Automatic recognition of object use based on wireless motion sensors

Bosch, Stephan; Marin-Perianu, Raluca; Havinga, Paul J.M.; Horst, Arie; Marin-Perianu, Mihai; Vasilescu, Andrei

doi:10.1109/iswc.2010.5665858

Cited by 20 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Human Activity Recognition system has many applications due to the ability to understand the complex scenes from the surveillance video, for example surveillance system deployed at the different public places like railway stations, airport, Banks, they all require recognition of suspicious or abnormal activities rather than normal activity [1][2][3]. For instance, railway surveillance system must be capable of recognizing some abnormal activities like "intentionally dropping the bag at railway station", "push the security personals", or "putting the bag in the trash bin" [4].…”

Section: Introductionmentioning

confidence: 99%

Hybrid HAR-CNN Model: A Hybrid Convolutional Neural Network Model for Predicting and Recognizing the Human Activity Recognition

Vishwakarma,

Kundu

et al. 2024

JMC

View full text Add to dashboard Cite

Human activity recognition (HAR) is an active research area in computer vision from past several years and research is still continuing in this field due to the unavailability of perfect recognition system. The human activity recognition system it covers e-health, patient monitoring, assistive daily living activities, video surveillance, security and behaviour analysis, and sports analysis. Many researchers have suggested techniques that use visual perception to detect human activities. Researchers will need to address problems including light variations in human activity detection, interclass similarity between scenes, the surroundings and recording setting, and temporal variation in order to construct an efficient vision-based human activity recognition system. However, a significant drawback of many deep learning models is their inability to achieve satisfactory results in real-world scenarios due to the conflicts mentioned above. To address this challenge, we developed a hybrid HAR-CNN classifier aimed at enhancing the learning outcomes of Deep CNNs by combining two models: Improved CNN and VGG-19. Using the KTH dataset, we collected 6,000 images for training, validation, and testing of our proposed technique. Our research findings indicate that the Hybrid HAR-CNN model, which combines Improved CNN with VGG-19 Net, outperforms individual deep learning models such as Improved CNN and VGG-19 Net.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid HAR-CNN Model: A Hybrid Convolutional Neural Network Model for Predicting and Recognizing the Human Activity Recognition

Vishwakarma,

Kundu

et al. 2024

JMC

View full text Add to dashboard Cite

show abstract

“…If worn by the user and attached to objects, such sensors can detect that an object is being used by a particular user by correlating their movements. This approach has two important advantages over the previous alternatives: (1) it gives a direct measure based on the actual object use (and not based on proximity to the object, for example) and (2) it provides much more and finer-grained sensor This work is an extension of earlier work presented at the fourteenth annual IEEE International Symposium on Wearable Computers (ISWC 2010) [5].…”

Section: Introductionmentioning

confidence: 99%

A study on automatic recognition of object use exploiting motion correlation of wireless sensors

Bosch

Marin-Perianu

Havinga

et al. 2011

Pers Ubiquit Comput

Self Cite

View full text Add to dashboard Cite

An essential component in the ubiquitous computing vision is the ability of detecting with which objects the user is interacting during his or her activities. We explore in this paper a solution to this problem based on wireless motion and orientation sensors (accelerometer and compass) worn by the user and attached to objects. We evaluate the performance in realistic conditions, characterized by limited hardware resources, measurement noise due to motion artifacts and unreliable wireless communication. We describe the complete solution, from the theoretical design, going through simulation and tuning, to the full implementation and testing on wireless sensor nodes. The implementation on sensor nodes is lightweight, with low communication bandwidth and processing needs. Compared to existing work, our approach achieves better performance (higher detection accuracy and faster response times), while being much more computationally efficient. The potential of the concept is further illustrated by means of an interactive multi-user game. We also provide a thorough discussion of the advantages, limitations and trade-offs of the proposed solution.

show abstract

“…Monitoring of vital signs, tracking, and data collection have been the main objectives of these sensor networks. Interaction with sensor-enabled objects [2], such as a dumbbell or ball, is an interesting upcoming usage area. BSNs are small-scale, use different types of sensors, and are usually limited to single-hop wireless communication.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Mobility and Sharing of WSNs By IP Applications

Bijwaard

Havinga

Eertink

2011

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Movement of wireless sensor and actuator networks, and of nodes between WSANs are becoming more commonplace. However, enabling remote usage of sensory data in multiple applications, remote configuration, and actuation is still a big challenge. The purpose of this paper is to analyse and describe which mobility support can best be used in different scenarios, and how shared usage of mobile WSANs by multiple IP applications can best be scaled up. This paper describes logistic and person monitoring scenarios, where different types of movements take place. These mobility types and their implications are categorized and analysed. Different degrees of support for these mobility types are analysed in the context of the mobility scenarios. Additionally, different schemes are analysed for shared use of mobile WSANs by multiple applications. In conclusion, guidelines are provided for dealing with mobile and overlapping WSANs and the most promising scheme for shared use of mobile WSANs by IP applications.

show abstract

Automatic recognition of object use based on wireless motion sensors

Cited by 20 publications

References 11 publications

Hybrid HAR-CNN Model: A Hybrid Convolutional Neural Network Model for Predicting and Recognizing the Human Activity Recognition

Hybrid HAR-CNN Model: A Hybrid Convolutional Neural Network Model for Predicting and Recognizing the Human Activity Recognition

A study on automatic recognition of object use exploiting motion correlation of wireless sensors

Analysis of Mobility and Sharing of WSNs By IP Applications

Contact Info

Product

Resources

About