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

Reducing Line Loss01:18

Reducing Line Loss

174
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
174
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.6K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.6K
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

7.4K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.4K
Line Loss01:10

Line Loss

273
The different configurations of source-load connections include wye (star) and delta connections. The relationship between line and phase voltages and currents varies depending on the configuration. When the source is supplying power, it is transmitted through the wires to the load, and during this transmission, some power is absorbed by the wires, leading to line loss.
Line loss impacts power delivery efficiency in a balanced three-phase circuit. The symmetry in such a circuit simplifies the...
273
Margin of Error01:27

Margin of Error

4.4K
The margin of error is also called the maximum error of an estimate. The margin of error is the maximum possible or expected difference between the observed sample parameter value and the actual population parameter value. For proportion, it is the maximum difference between the value of sample proportion obtained from the data and the true value of population proportion. As the true value of the population parameter is not known, the margin of error is calculated using the sample statistic.
4.4K
Distance Corrections01:15

Distance Corrections

51
To achieve precise distance measurements, especially in surveying and construction, certain corrections must be applied to account for potential sources of error like the standardization errors, temperature variations, and slope adjustments.Standardization error emerges when measurement equipment undergoes changes, such as wear, repairs, or weather impacts. To address this, surveyors compare the equipment’s readings to a standard. This process identifies any deviation that might lead to...
51

You might also read

Related Articles

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

Sort by
Same author

A Review of Embedded Artificial Intelligence Research (2023-2026): Technological Advancements, Representative Advances, and Future Prospects.

Micromachines·2026
Same author

An Adaptive Virtual Impedance Method for Grid-Connected Current Quality Improvement of a Single-Phase Virtual Synchronous Generator under Distorted Grid Voltage.

Sensors (Basel, Switzerland)·2023
Same author

Accurate Active and Reactive Power Sharing Based on a Modified Droop Control Method for Islanded Microgrids.

Sensors (Basel, Switzerland)·2023
Same author

A Review of Artificial Intelligence in Embedded Systems.

Micromachines·2023
Same author

A New Gain-Phase Error Pre-Calibration Method for Uniform Linear Arrays.

Sensors (Basel, Switzerland)·2023
Same author

Detection of Missing Insulator Caps Based on Machine Learning and Morphological Detection.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jul 23, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.7K

Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression.

Delong Cai1,2, Zhaoyun Zhang1, Zhi Zhang1

  • 1School of Electrical Engineering and Intelligentization, DongGuan University of Technology, Dongguan 523000, China.

Sensors (Basel, Switzerland)
|July 11, 2023
PubMed
Summary

The new Corner-point and Foreground-area IoU (CFIoU) loss improves small object detection by using corner point distance and target foreground area. This method enhances localization accuracy and convergence speed for better object detection performance.

Keywords:
bounding box regressionloss functionobject detectionsmall object

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

581
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

Related Experiment Videos

Last Updated: Jul 23, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

581
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.0K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Bounding box regression is critical for object detection accuracy, especially for small objects.
  • Existing Broad Intersection over Union (BIoU) losses face challenges with slow convergence and ineffective fitting information near the target box.
  • Current localization loss functions often underutilize the spatial information of the target's foreground area.

Purpose of the Study:

  • To propose a novel Corner-point and Foreground-area IoU (CFIoU) loss function to address limitations in bounding box regression for object detection.
  • To enhance the fitting information and utilization of spatial target data, particularly for small object detection.
  • To improve convergence speed and localization accuracy in object detection models.

Main Methods:

  • Introduced CFIoU loss by replacing normalized center-point distance with normalized corner point distance to improve fitting when boxes are close.
  • Incorporated adaptive target foreground area information into the loss function to provide richer contextual data for optimization.
  • Validated the CFIoU loss through simulation experiments and quantitative comparisons with mainstream BIoU losses on YOLOv5, YOLOv8, and SSD algorithms.

Main Results:

  • CFIoU loss significantly improved performance on VisDrone2019 and SODA-D datasets for both YOLOv5s and YOLOv8s, showing notable gains in Recall and mAP metrics.
  • On VisDrone2019, YOLOv5s with CFIoU saw +3.12% Recall and +2.73% mAP@0.5; YOLOv8s saw +1.72% Recall and +0.60% mAP@0.5.
  • On SODA-D, YOLOv5s with CFIoU achieved +6% Recall and +13.08% mAP@0.5; YOLOv8s saw +3.36% Recall and +3.66% mAP@0.5.
  • SSD algorithm incorporating CFIoU loss showed improved AP (+5.59%) and AP75 (+5.37%), demonstrating effectiveness even for algorithms not specialized in small object detection.

Conclusions:

  • The proposed CFIoU loss function is effective and superior for small object detection tasks.
  • CFIoU loss enhances localization accuracy and convergence, outperforming existing BIoU losses.
  • The CFIoU loss demonstrates versatility by improving performance across different object detection architectures, including those less proficient in small object detection.