René Grzeszick, Jan Marius Lenk, Fernando Moya Rueda, G. Fink, S. Feldhorst, M. T. Hompel
Although the fourth industrial revolution is already in pro-gress and advances have been made in automating factories, completely automated facilities are still far in the future. Human work is still an important factor in many factories and warehouses, especially in the field of logistics. Manual processes are, therefore, often subject to optimization efforts. In order to aid these optimization efforts, methods like human activity recognition (HAR) became of increasing interest in industrial settings. In this work a novel deep neural network architecture for HAR is introduced. A convolutional neural network (CNN), which employs temporal convolutions, is applied to the sequential data of multiple intertial measurement units (IMUs). The network is designed to separately handle different sensor values and IMUs, joining the information step-by-step within the architecture. An evaluation is performed using data from the order picking process recorded in two different warehouses. The influence of different design choices in the network architecture, as well as pre- and post-processing, will be evaluated. Crucial steps for learning a good classification network for the task of HAR in a complex industrial setting will be shown. Ultimately, it can be shown that traditional approaches based on statistical features as well as recent CNN architectures are outperformed.
{"title":"Deep Neural Network based Human Activity Recognition for the Order Picking Process","authors":"René Grzeszick, Jan Marius Lenk, Fernando Moya Rueda, G. Fink, S. Feldhorst, M. T. Hompel","doi":"10.1145/3134230.3134231","DOIUrl":"https://doi.org/10.1145/3134230.3134231","url":null,"abstract":"Although the fourth industrial revolution is already in pro-gress and advances have been made in automating factories, completely automated facilities are still far in the future. Human work is still an important factor in many factories and warehouses, especially in the field of logistics. Manual processes are, therefore, often subject to optimization efforts. In order to aid these optimization efforts, methods like human activity recognition (HAR) became of increasing interest in industrial settings. In this work a novel deep neural network architecture for HAR is introduced. A convolutional neural network (CNN), which employs temporal convolutions, is applied to the sequential data of multiple intertial measurement units (IMUs). The network is designed to separately handle different sensor values and IMUs, joining the information step-by-step within the architecture. An evaluation is performed using data from the order picking process recorded in two different warehouses. The influence of different design choices in the network architecture, as well as pre- and post-processing, will be evaluated. Crucial steps for learning a good classification network for the task of HAR in a complex industrial setting will be shown. Ultimately, it can be shown that traditional approaches based on statistical features as well as recent CNN architectures are outperformed.","PeriodicalId":209424,"journal":{"name":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114115083","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}
Tracking multiple targets with anonymous sensors (e.g. presence sensors) leads to a combinatorial explosion in the number of possible siuations (hypotheses) that need to be tracked, due to the uncertainty of the association of identities to observed tracks. We propose a novel Bayesian filtering algorithm that can solve this problem by employing a compact state representation. A single lifted state represents a uniform distribution over all possible identity-track associations. The state representation and dynamics is based on Multiset Rewriting Systems and Lifted Probabilistic Inference. We show that Bayesian filtering using this representation is possible without resorting to ground states. This is demonstrated for a person tracking scenario in an office environment where up to seven persons are observed with presence sensors. Our approach naturally allows to simultaneously track persons and estimate their total number. The number of hypotheses is several orders of magnitude smaller than using a ground state representation.
{"title":"Where are my colleagues?: Tracking and Counting Multiple Persons using Lifted Marginal Filtering","authors":"S. Lüdtke, Max Schröder, Frank Krüger, T. Kirste","doi":"10.1145/3134230.3134237","DOIUrl":"https://doi.org/10.1145/3134230.3134237","url":null,"abstract":"Tracking multiple targets with anonymous sensors (e.g. presence sensors) leads to a combinatorial explosion in the number of possible siuations (hypotheses) that need to be tracked, due to the uncertainty of the association of identities to observed tracks. We propose a novel Bayesian filtering algorithm that can solve this problem by employing a compact state representation. A single lifted state represents a uniform distribution over all possible identity-track associations. The state representation and dynamics is based on Multiset Rewriting Systems and Lifted Probabilistic Inference. We show that Bayesian filtering using this representation is possible without resorting to ground states. This is demonstrated for a person tracking scenario in an office environment where up to seven persons are observed with presence sensors. Our approach naturally allows to simultaneously track persons and estimate their total number. The number of hypotheses is several orders of magnitude smaller than using a ground state representation.","PeriodicalId":209424,"journal":{"name":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130677267","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}
Kristof Van Laerhoven, Mario Wenzel, A. Geelen, Christopher Hübel, M. Wolters, A. Hebestreit, L. Andersen, P. Veer, T. Kubiak
Public health trends are currently monitored and diagnosed based on large studies that often rely on pen-and-paper data methods that tend to require a large collection campaign. With the pervasiveness of smart-phones and -watches throughout the general population, we argue in this paper that such devices and their built-in sensors can be used to capture such data more accurately with less of an effort. We present a system that targets a pan-European and harmonised architecture, using smartphones and wrist-worn activity loggers to enable the collection of data to estimate sedentary behavior and physical activity, plus the consumption of sugar-sweetened beverages. We report on a unified pilot study across three countries and four cities (with different languages, locale formats, and data security and privacy laws) in which 83 volunteers were asked to log beverages consumption along with a series of surveys and longitudinal accelerometer data. Our system is evaluated in terms of compliance, obtained data, and first analyses.
{"title":"Experiences from a Wearable-Mobile Acquisition System for Ambulatory Assessment of Diet and Activity","authors":"Kristof Van Laerhoven, Mario Wenzel, A. Geelen, Christopher Hübel, M. Wolters, A. Hebestreit, L. Andersen, P. Veer, T. Kubiak","doi":"10.1145/3134230.3134239","DOIUrl":"https://doi.org/10.1145/3134230.3134239","url":null,"abstract":"Public health trends are currently monitored and diagnosed based on large studies that often rely on pen-and-paper data methods that tend to require a large collection campaign. With the pervasiveness of smart-phones and -watches throughout the general population, we argue in this paper that such devices and their built-in sensors can be used to capture such data more accurately with less of an effort. We present a system that targets a pan-European and harmonised architecture, using smartphones and wrist-worn activity loggers to enable the collection of data to estimate sedentary behavior and physical activity, plus the consumption of sugar-sweetened beverages. We report on a unified pilot study across three countries and four cities (with different languages, locale formats, and data security and privacy laws) in which 83 volunteers were asked to log beverages consumption along with a series of surveys and longitudinal accelerometer data. Our system is evaluated in terms of compliance, obtained data, and first analyses.","PeriodicalId":209424,"journal":{"name":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127216047","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}
David Nieves, C. Ferri, J. Hernández-Orallo, Carlos Monserrat Aranda
We present an event detection system in a laparoscopic surgery domain, as part of a more ambitious supervision by observation project. The system, which only requires the incorporation of two cameras in a laparoscopic training box, integrates several computer vision and machine learning techniques to detect the states and movements of the elements involved in the exercise. We compare the states detected by the system with the hand-labelled ground truth, using an exercise of the domain as example. We show that the system is able to detect the events accurately.
{"title":"Low-level Event Detection System for Minimally-Invasive Surgery Training","authors":"David Nieves, C. Ferri, J. Hernández-Orallo, Carlos Monserrat Aranda","doi":"10.1145/3134230.3134241","DOIUrl":"https://doi.org/10.1145/3134230.3134241","url":null,"abstract":"We present an event detection system in a laparoscopic surgery domain, as part of a more ambitious supervision by observation project. The system, which only requires the incorporation of two cameras in a laparoscopic training box, integrates several computer vision and machine learning techniques to detect the states and movements of the elements involved in the exercise. We compare the states detected by the system with the hand-labelled ground truth, using an exercise of the domain as example. We show that the system is able to detect the events accurately.","PeriodicalId":209424,"journal":{"name":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130216283","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}
{"title":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","authors":"","doi":"10.1145/3134230","DOIUrl":"https://doi.org/10.1145/3134230","url":null,"abstract":"","PeriodicalId":209424,"journal":{"name":"Proceedings of the 4th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124222254","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：