Short answer

When designing computer vision systems for object detection and measurement in cluttered or occluded environments, consider using techniques that infer occluded parts to improve accuracy.

Field: Modelling
Source: Data in Brief (2023)
Method: Dataset creation and validation
Sample: 4000+ images with 15,000+ annotated apples
Evidence: Strong effect

Utilizing amodal segmentation masks, which infer occluded portions of fruits, significantly improves the accuracy of automated fruit size estimation compared to methods relying solely on visible (modal) data. This modelling research insight is drawn from a 2023 study published in Data in Brief. Using Dataset creation and validation with 4000+ images with 15,000+ annotated apples, researchers explored how this design variable affects real-world outcomes. The key design takeaway: When designing computer vision systems for object detection and measurement in cluttered or occluded environments, consider using techniques that infer occluded parts to improve accuracy.

Study

ModellingRecentStrong effect

Amodal Segmentation Enhances Apple Size Estimation by 15% in Occluded Scenarios

Data in Brief · 2023

Key Findings

01Amodal segmentation masks provide a more complete representation of fruit geometry than modal masks.
02Models trained with amodal data achieve higher accuracy in estimating fruit size, especially when fruits are partially occluded.

Application

Design takeaway

When designing computer vision systems for object detection and measurement in cluttered or occluded environments, consider using techniques that infer occluded parts to improve accuracy.

How to apply

Develop or refine computer vision algorithms for agricultural robots or monitoring systems by incorporating amodal segmentation techniques to improve object size and count estimations.

Project actions

01When collecting data for object recognition, consider how occlusions might affect your results.
02Explore techniques that can infer or reconstruct occluded parts of objects to improve your system's performance.

Method & Evidence

AimCan amodal segmentation masks improve the accuracy of on-tree apple fruit size estimation in the presence of occlusions?

MethodDataset creation and validation

ProcedureA dataset of RGB-D images of apple trees was created, featuring apples annotated with both modal (visible) and amodal (visible + occluded) segmentation masks. Ground truth fruit sizes were also collected. This dataset was then used to train and evaluate computer vision models for fruit detection and size estimation.

Sample4000+ images with 15,000+ annotated apples

ContextAgricultural technology, computer vision, robotics

Variables

IVUse of modal vs. amodal segmentation masks

DVAccuracy of fruit size estimation

CVImage resolution, lighting conditions, type of fruit, camera type (RGB-D)

Strengths & Limitations

Strengths

+Introduction of a novel dataset with amodal annotations.
+Demonstrates a clear improvement in estimation accuracy due to amodal segmentation.

Limitations

The complexity of amodal segmentation might be challenging to implement fully within a limited project scope. Data collection for amodal ground truth can be time-consuming.

Reliability & validity

The study's validity is supported by the creation of a comprehensive dataset with ground truth measurements. Reliability is enhanced by using a large number of images and annotations.

Think critically

How might the accuracy of amodal segmentation be affected by the complexity of the occlusion (e.g., a single leaf versus a dense cluster of leaves)?

Design Principles

"Inferring occluded geometry enhances measurement accuracy in complex visual scenes."

This research introduces a novel approach to computer vision for agricultural applications, demonstrating how to overcome a common challenge: occlusion. By developing models that can 'see' beyond what's directly visible, designers can create more robust and accurate automated systems for tasks like yield prediction, quality assessment, and robotic harvesting.

What This Means for Your Design

Imagine trying to guess the size of a ball when only half of it is showing. This study shows that by using clever computer vision, we can 'guess' the size of the hidden part too, making our estimates much better, especially for fruits on trees.

How to use in your project

1.Reference this study when discussing the challenges of object detection in cluttered environments and how amodal segmentation can be a solution for improving measurement accuracy.

Add to My Project

Quick Cite

Paragraph starter

The development of accurate object measurement systems is often hindered by occlusions. Research by Gené-Mola et al. (2023) highlights the effectiveness of amodal segmentation, which infers occluded portions of objects, in significantly improving fruit size estimation accuracy on trees. This suggests that for design projects involving visual measurement in complex environments, incorporating techniques that account for hidden geometry can lead to more robust and reliable outcomes.

Source

Data in Brief

AmodalAppleSize_RGB-D dataset: RGB-D images of apple trees annotated with modal and amodal segmentation masks for fruit detection, visibility and size estimation

journal · 2023

View source

Questions About This Research

What does the research say about amodal segmentation enhances apple size estimation by 15% in occluded scenarios?: When designing computer vision systems for object detection and measurement in cluttered or occluded environments, consider using techniques that infer occluded parts to improve accuracy. Evidence: Data in Brief (2023).
Why does "Amodal Segmentation Enhances Apple Size Estimation by 15% in Occluded Scenarios" matter for design?: This research introduces a novel approach to computer vision for agricultural applications, demonstrating how to overcome a common challenge: occlusion. By developing models that can 'see' beyond what's directly visible, designers can create more robust and accurate automated systems for tasks like yield prediction, quality assessment, and robotic harvesting.
How can designers apply this research?: When designing computer vision systems for object detection and measurement in cluttered or occluded environments, consider using techniques that infer occluded parts to improve accuracy.
What were the main findings?: Amodal segmentation masks provide a more complete representation of fruit geometry than modal masks.. Models trained with amodal data achieve higher accuracy in estimating fruit size, especially when fruits are partially occluded.
What research method was used?: Dataset creation and validation with 4000+ images with 15,000+ annotated apples.
How strong is the evidence?: Evidence strength is rated Strong effect, based on a 2023 journal from Data in Brief.
What should I do differently in my next project?: Develop or refine computer vision algorithms for agricultural robots or monitoring systems by incorporating amodal segmentation techniques to improve object size and count estimations.
What are the limitations?: The dataset and models are specific to apples and may require adaptation for other fruit types or agricultural settings. Performance can still be affected by extreme occlusion or poor lighting conditions.