Auriemma Citarella, Giosuè Orefice, M. Castrillón-Santana, A. Ciaramella
{"title":"LOTS: Litter On The Sand dataset for litter segmentation","authors":"Paola Barra, Alessia Auriemma Citarella, Giosuè Orefice, M. Castrillón-Santana, A. Ciaramella","doi":"10.23919/MVA57639.2023.10216220","DOIUrl":"https://doi.org/10.23919/MVA57639.2023.10216220","url":null,"abstract":"The marine ecosystem is threatened by human waste released into the sea. One of the most challenging marine litter to identify and remove are the small particles settled on the sand which may be ingested by local fauna or cause damage to the marine ecosystem. Those particles are not easy to identify because they get confused with maritime/natural material, natural elements such as shells, stones or others, which can not be classified as \"litter\". In this work we present a dataset of Litter On The Sand (LOTS), with images of clean, dirty and wavy sand from 3 different beaches.","PeriodicalId":338734,"journal":{"name":"2023 18th International Conference on Machine Vision and Applications (MVA)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123086610","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信