Smooth Automatic Stopping for Ultra-Compact Vehicles

Premachandra, Chinthaka; Gohara, Ryo; Ninomiya, T.; Kato, K.

doi:10.1109/tiv.2019.2938098

Cited by 19 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can also try to implement this architecture in another field or train using different datasets to find out its capability as well as implementing it in mobile application. Furthermore, some robotic applications have been conducted using light-weight hardware [37][38][39][40][41][42]. In the future, we plan to apply our proposal in such kind of object detection applications.…”

Section: Discussionmentioning

confidence: 99%

Small and Slim Deep Convolutional Neural Network for Mobile Device

2020

Self Cite

View full text Add to dashboard Cite

Recent development of deep convolutional neural networks (DCNN) devoted in creating a slim model for devices with lower specification such as embedded, mobile hardware, or microcomputer. Slim model can be achieved by minimizing computational complexity which theoretically will make processing time faster. Therefore, our focus is to build an architecture with minimum floating-point operation per second (FLOPs). In this work, we propose a small and slim architecture which later will be compared to state-of-the-art models. This architecture will be implemented into two models which are CustomNet and CustomNet2. Each of these models implements 3 convolutional blocks which reduce the computational complexity while maintains its accuracy and able to compete with state-of-the-art DCNN models. These models will be trained using ImageNet, CIFAR 10, CIFAR 100 and other datasets. The result will be compared based on accuracy, complexity, size, processing time, and trainable parameter. From the result, we found that one of our models which is CustomNet2, is better than MobileNet, MobileNet-v2, DenseNet, NASNetMobile in accuracy, trainable parameter, and complexity. For future implementation, this architecture can be adapted using region based DCNN for multiple object detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Small and Slim Deep Convolutional Neural Network for Mobile Device

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…A Fuzzy Logic System (FLS) can map the input space with the output space of a control problem based on a set of linguistic rules [ 48 , 49 ]. Fuzzy logic can be considered as a reliable modeling method that can model any complex system or process without knowing the exact underlying dynamics [ 50 , 51 , 52 ]. In the case of wall-following behavior, the exact dynamics of the robot and an environment is not certain.…”

Section: Fuzzy Logic System For Wall-following Behaviormentioning

confidence: 99%

Wall-Following Behavior for a Disinfection Robot Using Type 1 and Type 2 Fuzzy Logic Systems

Muthugala

Samarakoon

Rayguru

et al. 2020

Sensors

View full text Add to dashboard Cite

Infectious diseases are caused by pathogenic microorganisms, whose transmission can lead to global pandemics like COVID-19. Contact with contaminated surfaces or objects is one of the major channels of spreading infectious diseases among the community. Therefore, the typical contaminable surfaces, such as walls and handrails, should often be cleaned using disinfectants. Nevertheless, safety and efficiency are the major concerns of the utilization of human labor in this process. Thereby, attention has drifted toward developing robotic solutions for the disinfection of contaminable surfaces. A robot intended for disinfecting walls should be capable of following the wall concerned, while maintaining a given distance, to be effective. The ability to operate in an unknown environment while coping with uncertainties is crucial for a wall disinfection robot intended for deployment in public spaces. Therefore, this paper contributes to the state-of-the-art by proposing a novel method of establishing the wall-following behavior for a wall disinfection robot using fuzzy logic. A non-singleton Type 1 Fuzzy Logic System (T1-FLS) and a non-singleton Interval Type 2 Fuzzy Logic System (IT2-FLS) are developed in this regard. The wall-following behavior of the two fuzzy systems was evaluated through simulations by considering heterogeneous wall arrangements. The simulation results validate the real-world applicability of the proposed FLSs for establishing the wall-following behavior for a wall disinfection robot. Furthermore, the statistical outcomes show that the IT2-FLS has significantly superior performance than the T1-FLS in this application.

show abstract

“…Frame and background subtraction can be used to detect moving objects in images [21][22][23][24][25][26][27][28][29][30][31][32]. In frame subtraction, moving objects are detected by calculating the image subtraction between two or a few consecutive frames [21,23,28].…”

Section: A Moving Object Candidate Extraction By Gaussian Mixture Momentioning

confidence: 99%

Detection and Tracking of Moving Objects at Road Intersections Using a 360-Degree Camera for Driver Assistance and Automated Driving

2020

Self Cite

View full text Add to dashboard Cite

Many complicated road intersections are seen while driving. In some, blind spots make it difficult for drivers or automated vehicles to discern moving objects coming from certain directions, possibly confusing drivers or autonomous vehicles wishing to cross or to turn at the intersection. To address this problem, we investigate detection and tracking of all moving objects at an intersection using a single 360degree-view camera (3DVC). Through experiments, we develop methods allowing a 3DVC to capture the entirety of a four-way intersection when installed at one corner. This paper also presents image processing algorithms for detecting and tracking moving objects at intersections by processing images from the installed 3DVC. Experiments under varied conditions demonstrate that the proposed detection algorithm has a very high detection rate. We also confirm the tracking ability for moving objects detected using the proposed algorithm. INDEX TERMS 360-degree camera (Omnidirectional camera), driver assistance, autonomous driving, moving object detection and tracking, image conversion.

show abstract

Smooth Automatic Stopping for Ultra-Compact Vehicles

Cited by 19 publications

References 27 publications

Small and Slim Deep Convolutional Neural Network for Mobile Device

Small and Slim Deep Convolutional Neural Network for Mobile Device

Wall-Following Behavior for a Disinfection Robot Using Type 1 and Type 2 Fuzzy Logic Systems

Detection and Tracking of Moving Objects at Road Intersections Using a 360-Degree Camera for Driver Assistance and Automated Driving

Contact Info

Product

Resources

About