Inspection planning approaches so far have focused on automatically obtaining an optimal set of viewpoints required to cover a given object. While research has provided interesting results, the automatic inspection planning has still not been made a part of the everyday inspection system development process. This is mostly because the plans are difficult to verify and it is impossible to compare them to laboratory-developed plans. In this work, we give an overview of available generate-and-test approaches, evaluate their results for various objects and finally compare them to plans created by inspection system development experts. The comparison emphasizes both benefits and downsides of automated approaches and highlights problems which need to be tackled in the future in order to make the automated inspection planning more applicable.
15 October 2020 in Machine Vision and Applications
The goal of visual surface inspection is to analyze an object’s surface and detect defects by looking at it from different angles. Developments over the past years have made it possible to partially automate this process. Inspection systems use robots to move cameras and obtain pictures that are evaluated by image processing algorithms. Setting up these systems or adapting them to new models is primarily done manually. A key challenge is to define camera viewpoints from which the images are taken. The number of viewpoints should be as low as possible while still guaranteeing an inspection of the desired quality. System engineers define and evaluate configurations that are improved based on a time-consuming trial-and-error process leading to a sufficient, but not necessarily optimal, configuration. With the availability of 3D surface models defined by triangular meshes, this step can be done virtually. This paper presents a new scalable approach to determine a small number of well-placed camera viewpoints for optical surface inspection planning. The initial model is approximated by B-spline surfaces. A set of geometric feature functionals is defined and used for an adaptive, non-uniform surface sampling that is sparse in geometrically low-complexity areas and dense in regions of higher complexity. The presented approach is applicable to solid objects with a given 3D surface model. It makes camera viewpoint generation independent of the resolution of the triangle mesh, and it improves previous results considering number of viewpoints and their relevance.
Natural disasters demand swift and accurate impact assessment, yet traditional field-based methods remain prohibitively slow. While semi-automatic techniques leveraging remote sensing and drone imagery have accelerated evaluations, existing datasets predominantly emphasize Western infrastructure, offering limited representation of African contexts. The EDDA dataset (a Mozambique post-disaster building damage dataset developed under the Efficient Humanitarian Aid Through Intelligent Image Analysis project), addresses this critical gap by capturing rural and urban damage patterns in Mozambique following Cyclone Idai. Despite encouraging early results, significant challenges persist due to task complexity, severe class imbalance, and substantial architectural diversity across regions. Building upon EDDA, this study introduces a two-stage building damage assessment pipeline that decouples localization from classification. We employ lightweight You Only Look Once (YOLO)-based detectors—RTMDet, YOLOv7, and YOLOv8—for building localization, followed by dedicated damage severity classification using state-of-the-art architectures including Compact Convolutional Transformers, EfficientNet, and ResNet. This approach tests whether separating feature extraction tasks—assigning detectors solely to localization and specialized classifiers to damage assessment—yields superior performance compared to multi-class detection models that jointly learn both objectives. Comprehensive evaluation across 640+ model combinations demonstrates that our two-stage pipeline achieves competitive performance (mAP 0.478) with enhanced modularity compared to multi-class detection baselines (mAP 0.455), offering improved robustness across diverse building types and imbalanced damage classes.