Single Model Test Research Articles

An anchor-free region proposal network for Faster R-CNN-based text detection approaches

The anchor mechanism of Faster R-CNN and SSD framework is considered not effective enough to scene text detection, which can be attributed to its Intersection-over-Union-based matching criterion between anchors and ground-truth boxes. In order to better enclose scene text instances of various shapes, it requires to design anchors of various scales, aspect ratios and even orientations manually, which makes anchor-based methods sophisticated and inefficient. In this paper, we propose a novel anchor-free region proposal network (AF-RPN) to replace the original anchor-based RPN in the Faster R-CNN framework to address the above problem. Compared with the anchor-based region proposal generation approaches (e.g., RPN, FPN–RPN, RRPN and FPN–RRPN), AF-RPN can get rid of complicated anchor design and achieves higher recall rate on both horizontal and multi-oriented text detection benchmark tasks. Owing to the high-quality text proposals, our Faster R-CNN-based two-stage text detection approach achieves the state-of-the-art results on ICDAR-2017 MLT, COCO-Text, ICDAR-2015 and ICDAR-2013 text detection benchmark tasks by only using single-scale and single-model testing.

Practical Airgap Prediction for Offshore Structures

Two new methods are proposed to predict airgap demand. Airgap demand is the maximum expected increase in the water surface elevation caused incident waves interacting with an offshore structure. The first new method enables inclusion of some second-order effects, though it is based on only first-order diffraction results. The method is simple enough to be practical for use as a hand-calculation in the early stages of design. Two existing methods of predicting airgap demand based on first-order diffraction are also briefly presented and results from the three methods are compared with model test results. All three methods yield results superior to those based on conventional post-processing of first-order diffraction results, and comparable to optimal post-processing of second-order diffraction results. A second new method is also presented; it combines extreme value theory with statistical regression to predict extreme airgap events using model test data. Estimates of extreme airgap events based on this method are found to be more reliable than estimates based on extreme observations from a single model test. This second new method is suitable for use in the final stages of design.