Object Detection (OD) has proven to be a significant computer vision method in extracting localized class information and has multiple applications in the industry. Although many of the state-of-the-art (SOTA) OD models perform well on medium and large sized objects, they seem to under perform on small objects. In most of the industrial use cases, it is difficult to collect and annotate data for small objects, as it is time-consuming and prone to human errors. Additionally, those datasets are likely to be unbalanced and often result in an inefficient model convergence. To tackle this challenge, this study presents a novel approach that injects additional data points to improve the performance of the OD models. Using synthetic data generation, the difficulties in data collection and annotations for small object data points can be minimized and to create a dataset with balanced distribution. This paper discusses the effects of a simple proportional class-balancing technique, to enable better anchor matching of the OD models. A comparison was carried out on the performances of the SOTA OD models: YOLOv5, YOLOv7 and SSD, for combinations of real and synthetic datasets within an industrial use case.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Enhancing Object Detection Performance for Small Objects Through Synthetic Data Generation and Proportional Class-Balancing Technique: A Comparative Study in Industrial Scenarios


    Additional title:

    Lect.Notes Mechanical Engineering



    Conference:

    European Symposium on Artificial Intelligence in Manufacturing ; 2023 ; Kaiserslautern, Germany September 19, 2023 - September 19, 2023



    Publication date :

    2024-06-27


    Size :

    16 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Fast Detection of Moving Objects in Complex Scenarios

    Rabe, C. / Franke, U. / Gehrig, S. et al. | British Library Conference Proceedings | 2007


    Enhancing Traffic Incident Detection Through ADASYN-Attention Fusion: A Comparative Study with RITIS Data

    Liu, Ruifeng / Xie, Yuanchang / Stamatiadis, Polichronis et al. | IEEE | 2024



    Fast detection of moving objects in complex scenarios

    Rabe, Clemens / Franke, Uwe / Gehrig, Stefan | IEEE | 2007


    Generation of a Class of Proportional Navigation Guided Interceptor Phantom Tracks

    Dhananjay, N. / Ghose, D. / Kuduvalli, A. | AIAA | 2015