Study of Marker Detection Performance on Deep Learning via Distortion and Rotation Augmentation of Training Data on Underwater Sonar Image

Lee, Eon-Ho; Lee, Yeongjun; Choi, Jinwoo; Lee, Se-Jin

doi:10.7746/jkros.2019.14.1.014

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The practical process of remote control kill‐free is shown in Figure 2 [22]. Lee and others detected the INVITE flooding attack by detecting the {INVITE,200ok} protocol attribute tuple [23]. Chang et al.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

A study on detection and defence of malicious code under network security over biomedical devices

Liu

Neware

Bhatt

et al. 2022

The Journal of Engineering

View full text Add to dashboard Cite

With the proliferation of massive varieties and unknown malicious viruses, it is difficult to achieve effective and timely defence by anti‐virus technology with virus signature matching as the core. Hence, the research of malicious code detection and defence is investigated. Firstly, it introduces the defence technology and detection technology. The simulation results show that the default infection probability of the simulation program is 15.1%. The default detection probability is 60.1%, the default number of nodes is 1000, the default time step is 1000 ms, and the default initial infected node is only node 0, that is, only the malicious code on node 0 is activated. After start‐up, the whole P2P starts to run, and the number of infected nodes increases. Finally, all nodes are infected. The infection speed becomes faster and faster. When the number of infected nodes reaches about half, the infection speed begins to slow down.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…[22]. Lee and others detected the INVITE flooding attack by detecting the {INVITE,200ok} protocol attribute tuple[23]. Chang et al proposed a method that can detect VoIP flooding attacks under multi-level mixed traffic, and the Hellinger Distance is used as a measure[24].…”

mentioning

confidence: 99%

A study on detection and defence of malicious code under network security over biomedical devices

Liu

Neware

Bhatt

et al. 2022

The Journal of Engineering

View full text Add to dashboard Cite

show abstract

“…To solve this problem, research is being actively conducted on estimating the position of a camera using artificial markers such as augmented reality (AR) or quick response (QR) markers [ 14 , 15 , 16 , 17 , 18 ]. Even though these methods use a low central processing unit (CPU), relatively fast and accurate position recognition is possible because artificial markers are recognized through their patterns even in a monotonous environment [ 14 , 19 , 20 , 21 ]. In addition, it is possible to evaluate the exact size of a marker by recognizing the four corners of the marker.…”

Section: Introductionmentioning

confidence: 99%

Marker-Based Method for Recognition of Camera Position for Mobile Robots

Gwak

Yang

Park

et al. 2021

Sensors

View full text Add to dashboard Cite

Position recognition is one of the core technologies for driving a robot because of differences in environment and rapidly changing situations. This study proposes a strategy for estimating the position of a camera mounted on a mobile robot. The proposed strategy comprises three methods. The first is to directly acquire information (e.g., identification (ID), marker size and marker type) to recognize the position of the camera relative to the marker. The advantage of this marker system is that a combination of markers of different sizes or having different information may be used without having to update the internal parameters of the robot system even if the user frequently changes or adds to the marker’s identification information. In the second, two novel markers are proposed to consider the real environment in which real robots are applied: a nested marker and a hierarchical marker. These markers are proposed to improve the ability of the camera to recognize markers while the camera is moving on the mobile robot. The nested marker is effective for robots like drones, which land and take off vertically with respect to the ground. The hierarchical marker is suitable for robots that move horizontally with respect to the ground such as wheeled mobile robots. The third method is the calculation of the position of an added or moved marker based on a reference marker. This method automatically updates the positions of markers after considering the change in the driving area of the mobile robot. Finally, the proposed methods were validated through experiments.

show abstract

Study on Underwater Object Tracking Based on Real-Time Recurrent Regression Networks Using Multi-beam Sonar Images

Lee¹,

Lee²,

Choi³

et al. 2020

J. Korea Robot. Soc.

View full text Add to dashboard Cite

Study of Marker Detection Performance on Deep Learning via Distortion and Rotation Augmentation of Training Data on Underwater Sonar Image

Cited by 4 publications

References 9 publications

A study on detection and defence of malicious code under network security over biomedical devices

A study on detection and defence of malicious code under network security over biomedical devices

Marker-Based Method for Recognition of Camera Position for Mobile Robots

Study on Underwater Object Tracking Based on Real-Time Recurrent Regression Networks Using Multi-beam Sonar Images

Contact Info

Product

Resources

About