A Storage-Efficient Feature for 3D Concrete Defect Segmentation to Replace Normal Vector
This addresses storage constraints for 3D concrete defect analysis on resource-constrained hardware, though it appears incremental as it modifies features rather than introducing a new paradigm.
The paper tackles the problem of high storage requirements for 3D point cloud features in concrete defect segmentation by proposing a new single-dimensional feature called relative angle, which achieved similar performance to normal vectors while reducing storage by 27.6% and compressing input channels by 83%.
Point cloud reconstruction of damage offers an effective solution to image-based methods vulnerable to background noise, yet its application is constrained by the high volume of 3D data. This study proposes a new feature, relative angle, computed as the angle between the normal vector of a point and the average normal vector of its parent point cloud. This single-dimensional feature provides directionality information equivalent to normal vectors for concrete surface defect characteristics. Through entropy-based feature evaluation, this study demonstrates the ability of relative angle to filter out redundant information in undamaged sections while retaining effective information in damaged sections. By training and testing with PointNet++, models based on the relative angles achieved similar performance to that of models based on normal vectors while delivering 27.6% storage reduction and 83% input channel compression. This novel feature has the potential to enable larger-batch execution on resource-constrained hardware without the necessity of architectural modifications to models.