2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA)最新文献_第3页

Using Facial Action Recognition to Evaluate User Perception in Aggravated HRC Scenarios 使用面部动作识别评估重度HRC场景下的用户感知

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552079

Laslo Dinges, A. Al-Hamadi, Thorsten Hempel, Z. Aghbari

引用次数: 2

Dimension Estimation in Two-Dimensional PCA 二维主成分分析中的维数估计

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552114

Una Radojicic, Niko Lictzén, K. Nordhausen, Joni Virta

引用次数: 2

Bounding Box Propagation for Semi-automatic Video Annotation of Nighttime Driving Scenes 基于边界盒传播的夜间驾驶场景半自动视频标注

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552141

Dominik Schörkhuber, Florian Groh, M. Gelautz

{"title":"Bounding Box Propagation for Semi-automatic Video Annotation of Nighttime Driving Scenes","authors":"Dominik Schörkhuber, Florian Groh, M. Gelautz","doi":"10.1109/ISPA52656.2021.9552141","DOIUrl":"https://doi.org/10.1109/ISPA52656.2021.9552141","url":null,"abstract":"Ground-truth annotations are a fundamental requirement for the development of computer vision and deep learning algorithms targeting autonomous driving. Available public datasets have for the most part been recorded in urban settings, while scenes showing countryside roads and nighttime driving conditions are underrepresented in current datasets. In this paper, we present a semi-automated approach for bounding box annotation which was developed in the context of nighttime driving videos. In our three-step approach, we (a) generate trajectory proposals through a tracking-by-detection method, (b) extend and verify object trajectories through single object tracking, and (c) propose a pipeline for efficient semiautomatic annotation of object bounding boxes in videos. We evaluate our approach on the CVL dataset, which focuses on nighttime driving conditions on European countryside roads. We demonstrate the improvements achieved by each processing step, and observe an increase of 23% in recall while precision remains almost constant when compared to the initial tracking-by-detection approach.","PeriodicalId":131088,"journal":{"name":"2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114634990","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

Novel Initial Parameters Computation for EM algorithm-based Univariate Asymmetric Generalized Gaussian Mixture 基于EM算法的单变量非对称广义高斯混合物初始参数计算新方法

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552149

A. Goumeidane, Nafaa Nacereddine

引用次数: 0

HD-RACE: Spray-based Local Tone Mapping Operator HD-RACE:基于喷雾的本地音调映射操作符

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552145

Karlo Koščević, Vedran Stipetić, E. Provenzi, Nikola Banić, M. Subašić, S. Lončarić

引用次数: 1

Mushroom Image Classification with CNNs: A Case-Study of Different Learning Strategies 基于cnn的蘑菇图像分类:不同学习策略的案例研究

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552053

N. Kiss, L. Czúni

{"title":"Mushroom Image Classification with CNNs: A Case-Study of Different Learning Strategies","authors":"N. Kiss, L. Czúni","doi":"10.1109/ISPA52656.2021.9552053","DOIUrl":"https://doi.org/10.1109/ISPA52656.2021.9552053","url":null,"abstract":"Picking mushrooms is traditionally a popular hobby for many people, on the other hand, image based mushroom recognition is a great challenge for machine learning methods due to the large number of species, similarities in appearance, and wide spectrum of environmental effects during imaging. While deep learning convolutional neural networks (CNNs) became monarch in image based recognition, the large number of possible architectures, the alternatives of training, the setting-up of proper data-sets, the settings of hyperparameters are making headaches for the researchers and developers to find optimal solutions for classification problems. In our article we are to solve a mushroom classification task by systematically going through the above key questions. First, we introduce how we created and cleaned a proper data-set for training, then why we selected a specific neural network considering the constraints of limited hardware resources. We go through different alternatives for training such as transfer learning, gradual freezing, changing model size, incremental-size learning, and also applying task specific subnetworks. Performance evaluation is made on our data-set of 106 species, the best approach reaching 92.6% accuracy.","PeriodicalId":131088,"journal":{"name":"2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127988813","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: 3

Zuckerwatte (zcwt): An open-source C++ library for standardizing computation and post-processing of the continuous wavelet transform Zuckerwatte (zcwt):一个开源的c++库，用于标准化连续小波变换的计算和后处理

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552081

Nicolai Spicher, M. Kukuk

{"title":"Zuckerwatte (zcwt): An open-source C++ library for standardizing computation and post-processing of the continuous wavelet transform","authors":"Nicolai Spicher, M. Kukuk","doi":"10.1109/ISPA52656.2021.9552081","DOIUrl":"https://doi.org/10.1109/ISPA52656.2021.9552081","url":null,"abstract":"In this work we introduce the open-source C++ library zcwt - Zuckerwatte (german for cotton candy) for facilitating working with zero-crossings of the continuous wavelet transform. The software library allows for fully automatic i) computation of the continuous wavelet transform with Gaussian wavelets up to order 8, ii) zero-crossing detection in all calculated scales, and iii) concatenation of zero-crossings to form continuous lines across all scales. This allows to compute zero-crossing lines in a standardized and transparent way with well-defined parameters, enabling reproducible research. Furthermore, as an example application demonstrating the use of these lines we provide an implementation of the iv) multi-scale parameter estimation method and apply it to real-world problems. The library is based on the linear algebra software library Armadillo and has, apart from that, only little dependencies and is easily extensible; e.g., we provide a class for easy definition of other wavelets. We provide a CMake file for simple installation across all operating systems. The library is freely available at: https://github.com/nspi/zcwt.","PeriodicalId":131088,"journal":{"name":"2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"241 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133682933","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

Catadioptric Stereo on a Smartphone 智能手机上的反射立体音响

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552146

Kristijan Bartol, David Bojani'c, Tomislav Petkovi'c, Tomislav Pribani'c

引用次数: 0

Compressed Sensing via Collaboratively Learned Dictionaries 基于协作学习字典的压缩感知

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552065

Kai Guo, Xijun Liang, Weizhi Lu

{"title":"Compressed Sensing via Collaboratively Learned Dictionaries","authors":"Kai Guo, Xijun Liang, Weizhi Lu","doi":"10.1109/ISPA52656.2021.9552065","DOIUrl":"https://doi.org/10.1109/ISPA52656.2021.9552065","url":null,"abstract":"In compressed sensing, the recovery error of a high dimensional signal can be approximately modeled by a multivariate Gaussian distribution N (µ, σ2I). The mean vector µ has its zero and nonzero elements correspond respectively to small dense errors caused by system noise, and large sparse errors caused by discarding relatively small coefficients in sparse recovery. To suppress small errors with zero mean, one major solution is to average the recovery results of multiple dictionaries. This will linearly decrease the error's variance σ2, and then enable the error taking zero value with high probability. Unfortunately, the averaging method cannot promise to decrease large errors with nonzero means. Moreover, in practice, large errors of distinct dictionaries tend to occur at the same coordinates with the same value signs, because the dictionaries learned independently tend to converge to the points close to each other and thus yield similar large errors in sparse recovery. This property prevents large errors from being decreased by average. In the paper, we prove that the average performance could be improved, if large errors of distinct dictionaries have disjoint supports. To obtain such dictionaries, we propose a collaborative dictionary learning model, which is implemented with a block coordinate decent method. The resulting dictionaries present desired experimental performance. A full version of the paper is accessible at https://drive.google.com/file/d/1_wy455PuKit1yf6QmXJxt81Y-ZZ5gq0s/view?usp=sharing","PeriodicalId":131088,"journal":{"name":"2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130389036","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

A Survey on Skeleton-Based Activity Recognition using Graph Convolutional Networks (GCN) 基于骨骼的图形卷积网络(GCN)活动识别研究综述

2021 12th International Symposium on Image and Signal Processing and Analysis (ISPA) Pub Date : 2021-09-13 DOI: 10.1109/ISPA52656.2021.9552064

Mesafint Fanuel, Xiaohong Yuan, Hyung Nam Kim, L. Qingge, K. Roy

引用次数: 2