Explore the vast range of titles available.

Today, the most widely used visual markers, such as ArUco and AprilTag, rely on square pixel arrays. While these markers can deliver satisfactory detection and identification outcomes, they remain vulnerable to corner occlusion despite incorporating corrective codes. Conversely, line-based markers offer increased resilience against occlusions but are typically constrained in terms of codification capacities. The markers developed in this research leverage linear information to propose a pyramidal line-based structure that exhibits robustness to corner occlusion while providing enhanced coding capacities. Moreover, the projective invariance of the constituent lines enables the validation of a homography-less identification method that considerably reduces computation resources and processing time. We assembled an extensive test dataset of 169,713 images for evaluation, including rotation, distances, and different levels of occlusion. Experiments on this dataset show that the proposed marker significantly outperforms previous fiducial marker systems across multiple metrics, including execution time and detection performance under occlusion. It effectively identifies markers with up to 50% occlusion and achieves identification at a resolution of 1920×1080 in 17.20 ms. The developed marker generation and identification, as well as an extensive marker Database, are publicly available for tests at https://github.com/OILUproject/OILUtag.

In this paper, a multi-frame based homography estimation method is proposed for video stitching in static camera environments. A homography that is robust against spatio-temporally induced noise can be estimated by intervals, using feature points extracted during a predetermined time interval. The feature point with the largest blob response in each quantized location bin, a representative feature point, is used for matching a pair of video sequences. After matching representative feature points from each camera, the homography for the interval is estimated by random sample consensus (RANSAC) on the matched representative feature points, with their chances of being sampled proportional to their numbers of occurrences in the interval. The performance of the proposed method is compared with that of the per-frame method by investigating alignment distortion and stitching scores for daytime and noisy video sequence pairs. It is shown that alignment distortion in overlapping regions is reduced and the stitching score is improved by the proposed method. The proposed method can be used for panoramic video stitching with static video cameras and for panoramic image stitching with less alignment distortion.

Existing homography and optical flow methods are erroneous in challenging scenes, such as fog, rain, night, and snow because the basic assumptions such as brightness and gradient constancy are broken. To address this issue, we present an unsupervised learning approach that fuses gyroscope into homography and optical flow learning. Specifically, we first convert gyroscope readings into motion fields named gyro field. Second, we design a self-guided fusion module (SGF) to fuse the background motion extracted from the gyro field with the optical flow and guide the network to focus on motion details. Meanwhile, we propose a homography decoder module (HD) to combine gyro field and intermediate results of SGF to produce the homography. To the best of our knowledge, this is the first deep learning framework that fuses gyroscope data and image content for both deep homography and optical flow learning. To validate our method, we propose a new dataset that covers regular and challenging scenes. Experiments show that our method outperforms the state-of-the-art methods in both regular and challenging scenes. The code and dataset are available at https://github.com/lhaippp/GyroFlowPlus.

In monocular vision measurement, a barrier to implementation is the perspective distortion caused by manufacturing errors in the imaging chip and non-parallelism between the measurement plane and its image, which seriously affects the accuracy of pixel equivalent and measurement results. This paper proposed a perspective distortion correction method for planar imaging based on homography mapping. Factors causing perspective distortion from the camera’s intrinsic and extrinsic parameters were analyzed, followed by constructing a perspective transformation model. Then, a corrected imaging plane was constructed, and the model was further calibrated by utilizing the homography between the measurement plane, the actual imaging plane, and the corrected imaging plane. The nonlinear and perspective distortions were simultaneously corrected by transforming the original image to the corrected imaging plane. The experiment measuring the radius, length, angle, and area of a designed pattern shows that the root mean square errors will be 0.016 mm, 0.052 mm, 0.16°, and 0.68 mm2, and the standard deviations will be 0.016 mm, 0.045 mm, 0.033° and 0.65 mm2, respectively. The proposed method can effectively solve the problem of high-precision planar measurement under perspective distortion.

This paper presents a measurement method of bridge vibration based on three-dimensional (3D) reconstruction. A video of bridge model vibration is recorded by an unmanned aerial vehicle (UAV), and the displacement of target points on the bridge model is tracked by the digital image correlation (DIC) method. Due to the UAV motion, the DIC-tracked displacement of the bridge model includes the absolute displacement caused by the excitation and the false displacement induced by the UAV motion. Therefore, the UAV motion must be corrected to measure the real displacement. Using four corner points on a fixed object plane as the reference points, the projection matrix for each frame of images can be estimated by the UAV camera calibration, and then the 3D world coordinates of the target points on the bridge model can be recovered. After that, the real displacement of the target points can be obtained. To verify the correctness of the results, the operational modal analysis (OMA) method is used to extract the natural frequencies of the bridge model. The results show that the first natural frequency obtained from the proposed method is consistent with the one obtained from the homography-based method. By further comparing with the homography-based correction method, it is found that the 3D reconstruction method can effectively overcome the limitation of the homography-based method that the fixed reference points and the target points must be coplanar.

Camera systems support the rapid assessment of ship traffic at ports, allowing for a better perspective of the maritime situation. However, optimal ship monitoring requires a level of automation that allows personnel to keep track of relevant variables in the maritime situation in an understandable and visualisable format. It therefore becomes important to have real-time recognition of ships present at the infrastructure, with their class and geographic position presented to the maritime situational awareness operator. This work presents a novel dataset, ShipSG, for the segmentation and georeferencing of ships in maritime monitoring scenes with a static oblique view. Moreover, an exploration of four instance segmentation methods, with a focus on robust (Mask-RCNN, DetectoRS) and real-time performances (YOLACT, Centermask-Lite) and their generalisation to other existing maritime datasets, is shown. Lastly, a method for georeferencing ship masks is proposed. This includes an automatic calculation of the pixel of the segmented ship to be georeferenced and the use of a homography to transform this pixel to geographic coordinates. DetectoRS provided the highest ship segmentation mAP of 0.747. The fastest segmentation method was Centermask-Lite, with 40.96 FPS. The accuracy of our georeferencing method was (22 ± 10) m for ships detected within a 400 m range, and (53 ± 24) m for ships over 400 m away from the camera.

Multi-viewpoint image stitching aims to stitch images taken from different viewpoints into pictures with a broader field of view. The stitched images are subject to artifacts, geometric distortion, and blur distortion due to the mismatch of feature points, inaccurate homography estimation, and improper fusion of the unstitched images. Deep learning has recently been increasingly applied to multi-viewpoint image stitching to overcome these problems. However, there has thus far been little related research to summarize the different deep learning techniques used for multi-viewpoint image stitching. Therefore, this review aims to explore the application of deep learning to multi-viewpoint image stitching. To better illustrate this topic, we first summarize the acquisition methods for multi-viewpoint images and the main challenges of image stitching. After which, deep learning techniques for multi-view image stitching with a single camera are sorted out. Subsequently, deep learning techniques for multi-view image stitching with camera arrays, including parallel-view multi-view image stitching and cross-view multi-view image stitching, are presented. Next, we summarize image stitching datasets, evaluation metrics, and experimental data of several leading stitching algorithms on public datasets. Finally, we discuss potential issues and future work on image stitching with multi-viewpoint images.

Visual obstacle discovery is a key step towards autonomous navigation of indoor mobile robots. Successful solutions have many applications in multiple scenes. One of the exceptions is the reflective ground. In this case, the reflections on the floor resemble the true world, which confuses the obstacle discovery and leaves navigation unsuccessful. We argue that the key to this problem lies in obtaining discriminative features for reflections and obstacles. Note that obstacle and reflection can be separated by the ground plane in 3D space. With this observation, we firstly introduce a pre-calibration based ground detection scheme that uses robot motion to predict the ground plane. Due to the immunity of robot motion to reflection, this scheme avoids failed ground detection caused by reflection. Given the detected ground, we design a ground-pixel parallax to describe the location of a pixel relative to the ground. Based on this, a unified appearance-geometry feature representation is proposed to describe objects inside rectangular boxes. Eventually, based on segmenting by detection framework, an appearance-geometry fusion regressor is designed to utilize the proposed feature to discover the obstacles. It also prevents our model from concentrating too much on parts of obstacles instead of whole obstacles. For evaluation, we introduce a new dataset for Obstacle on Reflective Ground (ORG), which comprises 15 scenes with various ground reflections, a total of more than 200 image sequences and 3400 RGB images. The pixel-wise annotations of ground and obstacle provide a comparison to our method and other methods. By reducing the misdetection of the reflection, the proposed approach outperforms others. The source code and the dataset will be available at https://github.com/xuefeng-cvr/IndoorObstacleDiscovery-RG

Structural displacement monitoring is an essential component of structural health monitoring of bridges, providing valuable information for performance evaluation, numerical model validation, and damage detection. While conventional contact-based sensors provide high accuracy, their installation is often complex, costly, and disruptive to traffic. Recent developments in unmanned aerial vehicle (UAV) platforms and vision-based measurement techniques offer a flexible, non-contact alternative; however, platform motion remains a major source of uncertainty. This study evaluates the accuracy and operational feasibility of UAV-based homography for static and dynamic displacement monitoring. The proposed approach is validated through three complementary experimental campaigns: a controlled calibration field test, a beam static load test, and bridge monitoring under traffic loading, with direct comparison to LVDT and RTS measurements. Under controlled conditions, sub-millimetre vertical precision was achieved, with RMSE values below 0.3 mm. In full-scale bridge applications, the method captured traffic-induced displacement trends with errors generally within 1–2 mm compared to LVDT data and with RMSE values below 1.4 mm. The results demonstrate that, when appropriate reference point configuration and imaging geometry are ensured, UAV-based homography provides a practical and sufficiently accurate solution for bridge displacement monitoring which is especially important in applications where sensor installation is difficult or unsafe.

As an important representation of scenes in virtual reality and augmented reality, image stitching aims to generate a panoramic image with a natural field-of-view by stitching multiple images together, which are captured by different visual sensors. Existing deep-learning-based methods for image stitching only conduct a single deep homography to perform image alignment, which may produce inevitable alignment distortions. To address this issue, we propose a content-seam-preserving multi-alignment network (CSPM-Net) for visual-sensor-based image stitching, which could preserve the image content consistency and avoid seam distortions simultaneously. Firstly, a content-preserving deep homography estimation was designed to pre-align the input image pairs and reduce the content inconsistency. Secondly, an edge-assisted mesh warping was conducted to further align the image pairs, where the edge information is introduced to eliminate seam artifacts. Finally, in order to predict the final stitched image accurately, a content consistency loss was designed to preserve the geometric structure of overlapping regions between image pairs, and a seam smoothness loss is proposed to eliminate the edge distortions of image boundaries. Experimental results demonstrated that the proposed image-stitching method can provide favorable stitching results for visual-sensor-based images and outperform other state-of-the-art methods.