In computer vision, timely and accurate execution of object identification tasks is critical. However, present road damage detection approaches based on deep learning suffer from complex models and computationally time-consuming issues. To address these issues, we present a lightweight model for road damage identification by enhancing the YOLOv5s approach. The resulting algorithm, YOLO-LRDD, provides a good balance of detection precision and speed. First, we propose the novel backbone network Shuffle-ECANet by adding an ECA attention module into the lightweight model ShuffleNetV2. Second, to ensure reliable detection, we employ BiFPN rather than the original feature pyramid network since it improves the network's capacity to describe features. Moreover, in the model training phase, localization loss is modified to Focal-EIOU in order to get higher-quality anchor box. Lastly, we augment the well-known RDD2020 dataset with many samples of Chinese road scenes and compare YOLO-LRDD against several state-of-the-art object detection techniques. The smaller model of our YOLO-LRDD offers superior performance in terms of accuracy and efficiency, as determined by our experiments. Compared to YOLOv5s in particular, YOLO-LRDD improves single image recognition speed by 22.3% and reduces model size by 28.8% while maintaining comparable accuracy. In addition, it is easier to implant in mobile devices because its model is smaller and lighter than those of the other approaches.

To cope with the challenges some commonly used displacement sensors may face in structural health monitoring, we proposed a wireless binocular stereovision measurement system based on the improved coarse-to-fine matching algorithm. The vision measurement system can perceive multipoint three-dimensional displacement and consists of two cameras, one remote control unit, and a solar panel. The improved coarse-to-fine matching algorithm only requires a flat surface with some painted textures instead of designed markers with refined patterns (circle, square, and chessboard). Omitting the textures keeps a balance between measurement accuracy and the burden of the target installation in the actual field of structural health monitoring. The proposed coarse-to-fine matching algorithm utilizes scale-invariant feature transform (SIFT) points to generate a robust initial guess and combines improved least squares matching (LSM) algorithm for advanced corresponding point matching. A precalculated look-up table for interpolation and parallel computation is used for higher matching precision and computational efficiency. Several experiments were conducted to present the accuracy and feasibility of the proposed metering system. A simulation test, an indoor shaking table test with several commonly used displacement sensors, and an outdoor experiment consider the natural condition. Experimental results verified that the proposed matching methodology could achieve 0.2-pixel matching accuracy, 0.1mm measuring precision in a laboratory, and millimeter-level precision in real conditions.

Structure from motion (SfM) has been treated as a mature technique to carry out the task of image orientation and 3D reconstruction. However, it is an ongoing challenge to obtain correct reconstruction results from image sets consisting of problematic match pairs. This paper investigated two types of problematic match pairs, stemming from repetitive structures and very short baselines. We built a weighted view-graph based on all potential match pairs and propose a progressive SfM method (PRMP-PSfM) that iteratively prioritizes and refines its match pairs (or edges). The method has two main steps: initialization and expansion. Initialization is developed for reliable seed reconstruction. Specifically, we prioritize a subset of match pairs by the union of multiple independent minimum spanning trees and refine them by the idea of cycle consistency inference (CCI), which aims to infer incorrect edges by analyzing the geometric consistency over cycles of the view-graph. The seed reconstruction is progressively expanded by iteratively adding new minimum spanning trees and refining the corresponding match pairs, and the expansion terminates when a certain completeness of the block is achieved. Results from evaluations on several public datasets demonstrate that PRMP-PSfM can successfully accomplish the image orientation task for datasets with repetitive structures and very short baselines and can obtain better or similar accuracy of reconstruction results compared to several state-of-the-art incremental and hierarchical SfM methods.

Image-based 3D reconstruction generates 3D mesh models from images and plays an important role in all walks of life. However, existing methods suffer from poor reconstruction quality and low reconstruction efficiency. To address this issue, we propose an improved optimization-based mesh reconstruction method with adaptive visibility reconstruction and dynamic photo-metric refinement. The adaptive visibility reconstruction adjusts soft visibility based on the observation and geometry structure of points to reconstruct details while suppressing noise in the rough mesh. The dynamic photo-metric refinement tunes the learning rate using historical gradients and stops to optimize converged triangles to speed up the mesh refinement. Experiments on BlendedMVS and real datasets showed that our method found a good balance between reconstruction quality and reconstruction efficiency. Compared with the state-of-the-art methods, OpenMVS and TDR, our method achieved higher reconstruction quality than OpenMVS and obtained competitive reconstruction quality with TDR, but required only one-third of the reconstruction time of OpenMVS and one-tenth of the reconstruction time of TDR. Our method balances reconstruction efficiency and reconstruction quality and can meet real-world application requirements.

Variational mesh refinement is a crucial step in multiview 3D reconstruction. Existing algorithms either focus on recovering mesh details or focus on suppressing noise. Approaches with consideration of both are lacking. To address this limitation, we proposed a new variational mesh refinement method named total differential mesh refinement (TDR), which mainly included two improvements. First, the traditional partial-differential photo-consistency gradient used in the variational mesh refinement method was replaced by the proposed total-differential photo-consistency gradient. With consideration of the photo-consistency correlation between adjacent pixels, our method can make photo-consistency achieve a more effective convergence than traditional approaches. Second, we introduced the bilateral normal filter with a novel self-adaptive mesh denoising strategy into the variational mesh refinement. This strategy maintains a balance between detail preservation and effective denoising via the zero-normalized cross-correlation (ZNCC) map. Various experiments demonstrated that our method is superior to traditional variational mesh refinement approaches in both accuracy and denoising effect. Moreover, compared with the mesh generated by open-source and commercial software (Context Capture), our meshes are more detailed, regular, and smooth.