Search Results (197)

Synthetic Aperture Radar (SAR) images and optical imagery have high potential for extracting digital elevation models (DEMs). The two main approaches for deriving elevation models from SAR data are interferometry (InSAR) and radargrammetry. Adapted from photogrammetric principles, radargrammetry relies on disparity model estimation as its core component. Matching strategies in radargrammetry typically follow local, global, or semi-global methodologies. Local methods, while having higher accuracy, especially in low-texture SAR images, require larger kernel sizes, leading to quadratic computational complexity. Conversely, global and semi-global models produce more consistent and higher-quality disparity maps but are computationally more intensive than local methods with small kernels and require more memory (RAM). In this study, inspired by the advantages of local matching algorithms, a computationally efficient and novel model is proposed for extracting corresponding pixels in SAR-intensity stereo images. To enhance accuracy, the proposed two-stage algorithm operates without an image pyramid structure. Notably, unlike traditional local and global models, the computational complexity of the proposed approach remains stable as the input size or kernel dimensions increase while memory consumption stays low. Compared to a pyramid-based local normalized cross-correlation (NCC) algorithm and adaptive semi-global matching (SGM) models, the proposed method maintains good accuracy comparable to adaptive SGM while reducing processing time by up to 50% relative to pyramid SGM and achieving a 35-fold speedup over the local NCC algorithm with an optimal kernel size. Validated on a Sentinel-1 stereo pair with a 10 m ground-pixel size, the proposed algorithm yields a DEM with an average accuracy of 34.1 m. Full article

We present HGC-Net, a hybrid pipeline for assessing geometric consistency between stereo image pairs. Our method integrates classical epipolar geometry with deep learning components to compute an interpretable scalar score A, reflecting the degree of alignment. Unlike traditional techniques, which may overlook subtle miscalibrations, HGC-Net reliably detects both severe and mild geometric distortions, such as sub-degree tilts and pixel-level shifts. We evaluate the method on the Middlebury 2014 stereo dataset, using synthetically distorted variants to simulate misalignments. Experimental results show that our score degrades smoothly with increasing geometric error and achieves high detection rates even at minimal distortion levels, outperforming baseline approaches based on disparity or calibration checks. The method operates in real time (12.5 fps on 1080p input) and does not require access to internal camera parameters, making it suitable for embedded stereo systems and quality monitoring in robotic and AR/VR applications. The approach also supports explainability via confidence maps and anomaly heatmaps, aiding human operators in identifying problematic regions. Full article

Located on the northern side of the China–Pakistan Highway in the Pamir Plateau, Laqi Gully represents a typical rainfall–meltwater coupled debris flow gully. During 2020–2024, seven debris flow events occurred in this area, four of which disrupted traffic and posed significant threats to the China–Pakistan Economic Corridor (CPEC). The hazard assessment of debris flows constitutes a crucial component in disaster prevention and mitigation. However, current research presents two critical limitations: traditional models primarily focus on single precipitation-driven debris flows, while low-resolution digital elevation models (DEMs) inadequately characterize the topographic features of alpine narrow valleys. Addressing these issues, this study employed GF-7 satellite stereo image pairs to construct a 1 m resolution DEM and systematically simulated debris flow propagation processes under 10–100-year recurrence intervals using a coupled rainfall–meltwater model. The results show the following: (1) The mudslide develops rapidly in the gully section, and the flow velocity decays when it reaches the highway. (2) At highway cross-sections, maximum velocities corresponding to 10-, 20-, 50-, and 100-year recurrence intervals measure 2.57 m/s, 2.75 m/s, 3.02 m/s, and 3.36 m/s, respectively, with maximum flow depths of 1.56 m, 1.78 m, 2.06 m, and 2.52 m. (3) Based on the hazard classification model of mudslide intensity and return period, the high-, medium-, and low-hazard sections along the highway were 58.65 m, 27.36 m, and 24.1 m, respectively. This research establishes a novel hazard assessment methodology for rainfall–meltwater coupled debris flows in narrow valleys, providing technical support for debris flow mitigation along the CPEC. The outcomes demonstrate significant practical value for advancing infrastructure sustainability under the United Nations Sustainable Development Goals (SDGs). Full article

Advancements in remote sensing technology have remarkably enhanced the 3D Earth surface reconstruction, which is pivotal for applications such as disaster relief, emergency management, and urban planning, etc. Although satellite imagery offers a cost-effective and extensive coverage solution for 3D reconstruction, the quality of the resulted digital surface model (DSM) heavily relies on the choice of stereo image pairs. However, current approaches of stereo Earth observation still employ a post-acquisition manner without sophisticated planning in advance, causing inefficiencies and low reconstruction quality. This paper introduces a novel quality-driven planning method for satellite stereo imaging, aiming at optimizing the search of stereo pairs to achieve high-quality 3D reconstruction. Moreover, a regression model is customized and incorporated to estimate the reconstructed point cloud geopositioning quality, based on the enhanced features of possible Earth-imaging opportunities. Experiments conducted on both real satellite images and simulated constellation data demonstrate the efficacy of the proposed method in estimating reconstruction quality beforehand and searching for optimal stereo pair combinations as the final satellite imaging schedule, which can improve the stereo quality significantly. Full article

With the advancement of agricultural automation technologies, apple-harvesting robots have gradually become a focus of research. As their “perceptual core,” machine vision systems directly determine picking success rates and operational efficiency. However, existing vision systems still exhibit significant shortcomings in target detection and positioning accuracy in complex orchard environments (e.g., uneven illumination, foliage occlusion, and fruit overlap), which hinders practical applications. This study proposes a visual system for apple-harvesting robots based on improved Mask R-CNN and binocular vision to achieve more precise fruit positioning. The binocular camera (ZED2i) carried by the robot acquires dual-channel apple images. An improved Mask R-CNN is employed to implement instance segmentation of apple targets in binocular images, followed by a template-matching algorithm with parallel epipolar constraints for stereo matching. Four pairs of feature points from corresponding apples in binocular images are selected to calculate disparity and depth. Experimental results demonstrate average coefficients of variation and positioning accuracy of 5.09% and 99.61%, respectively, in binocular positioning. During harvesting operations with a self-designed apple-picking robot, the single-image processing time was 0.36 s, the average single harvesting cycle duration reached 7.7 s, and the comprehensive harvesting success rate achieved 94.3%. This work presents a novel high-precision visual positioning method for apple-harvesting robots. Full article

The use of high-resolution satellite stereo pairs for dense image matching is a core technology for the low-cost generation of large-scale digital surface models (DSMs). However, water areas in satellite imagery often exhibit weak texture characteristics. This leads to serious issues in reconstructing water surface DSMs with traditional dense matching methods, such as significant holes and abnormal undulations. These problems significantly impact the intelligent application of satellite DSM products. To address these issues, this study innovatively proposes a water region DSM reconstruction method, boundary plane-constrained surface water stereo reconstruction (BPC-SWSR). The algorithm constructs a water surface reconstruction model with constraints on the plane’s tilt angle and boundary, combining effective ground matching data from the shoreline and the plane constraints of the water surface. This method achieves the seamless planar reconstruction of the water region, effectively solving the technical challenges of low geometric accuracy in water surface DSMs. This article conducts experiments on 10 high-resolution satellite stereo image pairs, covering three types of water bodies: river, lake, and sea. Ground truth water surface elevations were obtained through a manual tie point selection followed by forward intersection and planar fitting in water surface areas, establishing a rigorous validation framework. The DSMs generated by the proposed algorithm were compared with those generated by state-of-the-art dense matching algorithms and the industry-leading software Reconstruction Master version 6.0. The proposed algorithm achieves a mean RMSE of 2.279 m and a variance of 0.6613 m² in water surface elevation estimation, significantly outperforming existing methods with average RMSE and a variance of 229.2 m and 522.5 m², respectively. This demonstrates the algorithm’s ability to generate more accurate and smoother water surface models. Furthermore, the algorithm still achieves excellent reconstruction results when processing different types of water areas, confirming its wide applicability in real-world scenarios. Full article

Modern audio production workflows often require significant manual effort during the initial session preparation phase, including track labeling, format standardization, and gain staging. This paper presents a rule-based and Machine Learning-assisted automation system designed to minimize the time required for these tasks in Digital Audio Workstations (DAWs). The system automatically detects and labels audio tracks, identifies and eliminates redundant fake stereo channels, merges double-tracked instruments into stereo pairs, standardizes sample rate and bit rate across all tracks, and applies initial gain staging using target loudness values derived from a Genetic Algorithm (GA)-based system, which optimizes gain levels for individual track types based on engineer preferences and instrument characteristics. By replacing manual setup processes with automated decision-making methods informed by Machine Learning (ML) and rule-based heuristics, the system reduces session preparation time by up to 70% in typical multitrack audio projects. The proposed approach highlights how practical automation, combined with lightweight Neural Network (NN) models, can optimize workflow efficiency in real-world music production environments. Full article

Stereo images, which consist of left and right image pairs, are often unaligned when initially captured, as they represent raw data. Stereo images are typically used in scenarios requiring disparity between the left and right views, such as depth estimation. In such cases, image calibration is performed to obtain the necessary parameters, and, based on these parameters, image rectification is applied to align the epipolar lines of the stereo images. This preprocessing step is crucial for effectively utilizing stereo images. The conventional method for performing image calibration usually involves using a reference object, such as a checkerboard, to obtain these parameters. In this paper, we propose a novel approach that does not require any special reference points like a checkerboard. Instead, we employ object detection to segment object pairs and calculate the centroids of the segmented objects. By aligning the y-coordinates of these centroids in the left and right image pairs, we induce the epipolar lines to be parallel, achieving an effect similar to image rectification. Full article

Agricultural robots can mitigate labor shortages and advance precision farming. However, the dense vegetation canopies and uneven terrain in orchard environments reduce the reliability of traditional GPS-based localization, thereby reducing navigation accuracy and making autonomous navigation challenging. Moreover, inefficient path planning and an increased risk of collisions affect the robot’s ability to perform tasks such as fruit harvesting, spraying, and monitoring. To address these limitations, this study integrated stereo visual odometry with real-time appearance-based mapping (RTAB-Map)-based simultaneous localization and mapping (SLAM) to improve mapping and localization in both indoor and outdoor orchard settings. The proposed system leverages stereo image pairs for precise depth estimation while utilizing RTAB-Map’s graph-based SLAM framework with loop-closure detection to ensure global map consistency. In addition, an incorporated inertial measurement unit (IMU) enhances pose estimation, thereby improving localization accuracy. Substantial improvements in both mapping and localization performance over the traditional approach were demonstrated, with an average error of 0.018 m against the ground truth for outdoor mapping and a consistent average error of 0.03 m for indoor trails with a 20.7% reduction in visual odometry trajectory deviation compared to traditional methods. Localization performance remained robust across diverse conditions, with a low RMSE of 0.207 m. Our approach provides critical insights into developing more reliable autonomous navigation systems for agricultural robots. Full article

This paper provides a comparative analysis of calibration techniques applicable to stereo and near-infrared (NIR) camera systems, with a specific emphasis on the Intel RealSense SR300 alongside a standard 2-megapixel NIR camera. This study investigates the pivotal function of calibration within both stereo vision and NIR imaging applications, which are essential across various domains, including robotics, augmented reality, and low-light imaging. For stereo systems, we scrutinise the conventional method involving a 9 × 6 chessboard pattern utilised to ascertain the intrinsic and extrinsic camera parameters. The proposed methodology consists of three main steps: (1) real-time calibration error classification for stereo cameras, (2) NIR-specific calibration techniques, and (3) a comprehensive evaluation framework. This research introduces a novel real-time evaluation methodology that classifies calibration errors predicated on the pixel offsets between corresponding points in the left and right images. Conversely, NIR camera calibration techniques are modified to address the distinctive properties of near-infrared light. We deliberate on the difficulties encountered in devising NIR–visible calibration patterns and the imperative to consider the spectral response and temperature sensitivity within the calibration procedure. The paper also puts forth an innovative calibration assessment application that is relevant to both systems. Stereo cameras evaluate the corner detection accuracy in real time across multiple image pairs, whereas NIR cameras concentrate on assessing the distortion correction and intrinsic parameter accuracy under varying lighting conditions. Our experiments validate the necessity of routine calibration assessment, as environmental factors may compromise the calibration quality over time. We conclude by underscoring the disparities in the calibration requirements between stereo and NIR systems, thereby emphasising the need for specialised approaches tailored to each domain to guarantee an optimal performance in their respective applications. Full article

Three-dimensional reconstruction entails the development of mathematical models of three-dimensional objects that are suitable for computational representation and processing. This technique constructs realistic 3D models of images and has significant practical applications across various fields. This study proposes a rapid and precise multi-view 3D reconstruction method to address the challenges of low reconstruction efficiency and inadequate, poor-quality point cloud generation in incremental structure-from-motion (SFM) algorithms in multi-view geometry. The methodology involves capturing a series of overlapping images of campus. We employed the Scale-invariant feature transform (SIFT) algorithm to extract feature points from each image, applied the KD-Tree algorithm for inter-image matching, and Enhanced autonomous threshold adjustment by utilizing the Random sample consensus (RANSAC) algorithm to eliminate mismatches, thereby enhancing feature matching accuracy and the number of matched point pairs. Additionally, we developed a feature-matching strategy based on similarity, which optimizes the pairwise matching process within the incremental structure from a motion algorithm. This approach decreased the number of matches and enhanced both algorithmic efficiency and model reconstruction accuracy. For dense reconstruction, we utilized the patch-based multi-view stereo (PMVS) algorithm, which is based on facets. The results indicate that our proposed method achieves a higher number of reconstructed feature points and significantly enhances algorithmic efficiency by approximately ten times compared to the original incremental reconstruction algorithm. Consequently, the generated point cloud data are more detailed, and the textures are clearer, demonstrating that our method is an effective solution for three-dimensional reconstruction. Full article

Multispectral imaging plays a key role in crop monitoring. A major challenge, however, is spectral band misalignment, which can hinder accurate plant health assessment by distorting the calculation of vegetation indices. This study presents a novel approach for short-range calibration of a multispectral camera, utilizing stereo vision for precise geometric correction of acquired images. By using multispectral camera lenses as binocular pairs, the sensor acquisition distance was estimated, and an alignment model was developed for distances ranging from 500 mm to 1500 mm. The approach relied on selecting the red band image as a reference, while the remaining bands were treated as moving images. The stereo camera calibration algorithm estimated the target distance, enabling the correction of band misalignment through previously developed models. The alignment models were applied to assess the health status of baby leaf crops (Lactuca sativa cv. Maverik) by analyzing spectral indices correlated with chlorophyll content. The results showed that the stereo vision approach used for distance estimation achieved high accuracy, with average reprojection errors of approximately 0.013 pixels (4.485 × 10⁻⁵ mm). Additionally, the proposed linear model was able to explain reasonably the effect of distance on alignment offsets. The overall performance of the proposed experimental alignment models was satisfactory, with offset errors on the bands less than 3 pixels. Despite the results being not yet sufficiently robust for a fully predictive model of chlorophyll content in plants, the analysis of vegetation indices demonstrated a clear distinction between healthy and unhealthy plants. Full article

Accurate estimates of forest aboveground biomass (AGB) are necessary for the accurate tracking of forest carbon stock. Gaofen-7 (GF-7) is the first civilian sub-meter three-dimensional (3D) mapping satellite from China. It is equipped with a laser altimeter system and a dual-line array stereoscopic mapping camera, which enables it to synchronously generate full-waveform LiDAR data and stereoscopic images. The bulk of existing research has examined how accurate GF-7 is for topographic measurements of bare land or canopy height. The measurement of forest aboveground biomass has not received as much attention as it deserves. This study aimed to assess the GF-7 stereo imaging capability, displayed as topographic features for aboveground biomass estimation in forests. The aboveground biomass model was constructed using the random forest machine learning technique, which was accomplished by combining the use of in situ field measurements, pairs of GF-7 stereo images, and the corresponding generated canopy height model (CHM). Findings showed that the biomass estimation model had an accuracy of R² = 0.76, RMSE = 7.94 t/ha, which was better than the inclusion of forest canopy height (R² = 0.30, RMSE = 21.02 t/ha). These results show that GF-7 has considerable application potential in gathering large-scale high-precision forest aboveground biomass using a restricted amount of field data. Full article

The creation of digital surface models (DSMs) from aerial and satellite imagery is often the starting point for different remote sensing applications. For this task, the two main used approaches are stereo matching and multi-view stereo (MVS). The former needs stereo-rectified pairs as inputs and the results are in the disparity domain. The latter works with images from various perspectives and produces a result in the depth domain. So far, both approaches have proven to be successful in producing accurate DSMs, especially in the deep learning area. Nonetheless, an assessment between the two is difficult due to the differences in the input data, the domain where the directly generated results are provided and the evaluation metrics. In this manuscript, we processed synthetic and real optical data to be compatible with the stereo and MVS algorithms. Such data is then applied to learning-based algorithms in both analyzed solutions. We focus on an experimental setting trying to establish a comparison between the algorithms as fair as possible. In particular, we looked at urban areas with high object densities and sharp boundaries, which pose challenges such as occlusions and depth discontinuities. Results show in general a good performance for all experiments, with specific differences in the reconstructed objects. We describe qualitatively and quantitatively the performance of the compared cases. Moreover, we consider an additional case to fuse the results into a DSM utilizing confidence estimation, showing a further improvement and opening up a possibility for further research. Full article

This paper presents a robust point cloud registration method based on a multi-scale covariance matrix descriptor and an accurate transformation estimation. Compared with state-of-the-art feature descriptors, such as FPH, 3DSC, spin image, etc., our proposed multi-scale covariance matrix descriptor is superior for dealing with registration problems in a higher noise environment since the mean operation in generating the covariance matrix can filter out most of the noise-damaged samples or outliers and also make itself robust to noise. Compared with transformation estimation, such as feature matching, clustering, ICP, RANSAC, etc., our transformation estimation is able to find a better optimal transformation between a pair of point clouds since our transformation estimation is a multi-level point cloud transformation estimator including feature matching, coarse transformation estimation based on clustering, and a fine transformation estimation based on ICP. Experiment findings reveal that our proposed feature descriptor and transformation estimation outperforms state-of-the-art feature descriptors and transformation estimation, and registration effectiveness based on our registration framework of point cloud is extremely successful in the Stanford 3D Scanning Repository, the SpaceTime dataset, and the Kinect dataset, where the Stanford 3D Scanning Repository is known for its comprehensive collection of high-quality 3D scans, and the SpaceTime dataset and the Kinect dataset are captured by a SpaceTime Stereo scanner and a low-cost Microsoft Kinect scanner, respectively. Full article