Proceedings of the 2022 5th International Conference on Machine Vision and Applications最新文献

A Compact Tri-Modal Camera Unit for RGBDT Vision 一种用于RGBDT视觉的紧凑型三模态相机单元

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523116

Julian Strohmayer, M. Kampel

{"title":"A Compact Tri-Modal Camera Unit for RGBDT Vision","authors":"Julian Strohmayer, M. Kampel","doi":"10.1145/3523111.3523116","DOIUrl":"https://doi.org/10.1145/3523111.3523116","url":null,"abstract":"The combination of RGBD and thermal cameras in multi-modal person-centric vision applications has great potential. As a complementary modality, thermal cameras can compensate for weaknesses such as the inability to operate in absolute darkness of conventional RGB cameras or the range limitations associated with consumer depth cameras, resulting in a more robust computer vision system. In addition, the high contrast between persons and their surroundings in thermal images can ease fundamental detection and segmentation tasks. Unfortunately, the market supply of low-cost consumer RGBDT vision systems is non-existent at the moment, which slows down progress in the field of person-centric vision. We address this problem by proposing a Compact Tri-modal CAmera uniT (CTCAT) for RGBDT vision, which can be manufactured from off-the-shelf components and 3D printed parts. CTCAT features a 1280 × 720 RGB camera, a 640 × 480 structured light depth camera with an operating range of 0.6 − 8m, and a 160 × 120 uncooled radiometric thermal camera. RGB, depth, and thermal images can be captured simultaneously at frame rates up to 9 fps. In this work, we describe the components, fabrication, and calibration of CTCAT. In addition, a new multi-modal calibration target suitable for the geometric calibration of RGB, depth, and thermal cameras is presented, which offers advantages over the state of the art in terms of contrast and practicality. Moreover, radiometric calibration of CTCAT is performed to evaluate the applicability to person-centric vision applications requiring radiometry.","PeriodicalId":185161,"journal":{"name":"Proceedings of the 2022 5th International Conference on Machine Vision and Applications","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124701459","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

Stock Volatility Forecast Base on Comparative Learning and Autoencoder Framework 基于比较学习和自编码器框架的股票波动率预测

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523126

Yuxiao Du, Qinyu Li, Zeyu Zhang, Yuxin Liu

引用次数: 1

Transfer Learning based Precise Pose Estimation with Insufficient Data 数据不足情况下基于迁移学习的精确姿态估计

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523118

Wonje Choi, Honguk Woo

引用次数: 0

The Study of Emotional Brain to Detect Emotions Using Brain EEG Signals and Improving Accuracy of Emotion Detection System Using Feature Selection Techniques 利用脑电信号进行情绪脑检测及特征选择技术提高情绪检测系统准确性的研究

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523115

N. Kimmatkar, V. Babu

{"title":"The Study of Emotional Brain to Detect Emotions Using Brain EEG Signals and Improving Accuracy of Emotion Detection System Using Feature Selection Techniques","authors":"N. Kimmatkar, V. Babu","doi":"10.1145/3523111.3523115","DOIUrl":"https://doi.org/10.1145/3523111.3523115","url":null,"abstract":"Now a days Emotion detection using brain EEG signal is becoming interest area of many researchers because of it's tremendous application in healthcare and BCI field. Database acquisition, pre-processing, feature extraction and classification are the main stages in this process. In this research study first existing database of brain EEG signal are studied. Most of the researchers used DEAP database for emotion classification. DEAP database is especially made for music recommendation system. Because of the non-linear and non- stationary nature and poor spatial resolution of Brain EEG signals, researchers faced challenges in each phase of emotion detection process. It is found that the classification accuracy is very low. It becomes necessary to study emotional brain and according to that select electrodes for emotion detection to improve classification accuracy. In this research study self-created dataset is used. Two way approach is used for feature selection to improve accuracy. In the first approach least correlated features are omitted from feature set. and in the second approach RFE recursive feature elimination technique is used for feature ranking. The features ranked high are considered in feature set. It is found that classification accuracy is improved using these techniques.","PeriodicalId":185161,"journal":{"name":"Proceedings of the 2022 5th International Conference on Machine Vision and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129097690","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

Simultaneous Integration of Multimodal Interfaces for Generating Structured and Reliable Robotic Task Configurations 同时集成多模态接口生成结构化和可靠的机器人任务配置

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523120

S. K. Paul, P. Hoseini, Arjun Vettath Gopinath, M. Nicolescu, M. Nicolescu

{"title":"Simultaneous Integration of Multimodal Interfaces for Generating Structured and Reliable Robotic Task Configurations","authors":"S. K. Paul, P. Hoseini, Arjun Vettath Gopinath, M. Nicolescu, M. Nicolescu","doi":"10.1145/3523111.3523120","DOIUrl":"https://doi.org/10.1145/3523111.3523120","url":null,"abstract":"This paper presents a framework that simultaneously integrates multiple input interfaces and extracts task parameters suitable for task execution in a human-robot collaborative environment. We used pointing gestures and natural language instruction as inputs as they provide the most natural interaction interfaces for humans. In the proposed method, the pointing gesture type and the pointing direction are estimated from RGB images, and the object being pointed at is inferred from the prior gesture information and the objects detected in the scene. Subsequently, the verbal command is parsed to extract task action, the object of interest along with its attributes and position in the 2D image frame. This extracted information from gesture recognition and verbal command is used to form task configurations for the desired human-robot collaborative tasks as well as to help resolve any uncertain or missing task parameters. The proposed framework shows very promising results in identifying the relevant task parameters for the intended robotic tasks in different real-world interaction scenarios.","PeriodicalId":185161,"journal":{"name":"Proceedings of the 2022 5th International Conference on Machine Vision and Applications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128480587","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

Towards Face Representation Learning Conditioned on the Soft Biometrics 基于软生物特征的人脸表征学习研究

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523112

JongWon Hwang, L. Tiong, A. Teoh

{"title":"Towards Face Representation Learning Conditioned on the Soft Biometrics","authors":"JongWon Hwang, L. Tiong, A. Teoh","doi":"10.1145/3523111.3523112","DOIUrl":"https://doi.org/10.1145/3523111.3523112","url":null,"abstract":"Abstract: In this paper, we present a method to leverage soft biometric as a means of conditioning biometrics for better face representation learning. By conditioning, we meant the soft biometric trait (age, gender, etc.) is used as an auxiliary biometric for training along with face modality while it is absent during the inference stage. We propose a two-stream deep neural network consisting of a multilayer perceptron network (MLP) and a convolutional neural network (CNN), which can learn a feature representation from soft biometric vectors and face images, respectively. The two-stream network can be optimized simultaneously and the information can be exploited from both biometrics. The learned conditioning soft biometric representation from the MLP serves as a center prototype of the feature learned from the face network, which is beneficial to contract the intra-class variation of the face feature representation. Due to the lacking of the face dataset that comes along with soft biometrics, we construct a database for evaluation purposes. Extensive experiments are performed on two face datasets that equip with soft biometrics and the results show the superiority of our method compared to the face modality alone.","PeriodicalId":185161,"journal":{"name":"Proceedings of the 2022 5th International Conference on Machine Vision and Applications","volume":"349 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134074409","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

Analysis and Example Implementation of Data Visualization Technology 数据可视化技术的分析与实例实现

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523119

Xianyu Meng, Liangli Ma, Yingxue Zhou

引用次数: 0

Depth and Thermal Images in Face Detection - A Detailed Comparison Between Image Modalities 深度和热图像在人脸检测-图像模式之间的详细比较

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523114

Wiktor Mucha, M. Kampel

{"title":"Depth and Thermal Images in Face Detection - A Detailed Comparison Between Image Modalities","authors":"Wiktor Mucha, M. Kampel","doi":"10.1145/3523111.3523114","DOIUrl":"https://doi.org/10.1145/3523111.3523114","url":null,"abstract":"Face detection is a well-known issue in image processing, and numerous studies are present in this field. A prominent part of the work is devoted to RGB images, leaving depth and thermal data with less interest. However, in some conditions like low-light areas where face detection is needed, non-RGB sensors might perform better. Also, mounting an additional RGB camera could be challenging or not possible, considering privacy concerns. In this work, current deep learning methodologies are employed to train depth and thermal detection models. The training is done using combined publicly available data that is processed by us for this purpose in order to create necessary annotations for a learning process. The resulting models are validated on a new trimodal dataset collected for this experiments purpose. It contains images captured with RGB, depth, and thermal sensors. Various scenes with single and multiple faces appearances can be found. The results show that non-RGB solutions can be applied in practice with highly robust accuracy and their efficiency is close to RGB detectors. However, their performance depends on the environment and that circumstances are described later in this article.","PeriodicalId":185161,"journal":{"name":"Proceedings of the 2022 5th International Conference on Machine Vision and Applications","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133641162","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

Ghosting Effect Removal for Multi-Frame Super-Resolution on CCTV Videos with Moving Objects 多帧超分辨率CCTV移动对象视频重影效果去除

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523117

Jarrett Ethan Singian, Jade Nicole Tan, Martin Angelo Tierro, Neil Patrick Del Gallego, J. Ilao, Arren Matthew C. Antioquia

引用次数: 0

Propensity Score Matching on Discrete Treatment: Beijing Pm2.5 Case Study 离散处理的倾向得分匹配:以北京Pm2.5为例

Proceedings of the 2022 5th International Conference on Machine Vision and Applications Pub Date : 2022-02-18 DOI: 10.1145/3523111.3523125

J. Hou, Shaofei Shen, Jing Han, Siqi Xu, Yijing Liu

引用次数: 0