Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Transformers in Distribution System01:27

Transformers in Distribution System

Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
Transformers with Off-Nominal Turns Ratios01:25

Transformers with Off-Nominal Turns Ratios

In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the rated...
Types Of Transformers01:16

Types Of Transformers

Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Involvement of immunomodulators in the development of cancer vaccines.

Biochimica et biophysica acta. Molecular basis of disease·2026
Same author

'Alone on our NF1 island': a patient-led mixed-method survey study to understand the care pathway for neurofibromatosis type 1 (NF1) patients in the UK.

BMJ open quality·2025
Same author

Deep Learning-Derived Myocardial Strain.

JACC. Cardiovascular imaging·2024
Same author

Interpretable deep learning prediction of 3d assessment of cardiac function.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2021
Same author

Systematic Quantification of Sources of Variation in Ejection Fraction Calculation Using Deep Learning.

JACC. Cardiovascular imaging·2021

Related Experiment Videos

Mobile real-time detection transformer for computationally constrained devices.

Arjun Prashanth1, Andhavarapu Balu1, Ishan Jain1

  • 1School of Computer Science and Engineering (SCOPE), VIT University, 600127, Chennai campus, India.

Scientific Reports
|July 13, 2026
PubMed
Summary

We introduce Mobile RT-DETR (MRTDETR), a lightweight object detection model that achieves high accuracy and speed by utilizing a MobileNetv3 backbone. MRTDETR offers a superior trade-off between accuracy and computational cost, making it ideal for edge devices.

Keywords:
Deep LearningMachine LearningObject DetectionTransformers

Related Experiment Videos

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Real Time Detection Transformer (RT-DETR) represents the state-of-the-art in object detection, outperforming YOLOv8 in accuracy and speed.
  • Existing lightweight models often compromise accuracy for efficiency, limiting their applicability in resource-constrained environments.

Purpose of the Study:

  • To develop a compact and high-speed object detection model, Mobile RT-DETR (MRTDETR), based on the RT-DETR architecture.
  • To optimize the model for edge deployment by evaluating its performance on a Raspberry Pi 5.

Main Methods:

  • Utilized a lightweight MobileNetv3 backbone within the RT-DETR framework.
  • Integrated specific layers (7, 13, and 15) of the MobileNetv3 backbone as encoder inputs.
  • Explored and subsequently excluded separable self-attention mechanisms.

Main Results:

  • Achieved 44.6% mAP (batch size 4, RTX 3050) and 43.1% mAP (batch size 64, H100 PCIe), surpassing FasterRCNN, MobileFormer, and MobileViT.
  • Demonstrated competitive performance with YOLOv8 and YOLOv9 detectors at 15.23 GFLOPs, with significantly fewer FLOPs.
  • On Raspberry Pi 5, MRTDETR showed an average inference time of 1,967.4 ms, 435.86 MB VmRSS, 1,350.27 MB VmSize, and an ONNX file size of 43.1 MB.

Conclusions:

  • MRTDETR offers an optimal balance between accuracy and computational efficiency (FLOPs) compared to existing models.
  • The model's performance on edge devices, validated through real-world profiling, makes it a strong candidate for practical, resource-limited applications.