English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

While computer vision has received increasing attention in computer scienceover the last decade, there are few efforts in applying this to leverageengineering design research. Existing datasets and technologies allowresearchers to capture and access more observations and video files, henceanalysis is becoming a limiting factor. Therefore, this paper is investigatingthe application of machine learning, namely object detection methods to aid inthe analysis of physical porotypes. With access to a large dataset of digitallycaptured physical prototypes from early-stage development projects (5950 imagesfrom 850 prototypes), the authors investigate applications that can be used foranalysing this dataset. The authors retrained two pre-trained object detectionmodels from two known frameworks, the TensorFlow Object Detection API andDarknet, using custom image sets of images of physical prototypes. As a result,a proof-of-concept of four trained models are presented; two models fordetecting samples of wood-based sheet materials and two models for detectingsamples containing microcontrollers. All models are evaluated using standardmetrics for object detection model performance and the applicability of usingobject detection models in engineering design research is discussed. Resultsindicate that the models can successfully classify the type of material andtype of pre-made component, respectively. However, more work is needed to fullyintegrate object detection models in the engineering design analysis workflow.The authors also extrapolate that the use of object detection for analysingimages of physical prototypes will substantially reduce the effort required foranalysing large datasets in engineering design research.

On Applying Machine Learning/Object Detection Models for Analysing Digitally Captured Physical Prototypes from Engineering Design Projects