paper-with-me

홈 › Papers

Domain Randomization for Object Detection in Manufacturing Applications using Synthetic Data: A Comprehensive Study

2025-06-09 · Xiaomeng Zhu, Jacob Henningsson, Duruo Li, Pär Mårtensson, Lars Hanson, Mårten Björkman, Atsuto Maki

This paper addresses key aspects of domain randomization in generating synthetic data for manufacturing object detection applications. To this end, we present a comprehensive data generation pipeline that reflects different factors: object characteristics, background, illumination, camera settings, and post-processing. We also introduce the Synthetic Industrial Parts Object Detection dataset (SIP15-OD) consisting of 15 objects from three industrial use cases under varying environments as a test bed for the study, while also employing an industrial dataset publicly available for robotic applications. In our experiments, we present more abundant results and insights into the feasibility as well as challenges of sim-to-real object detection. In particular, we identified material properties, rendering methods, post-processing, and distractors as important factors. Our method, leveraging these, achieves top performance on the public dataset with Yolov8 models trained exclusively on synthetic data; mAP@50 scores of 96.4% for the robotics dataset, and 94.1%, 99.5%, and 95.3% across three of the SIP15-OD use cases, respectively. The results showcase the effectiveness of the proposed domain randomization, potentially covering the distribution close to real data for the applications.

📄 PDF Abstract BibTeX arXiv:2506.07539

Code (1)

jacobhenningsson95/synmfg_code 공식 구현

Tasks

Objectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

YOLOv8 설명 없음

Similar Papers 제목 키워드 기반

Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection

2024-03-06 · Nico Baumgart, Markus Lange-Hegermann, Mike Mücke

In industrial manufacturing, numerous tasks of visually inspecting or detecting specific objects exist that are currently performed manually or by classical image processing methods. Therefore, introducing recent deep le…

Image Generationobject-detectionObject Detection

Object Detection Using Sim2Real Domain Randomization for Robotic Applications

2022-08-08 · Dániel Horváth, Gábor Erdős, Zoltán Istenes, Tomáš Horváth 외

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific …

GPUobject-detectionObject DetectionTransfer Learning

Hybrid Synthetic Data Generation with Domain Randomization Enables Zero-Shot Vision-Based Part Inspection Under Extreme Class Imbalance

2025-11-28 · Ruo-Syuan Mei, Sixian Jia, Guangze Li, Soo Yeon Lee 외 arxiv

Machine learning, particularly deep learning, is transforming industrial quality inspection. Yet, training robust machine learning models typically requires large volumes of high-quality labeled data, which are expensive…

Synthetic Data GenerationZero-Shot LearningObject Detection

Fully-Synthetic Training for Visual Quality Inspection in Automotive Production

2025-03-12 · Christoph Huber, Dino Knoll, Michael Guthe

Visual Quality Inspection plays a crucial role in modern manufacturing environments as it ensures customer safety and satisfaction. The introduction of Computer Vision (CV) has revolutionized visual quality inspection by…

Defect Detectionobject-detectionObject Detection

Object Detection using Domain Randomization and Generative Adversarial Refinement of Synthetic Images

2018-05-30 · Fernando Camaro Nogues, Andrew Huie, Sakyasingha Dasgupta

In this work, we present an application of domain randomization and generative adversarial networks (GAN) to train a near real-time object detector for industrial electric parts, entirely in a simulated environment. Larg…

object-detectionObject DetectionTranslation