Implementation of Automated Annotation through Mask RCNN Object Detection model in CVAT using AWS EC2 Instance

Guillermo, Marielet; Billones, Robert Kerwin C.; Vicerra, Ryan Rhay P.; Sybingco, Edwin; Dadios, Elmer P.; Fillone, Alexis M.

doi:10.1109/tencon50793.2020.9293906

Cited by 26 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the research of lightweight object detection network, previous works have achieved some remarkable success. With the rapid development of the Internet of Things (IoT), some efforts [49][50][51] have been made to reduce the need for storage space and computational complexity on edge devices by using the IoT and cloud-based services. These existing efforts send algorithms and databases to AWS services hosted in the cloud for saving storage space on the edge devices.…”

Section: Discussionmentioning

confidence: 99%

SSD7-FFAM: A Real-Time Object Detection Network Friendly to Embedded Devices from Scratch

Lin

2021

Applied Sciences

View full text Add to dashboard Cite

The high requirements for computing and memory are the biggest challenges in deploying existing object detection networks to embedded devices. Living lightweight object detectors directly use lightweight neural network architectures such as MobileNet or ShuffleNet pre-trained on large-scale classification datasets, which results in poor network structure flexibility and is not suitable for some specific scenarios. In this paper, we propose a lightweight object detection network Single-Shot MultiBox Detector (SSD)7-Feature Fusion and Attention Mechanism (FFAM), which saves storage space and reduces the amount of calculation by reducing the number of convolutional layers. We offer a novel Feature Fusion and Attention Mechanism (FFAM) method to improve detection accuracy. Firstly, the FFAM method fuses high-level semantic information-rich feature maps with low-level feature maps to improve small objects’ detection accuracy. The lightweight attention mechanism cascaded by channels and spatial attention modules is employed to enhance the target’s contextual information and guide the network to focus on its easy-to-recognize features. The SSD7-FFAM achieves 83.7% mean Average Precision (mAP), 1.66 MB parameters, and 0.033 s average running time on the NWPU VHR-10 dataset. The results indicate that the proposed SSD7-FFAM is more suitable for deployment to embedded devices for real-time object detection.

show abstract

Section: Discussionmentioning

confidence: 99%

SSD7-FFAM: A Real-Time Object Detection Network Friendly to Embedded Devices from Scratch

Lin

2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…We used CVAT [12] to mark the spinal canal, intervertebral disc, and facet joint in the spinal MRI images; the marking format was a segmentation mask [13]. A marked segmentation mask is used as the ground truth, which is required for the training and veri cation of the spinal canal segmentation model.…”

Section: Data Annotation By Cvatmentioning

confidence: 99%

Using deep learning to identify the stenosis of the vertebral foramen and intervertebral canal accurately with the index IoU

Yeh

Hsu

et al. 2023

Preprint

View full text Add to dashboard Cite

Artificial intelligence is a computer technology that has attracted considerable attention in recent years. As computer equipment has become increasingly advanced, deep learning in the field of artificial intelligence has made breakthroughs. In recent years, the use of deep learning in the medical field has contributed to many issues of efficiency and accuracy. Regardless of the excellent results in radiology, pathology, endoscopy, ultrasound, and biochemical examination, in this study, we used deep learning as a tool to identify spinal canals and spinal foramen stenosis. Based on previous studies, new techniques, such as erosion and expansion, were added to make the results more accurate, and provide area, IoU and other indicators for evaluation. This paper not only applies the latest computer science and information engineering technology--deep learning to medicine, but also uses a breakthrough network model to improve the recognition effect.Use quantitative indicators to make results more reliable. In this study, we compared two network architecture, Resnet50 and VGG16, to identify the spinal canal and intervertebral foramen. Resnet50 had quite good results in IoU, which were 77.4% and 80.9% in spinal canal and intervertebral foramen, respectively.

show abstract

“…Deep learning is a subset of machine learning that uses three or more layers of artificial neural networks to study processes similar to those of the human brain. These neural networks attempt to emulate human brain function by allowing it to "learn" from vast amounts of data, yet they are incredibly inadequate to do so (Guillermo et al, 2020). Although a single-layer neural network may produce approximate predictions, extra layers can assist optimize and improve accuracy.…”

Section: Deep Learningmentioning

confidence: 99%

Prototype Model Development using Python for Detection of Transparent Face Mask and Identification of the State of Usage of Transparent Face Mask

De Jesus,

De Los Santos,

Escoto

et al. 2023

IJCSR

View full text Add to dashboard Cite

Purpose -The right use of face masks is one of the health practices that have been implemented in response to the COVID-19 pandemic danger. The automated monitoring of face mask usage is aided using face mask detection models.Methodology -A prototype model that can detect and identify the state of usage of a transparent face mask was developed using the object detection model Resnet50. It was trained with datasets containing people wearing proper and improper way of transparent 1907 Practical Implications -The prototype model promotes health security and public safety and adheres to standard data privacy protections in the usage of a transparent face mask.

show abstract

Implementation of Automated Annotation through Mask RCNN Object Detection model in CVAT using AWS EC2 Instance

Cited by 26 publications

References 28 publications

SSD7-FFAM: A Real-Time Object Detection Network Friendly to Embedded Devices from Scratch

SSD7-FFAM: A Real-Time Object Detection Network Friendly to Embedded Devices from Scratch

Using deep learning to identify the stenosis of the vertebral foramen and intervertebral canal accurately with the index IoU

Prototype Model Development using Python for Detection of Transparent Face Mask and Identification of the State of Usage of Transparent Face Mask

Contact Info

Product

Resources

About