Search Results (9,392)

This paper proposes an enhanced visual simultaneous localization and mapping (vSLAM) algorithm tailored for mobile robots operating in indoor dynamic scenes. By incorporating point-line features and leveraging the Manhattan world model, the proposed PLM-SLAM framework significantly improves localization accuracy and map consistency. This algorithm optimizes the line features detected by the Line Segment Detector (LSD) through merging and pruning strategies, ensuring real-time performance. Subsequently, dynamic point-line features are rejected based on Lucas–Kanade (LK) optical flow, geometric constraints, and depth information, minimizing the impact of dynamic objects. The Manhattan world model is then utilized to reduce rotational estimation errors and optimize pose estimation. High-precision line feature matching and loop closure detection mechanisms further enhance the robustness and accuracy of the system. Experimental results demonstrate the superior performance of PLM-SLAM, particularly in high-dynamic indoor environments, outperforming existing state-of-the-art methods. Full article

The health, safety, and well-being of household pets such as cats has become a challenging task in previous years. To estimate a cat’s behavior, objective observations of both the frequency and variability of specific behavior traits are required, which might be difficult to come by in a cat’s ordinary life. There is very little research on cat activity and cat disease analysis based on real-time data. Although previous studies have made progress, several key questions still need addressing: What types of data are best suited for accurately detecting activity patterns? Where should sensors be strategically placed to ensure precise data collection, and how can the system be effectively automated for seamless operation? This study addresses these questions by pointing out whether the cat should be equipped with a sensor, and how the activity detection system can be automated. Magnetic, motion, vision, audio, and location sensors are among the sensors used in the machine learning experiment. In this study, we collect data using three types of differentiable and realistic wearable sensors, namely, an accelerometer, a gyroscope, and a magnetometer. Therefore, this study aims to employ cat activity detection techniques to combine data from acceleration, motion, and magnetic sensors, such as accelerometers, gyroscopes, and magnetometers, respectively, to recognize routine cat activity. Data collecting, data processing, data fusion, and artificial intelligence approaches are all part of the system established in this study. We focus on One-Dimensional Convolutional Neural Networks (1D-CNNs) in our research, to recognize cat activity modeling for detection and classification. Such 1D-CNNs have recently emerged as a cutting-edge approach for signal processing-based systems such as sensor-based pet and human health monitoring systems, anomaly identification in manufacturing, and in other areas. Our study culminates in the development of an automated system for robust pet (cat) activity analysis using artificial intelligence techniques, featuring a 1D-CNN-based approach. In this experimental research, the 1D-CNN approach is evaluated using training and validation sets. The approach achieved a satisfactory accuracy of 98.9% while detecting the activity useful for cat well-being. Full article

Understanding the factors influencing the variability in the composition of fish assemblages is essential for bolstering the resilience of coral reef ecosystems, effective coral reef management and maintaining sustainable fisheries. The benthic composition and reef fish assemblages at eight sites at the poorly studied St. Brandon, also known as a bank fisheries area in the Indian Ocean, were assessed to discern distribution patterns, including differences between channel (Passe Grand Capitaine, Passe Ile Longue-Canal Coco and Passe La Cayane) and non-channel (Chaloupe, Anchor Points 1 and 2, Bain des Dames, Pearl Island) sites and fisheries sustainability. The benthic composition exhibited clusters, revealing the distinct separation of Chaloupe which predominantly featured sand (75.26%) interspersed with sporadic coral patches characterized by live and dead corals and rubble. The three channel sites composed a cluster. Coral species across eight families were identified, with significant variability (p < 0.05) observed in their benthic cover, particularly live coral cover (LCC). Fish density and diversity analyses unveiled 58 fish species from 12 families, with no statistically significant disparity in density among sites. Total fish biomass (TFB) and target fish biomass (TB) ranged from 138.02 ± 65.04 to 4110.16 ± 3048.70 kg/ha and from 28.31 ± 24.52 to 3851.27 ± 2753.18 kg/ha, respectively. TFB and TB differed significantly (p < 0.05) among sites irrespective of channel and non-channel sites, with Pearl Island recording the highest biomass. TFB and TB recorded at five out of the eight surveyed sites exceeded the mean biomass benchmark (B₀) for the Western Indian Ocean, set at 1150.00 and 560.00 kg/ha for TFB and TB, respectively. Functional group analysis unveiled six discrete groups influencing TFB, with scrapers being the most dominant. This study presents the first report on fish biomass surveys in St. Brandon, highlighting a case for sustainable fisheries in the waters of the Republic of Mauritius. Full article

To optimize rice yield and enhance quality through targeted field management at each growth stage, rapid and accurate identification of rice growth stages is crucial. This study presents the Mobilenetv3-YOLOv8 rice growth-stage recognition model, designed for high efficiency and accuracy using Unmanned Aerial Vehicle (UAV) imagery. A UAV captured images of rice fields across five distinct growth stages from two altitudes (3 m and 20 m) across two independent field experiments. These images were processed to create training, validation, and test datasets for model development. Mobilenetv3 was introduced to replace the standard YOLOv8 backbone, providing robust small-scale feature extraction through multi-scale feature fusion. Additionally, the Coordinate Attention (CA) mechanism was integrated into YOLOv8’s backbone, outperforming the Convolutional Block Attention Module (CBAM) by enhancing position-sensitive information capture and focusing on crucial pixel areas. Compared to the original YOLOv8, the enhanced Mobilenetv3-YOLOv8 model improved rice growth-stage identification accuracy and reduced the computational load. With an input image size of 400 × 400 pixels and the CA implemented in the second and third backbone layers, the model achieved its best performance, reaching 84.00% mAP and 84.08% recall. The optimized model achieved parameters and Giga Floating Point Operations (GFLOPs) of 6.60M and 0.9, respectively, with precision values for tillering, jointing, booting, heading, and filling stages of 94.88%, 93.36%, 67.85%, 78.31%, and 85.46%, respectively. The experimental results revealed that the optimal Mobilenetv3-YOLOv8 shows excellent performance and has potential for deployment in edge computing devices and practical applications for in-field rice growth-stage recognition in the future. Full article

Human activity recognition (HAR) technology is related to human safety and convenience, making it crucial for it to infer human activity accurately. Furthermore, it must consume low power at all times when detecting human activity and be inexpensive to operate. For this purpose, a low-power and lightweight design of the HAR system is essential. In this paper, we propose a low-power and lightweight HAR system using point-cloud data collected by radar. The proposed HAR system uses a pillar feature encoder that converts 3D point-cloud data into a 2D image and a classification network based on depth-wise separable convolution for lightweighting. The proposed classification network achieved an accuracy of 95.54%, with 25.77 M multiply–accumulate operations and 22.28 K network parameters implemented in a 32 bit floating-point format. This network achieved 94.79% accuracy with 4 bit quantization, which reduced memory usage to 12.5% compared to existing 32 bit format networks. In addition, we implemented a lightweight HAR system optimized for low-power design on a heterogeneous computing platform, a Zynq UltraScale+ ZCU104 device, through hardware–software implementation. It took 2.43 ms of execution time to perform one frame of HAR on the device and the system consumed 3.479 W of power when running. Full article

General face recognition is currently one of the key technologies in the field of computer vision, and it has achieved tremendous success with the support of deep-learning technology. General face recognition models currently exhibit extremely high accuracy on some high-quality face datasets. However, their performance decreases in challenging environments, such as low-light scenes. To enhance the performance of face recognition models in low-light scenarios, we propose a face recognition approach based on feature decoupling and fusion (DeFFace). Our main idea is to extract facial-related features from images that are not influenced by illumination. First, we introduce a feature decoupling network (D-Net) to decouple the image into facial-related features and illumination-related features. By incorporating the illumination triplet loss optimized with unpaired identity IDs, we regulate illumination-related features to minimize the impact of lighting conditions on the face recognition system. However, the decoupled features are relatively coarse. Therefore, we introduce a feature fusion network (F-Net) to further extract the residual facial-related features from the illumination-related features and fuse them with the initial facial-related features. Finally, we introduce a lighting-facial correlation loss to reduce the correlation between the two decoupled features in the specific space. We demonstrate the effectiveness of our method on four real-world low-light datasets and three simulated low-light datasets. We retrain multiple general face recognition methods using our proposed low-light training sets to further validate the advanced performance of our method. Compared to general face recognition methods, our approach achieves an average improvement of more than 2.11 percentage points on low-light face datasets. In comparison with image enhancement-based solutions, our method shows an average improvement of around 16 percentage points on low-light datasets, and it also delivers an average improvement of approximately 5.67 percentage points when compared to illumination normalization-based methods. Full article

The increasing adoption of 2D/3D laser line sensors in industrial and research applications necessitates accurate and efficient simulation tools for tasks such as surface inspection, dimensional verification, and quality control. This paper presents a novel algorithm developed in MATLAB for simulating the measurements of any 2D/3D laser line sensor on STL CAD models. The algorithm uses a modified fast-ray triangular intersection method, addressing challenges such as overlapping triangles in assembly models and incorporating sensor resolution to ensure realistic simulations. Quantitative analysis shows a significant reduction in computation time, enhancing the practical utility of the algorithm. The simulation results exhibit a mean deviation of 0.42 mm when compared to real-world measurements. Notably, the algorithm effectively handles complex geometric features, such as holes and grooves, and offers flexibility in generating point cloud data in both local and global coordinate systems. This work not only reduces the need for physical prototyping, thereby contributing to sustainability, but also supports AI training by generating accurate synthetic data. Future work should aim to further optimize the simulation speed and explore noise modeling to enhance the realism of simulated measurements. Full article

Using digital twin models of tunnels has become critical to their efficient maintenance and management. A high-precision 3D tunnel model is the prerequisite for a successful digital twin model of tunnel applications. However, constructing high-precision 3D tunnel models with high-quality textures and structural integrity based on mobile laser scanning data remains a challenge, particularly for tunnels of different shapes. This study addresses this problem by developing a novel method for the 3D reconstruction of multi-shaped tunnels based on mobile laser scanning data. This method does not require any predefined mathematical models or projection parameters to convert point clouds into 2D intensity images that conform to the geometric features of tunnel linings. This method also improves the accuracy of 3D tunnel mesh models by applying an adaptive threshold approach that reduces the number of pseudo-surfaces generated during the Poisson surface reconstruction of tunnels. This method was experimentally verified by conducting 3D reconstruction tasks involving tunnel point clouds of four different shapes. The superiority of this method was further confirmed through qualitative and quantitative comparisons with related approaches. By automatically and efficiently constructing a high-precision 3D tunnel model, the proposed method offers an important model foundation for digital twin engineering and a valuable reference for future tunnel model construction projects. Full article

To improve the accuracy of detecting small and long-distance objects while self-driving cars are in motion, in this paper, we propose a 3D object detection method, Att-BEVFusion, which fuses camera and LiDAR data in a bird’s-eye view (BEV). First, the transformation from the camera view to the BEV space is achieved through an implicit supervision-based method, and then the LiDAR BEV feature point cloud is voxelized and converted into BEV features. Then, a channel attention mechanism is introduced to design a BEV feature fusion network to realize the fusion of camera BEV feature space and LiDAR BEV feature space. Finally, regarding the issue of insufficient global reasoning in the BEV fusion features generated by the channel attention mechanism, as well as the challenge of inadequate interaction between features. We further develop a BEV self-attention mechanism to apply global operations on the features. This paper evaluates the effectiveness of the Att-BEVFusion fusion algorithm on the nuScenes dataset, and the results demonstrate that the algorithm achieved 72.0% mean average precision (mAP) and 74.3% nuScenes detection score (NDS), with an advanced detection accuracy of 88.9% and 91.8% for single-item detection of automotive and pedestrian categories, respectively. Full article

To address the challenge of rapid geometric model development in the digital twin industry, this paper presents a comprehensive pipeline for constructing 3D models from images using monocular vision imaging principles. Firstly, a structure-from-motion (SFM) algorithm generates a 3D point cloud from photographs. The feature detection methods scale-invariant feature transform (SIFT), speeded-up robust features (SURF), and KAZE are compared across six datasets, with SIFT proving the most effective (matching rate higher than 0.12). Using K-nearest-neighbor matching and random sample consensus (RANSAC), refined feature point matching and 3D spatial representation are achieved via antipodal geometry. Then, the Poisson surface reconstruction algorithm converts the point cloud into a mesh model. Additionally, texture images are enhanced by leveraging a visual geometry group (VGG) network-based deep learning approach. Content images from a dataset provide geometric contours via higher-level VGG layers, while textures from style images are extracted using the lower-level layers. These are fused to create texture-transferred images, where the image quality assessment (IQA) metrics SSIM and PSNR are used to evaluate texture-enhanced images. Finally, texture mapping integrates the enhanced textures with the mesh model, improving the scene representation with enhanced texture. The method presented in this paper surpassed a LiDAR-based reconstruction approach by $20\%$ in terms of point cloud density and number of model facets, while the hardware cost was only $1\%$ of that associated with LiDAR. Full article

Dense three-dimensional point clouds are the cornerstone of modern architectural 3D reconstruction, containing a wealth of semantic structural information about building facades. However, current methods struggle to automatically and accurately extract the complex detailed structures of building facades from unstructured point clouds, with detailed facade modeling often relying heavily on manual interaction. This study introduces an efficient method for semantic structural detail enhancement of building facade point clouds, achieved through feature-guided dual-layer optimization of position and shape. The proposed framework addresses three key challenges: (1) robust extraction of facade semantic feature point clouds to effectively perceive the underlying geometric features of facade structures; (2) improved grouping of similarly structured objects using Hausdorff distance discrimination, overcoming the impact of point cloud omissions and granularity differences; (3) position-shape double optimization for facade enhancement, achieving detailed structural optimization. Validated on three typical datasets, the proposed method not only achieved 98.5% accuracy but also effectively supplemented incomplete scan results. It effectively optimizes semantic structures that widely exist and have the characteristic of repeated appearance on building facades, providing robust support for smart city construction and analytical applications. Full article

Background: This multicenter and retrospective study investigated the additive value of tumor morphologic features derived from the functional tumor volume (FTV) tumor mask at pre-treatment (T0) and the early treatment time point (T1) in the prediction of pathologic outcomes for breast cancer patients undergoing neoadjuvant chemotherapy. Methods: A total of 910 patients enrolled in the multicenter I-SPY 2 trial were included. FTV and tumor morphologic features were calculated from the dynamic contrast-enhanced (DCE) MRI. A poor response was defined as a residual cancer burden (RCB) class III (RCB-III) at surgical excision. The area under the receiver operating characteristic curve (AUC) was used to evaluate the predictive performance. The analysis was performed in the full cohort and in individual sub-cohorts stratified by hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) status. Results: In the full cohort, the AUCs for the use of the FTV ratio and clinicopathologic data were 0.64 ± 0.03 (mean ± SD [standard deviation]). With morphologic features, the AUC increased significantly to 0.76 ± 0.04 (p < 0.001). The ratio of the surface area to volume ratio between T0 and T1 was found to be the most contributing feature. All top contributing features were from T1. An improvement was also observed in the HR+/HER2- and triple-negative sub-cohorts. The AUC increased significantly from 0.56 ± 0.05 to 0.70 ± 0.06 (p < 0.001) and from 0.65 ± 0.06 to 0.73 ± 0.06 (p < 0.001), respectively, when adding morphologic features. Conclusion: Tumor morphologic features can improve the prediction of RCB-III compared to using FTV only at the early treatment time point. Full article

This work presents a novel RGB-D dynamic simultaneous localization and mapping (SLAM) method that improves accuracy, stability, and efficiency of localization while relying on deep learning in a dynamic environment, in contrast to traditional static scene-based visual SLAM methods. Based on the classic framework of traditional visual SLAM, we propose a method that replaces the traditional feature extraction method with a convolutional neural network approach, aiming to enhance the accuracy of feature extraction and localization, as well as to improve the algorithm’s ability to capture and represent the characteristics of the entire scene. Subsequently, the semantic segmentation thread was utilized in a target detection network combined with geometric methods to identify potential dynamic areas in the image and generate masks for dynamic objects. Finally, the standard deviation of the depth information of potential dynamic points was calculated to identify true dynamic feature points, to guarantee that static feature points were used for position estimation. We performed experiments based on the public datasets to validate the feasibility of the proposed algorithm. The experimental results indicate that the improved SLAM algorithm, which boasts a reduction in absolute trajectory error (ATE) by approximately 97% compared to traditional static visual SLAM and about 20% compared to traditional dynamic visual SLAM, also exhibited a 68% decrease in computation time compared to well-known dynamic visual SLAM, thereby possessing absolute advantages in both positioning accuracy and operational efficiency. Full article

Three-dimensional (3D) applications lead the digital transition toward more immersive and interactive multimedia technologies. Point clouds (PCs) are a fundamental element in capturing and rendering 3D digital environments, but they present significant challenges due to the large amount of data typically needed to represent them. Although PC compression techniques can reduce the size of PCs, they introduce degradations that can negatively impact the PC’s quality and therefore the object representation’s accuracy. This trade-off between data size and PC quality highlights the critical importance of PC quality assessment (PCQA) techniques. In this article, we review the state-of-the-art no-reference (NR) objective quality metrics for PCs, which can accurately estimate the quality of generated and compressed PCs solely based on feature information extracted from the distorted PC. These characteristics make NR PCQA metrics particularly suitable in real-world application scenarios where the original PC data are unavailable for comparison, such as in streaming applications. Full article

A submerged elevation located off the coast of Le Castella, a small village on the Ionian Coast of Calabria (Italy) populated for thousands of years that features notable archaeological remains from the Great Greece (Magna Graecia) and the Middle Ages, was investigated through in-depth, multidisciplinary, geoarchaeological research. This submarine elevation, once aligned with the marine terrace MIS 3 of Le Castella and still completely emerged between 10 and 8 ka years ago, slowly sank due to erosion and local tectonic-structural subsidence and was also favoured by a submerged normal fault that cuts the terrace in two. The dismantling and sinking of this part of the marine terrace has significantly changed the Late Holocene shorelines, with notable consequences on a topographic and archaeological level. In fact, one of the consequences of the sinking of this ancient promontory was the disappearance of two small islands that were reported to be right in front of Le Castella by numerous historical and cartographic sources. In the last decades, there has been a scientific debate over the existence of these islets, but no convincing evidence has been found about their actual presence up until now. This research, funded by the Marine Protected Area “Capo Rizzuto”, was conducted by means of underwater archaeological and geological surveys, geophysical seabed mapping systems, and both direct and instrumental optical surveys made with an Autonomous Surface Vehicle. The outcomes allow us to confirm the presence of these two partially emerged rock bodies up to half a millennium ago. In addition, the presence of anthropogenic extrabasinal materials in a marine area corresponding to one of the highest points of the submerged elevation allows us to define the exact position of one of the two islets. These archaeological findings have been subject, for the first time ever, to a thorough topographical and architectural analysis, then compared with other near and very similar submerged structures. On the basis of these comparisons, the findings should be attributed to the Byzantine Age or, at most, to the Middle Ages. In-depth archival research on portolan charts and navigation maps, in many cases unpublished and dating from the Middle Ages to the early 18th century, supports the results of our marine investigations from a historical point of view. Full article