Accurate Mapping Research Articles

Methods for Detection and Mapping of Methylated and Hydroxymethylated Cytosine in DNA.

The chemical modifications of DNA are of pivotal importance in the epigenetic regulation of cellular processes. Although the function of 5-methylcytosine (5mC) has been extensively investigated, the significance of 5-hydroxymethylcytosine (5hmC) has only recently been acknowledged. Conventional methods for the detection of DNA methylation frequently lack the capacity to distinguish between 5mC and 5hmC, resulting in the combined reporting of both. The growing importance of 5hmC has prompted the development of a multitude of methods for the qualitative and quantitative analysis of 5hmC in recent years, thereby facilitating researchers' understanding of the mechanisms underlying the onset and progression of numerous diseases. This review covers both established and novel methods for the detection of cytosine modifications, including 5mC, 5hmC, 5-formylcytosine (5fC) and 5-carboxylcytosine (5caC), with a particular focus on those that allow for accurate mapping and detection, particularly with third-generation sequencing. The review aims to help researchers choose the most appropriate methods based on their specific research goals and budget.

Modified ICP based Framework for 3D Localization and Mapping in GNSS-denied Environments using LiDAR

Abstract. Lidar odometry and mapping has emerged as fundamental technology in various fields, including accurate positioning and mapping, autonomous vehicles, robotics, and environmental monitoring. The ability to create accurate maps and calculate trajectories is essential for localization and navigation in complex environments, particularly in scenarios where GNSS signal are unavailable. In this context, we propose a novel method for simultaneous localization and mapping (SLAM) specifically designed for GNSS-denied environments and without the need for high-accuracy ranging or inertial measurement units (IMUs). Our approach aims to address the challenges posed by GNSS-denied environments and the cost constraints associated with using multiple sensors. By using only lidar sensors, specifically the Velodyne VLP 16 sensor, we offer a cost-effective solution. Our method utilizes a modified version of the Iterative Closest Point (ICP) algorithm to handle consecutive lidar scans seamlessly. In addition to our method, we conducted thorough accuracy assessments on the created map. The reason behind extensive accuracy evaluation is to ensure the quality of registration. By comparing alignment between the features of different frames within the map and determining the error between the registered features and the original, we gain a more comprehensive understanding of registration quality.

A novel autonomous exploration algorithm via LiDAR/IMU SLAM and hierarchical subsystem for mobile robot in unknown indoor environments

Abstract Autonomous exploration in unknown environments is an essential capability for mobile robots. The complexity of autonomous exploration, however, means that existing algorithms struggle to balance efficiency and comprehensiveness, causing low mapping accuracy and redundant path planning. To perform accurate and efficient exploration tasks, we have proposed a novel autonomous exploration algorithm via LiDAR/IMU (Inertial Measurement Unit) Simultaneous Localization and Mapping (SLAM) and hierarchical subsystem for mobile robot in unknown environments. Firstly, to enhance mapping accuracy for mobile robot exploration, LiDAR/IMU SLAM is improved with the assistance of backward propagation and iterated Kalman filter, and Bidirectional Rapidly–Exploring Random Trees* (BI–RRT*) is applied for efficient frontier point detection. Secondly, we optimize local path planning by leveraging information theory through perceptual quality evaluation, which is then integrated with global path planning utilizing an enhanced Travelling Salesman Problem solver and a sparse grid map to amplify exploration efficiency. Thirdly, an enhanced hierarchical autonomous exploration method for mobile robots is proposed, which incorporates local path planning for seamless navigation around highly promising exploration spots, coupled with global path planning to effectively interconnect various sub–regions. Finally, simulations and field tests have demonstrated that the proposed method explores an unknown indoor environment with a 30.8% reduction in exploration time and a 29.9% reduction in exploration path in comparison with Dynamic Stage Viewpoint Planner. The map constructed in this paper has more accurate details and exploration paths have been shortened to ensure effective exploration.

Spatial Analysis of Land Use Land Cover Dynamics in the Madurai District Using Sentinel-2 Data and Supervised Learning Algorithms

Abstract. LULC, or Land Use and Land Cover, refers to the classification and description of different types of land and its usage patterns, including urban areas, forests, agricultural land, etc. In remote sensing, satellite imagery for LULC mapping is becoming more widespread. Numerous studies examine various approaches to improve mapping efficiency and accuracy, highlighting the significance of various data sources, machine learning algorithms, and categorization techniques. This study employs machine learning classifiers, namely Random Forest (RF), Support Vector Machine (SVM), Gradient Boosted Trees (GTB), Classification and Regression Trees (CART), and K-Nearest Neighbors (KNN) for land use and land cover (LULC) classification of Madurai district utilizing Google Earth Engine. The findings reveal the impressive performance of Random Forest, boasting an overall accuracy of 99.01 percent coupled with a commendable Kappa coefficient of 98.68. Conversely. However, amidst these commendable achievements, it’s noteworthy to highlight the nuanced variations observed between the accuracy of training and validation sets. This discrepancy is attributed to the intrinsic intricacies of the learning processes inherent within the algorithms, underscoring the nuanced nature of algorithmic methodologies and their implications on accuracy assessment within spatial analysis frameworks. The generated land use and land cover (LULC) map allows for a comparison between the ground truth data and the surveys conducted to assess issues such as water scarcity and the drying of natural and man-made water bodies.

Robust and accurate visual geo-localization using prior map constructed by handheld LiDAR SLAM with camera image and terrestrial LiDAR point cloud

ABSTRACT Visual geo-localization using prior map of known environments has extensive applications in the fields such as self-driving, augmented reality and navigation. Currently, such prior maps are usually constructed by visual SLAM or SFM. However, the recent advances in LiDAR SLAM technology with RGB camera demonstrate great potential in efficient and accurate prior map construction and visual geo-localization. In this research, we developed a novel prior map construction approach which seamlessly integrates a handheld LiDAR SLAM system, a global LiDAR localization algorithm and a sparse set of terrestrial LiDAR scans as accurate control within a factor graph optimization framework. The developed LiDAR SLAM system augmented by terrestrial LiDAR scans achieves an improved mapping accuracy of 8 cm under GNSS-denied conditions in the areas over 50,000 m2 while the state-of-art FAST-LIO2 alone fails and produces a mapping error over 30 m. The results show that a competitive accuracy of visual geo-localization on a mobile phone using the constructed prior map is achieved (i.e. 60 and 76 cm in two tests respectively). Finally, this work also demonstrates a novel LiDAR point cloud fusion method that produces optimized and consistent coarse-to-fine 3D reconstruction in large and complex scenes.

Proposal of UAV-SLAM-Based 3D Point Cloud Map Generation Method for Orchards Measurements

This paper proposes a method for generating highly accurate point cloud maps of orchards using an unmanned aerial vehicle (UAV) equipped with light detection and ranging (LiDAR). The point cloud captured by the UAV-LiDAR was converted to a geographic coordinate system using a global navigation satellite system / inertial measurement unit (GNSS/IMU). The converted point cloud is then aligned with the simultaneous localization and mapping (SLAM) technique. As a result, a 3D model of an orchard is generated in a low-cost and easy-to-use manner for pesticide application with precision. The method of direct point cloud alignment with real-time kinematic-global navigation satellite system (RTK-GNSS) had a root mean square error (RMSE) of 42 cm between the predicted and true crop height values, primarily due to the effects of GNSS multipath and vibration of automated vehicles. Contrastingly, our method demonstrated better results, with RMSE of 5.43 cm and 2.14 cm in the vertical and horizontal axes, respectively. The proposed method for predicting crop location successfully achieved the required accuracy of less than 1 m with errors not exceeding 30 cm in the geographic coordinate system.

High-resolution population mapping based on SDGSAT-1 glimmer imagery and deep learning: a case study of the Guangdong-Hong Kong-Marco Greater Bay Area

ABSTRACT Accurate population mapping is crucial for disaster management, urban planning, etc. However, current methods using nighttime light (NTL) and gridded population datasets are limited by low spatial resolution and insufficient training data for complex models such as deep learning. These models do not adequately utilize spatial information in population mapping. To address these limitations, this study proposes a high-resolution population mapping method using the Sustainable Development Goals Science Satellite 1 (SDGSAT-1) glimmer imager data and deep learning. The method includes a sample generation strategy with multiple regression and multilevel screening to provide sufficient, high-quality samples for deep learning. A Fine Population mapping network (FinePop-net) is also developed to train regression models using image samples, capturing multi-scale features for model training. When applied to the Guangdong-Hong Kong-Macao Greater Bay Area with 40-meter resolution SDGSAT 1 glimmer imagery, the method significantly reduced the average absolute error and root-mean-square error by 9.35% and 11.44%, respectively, compared with those of the pixel-level learning methods. It also outperformed other population spatialization datasets and NTL data by over 30% and 10%, respectively, in terms of error reduction. The results highlight the method’s effectiveness and the value of SDGSAT-1 glimmer imagery for fine population spatialization.

Automatic Detection of Flood Extent and Volume Estimation from Sentinel-2 Satellite Images using Deep Learning Techniques in India

Floods are unexpected natural disasters that can have a major impact on human life, soil along bank erosion, damage vital infrastructure, road closures, economy standard, and society of various affected regions. An initial step of proper assessment is necessary for flood damage along with accurate measurements to easily restore essential damage of infrastructure, relief, and mitigation as quickly as possible. Nowadays, the rapid development of remote sensing images using deep learning as a most positive tool for accurately estimating the extent of overall flood detection surfaces. The monitoring of flood detections from remote sensing images still extends a few issues due to mostly varying from different weather changes conditions, cloud coverage areas that can have a limit to use of level of visible remote sensing satellite collected data. Moreover, Remote Sensing Satellite based observations may not always be mapped to the distribution's flood point peak, also it is very essential for both the flood extent and flood volume estimation. To overcome this challenge, we have presented a new remote sensing technology that integrates with a high resolution multi-spectral satellite data/information by using an advanced Deep Learning to accurately analyze remote sensing based observations. In our experiment, we use the European Space Agency (ESA) launched Sentinel type-1, Sentinel type-2 data and Digital Elevation Model (DEM) to accurately measure flood monitoring results. In our study, we reviewed a real example of the flood situation that happened in 2019 in Kolhapur. In our results, we evaluated a flood volume estimation at 0.0010 km3 in Kolhapur district. Finally, the proposed methodology provides an effective way to accurately motoring floods using low-cost satellite data and deep learning approaches. This project has the potential to improve the more accurate flood detection and mapping which can prevent an exactly timely response and immediate recovery efforts for flood surrounding affected areas.

The Nexus between Land Use/Cover changes and Land Surface Temperature: Remote sensing based Two-Decadal Analysis

The use of Remote Sensing (RS) data is crucial for promptly detecting and monitoring changes in both short and long term, providing real time information on Land Use/Cover (LULC), Land Surface Temperature (LST), and Enhanced Vegetation Index (EVI), adapting spatio-temporal variations. The primary focus of this study is to assess the effect of LULC changes on LST in Tashk-Bakhtegan and Maharloo (TBM) lakes basin, Iran, within 2001, 2011, and 2021, using MODIS data. Specifically, five main LULC classes involving: water body, rangeland, cropland, urban area, and bareland were identified. Beside accuracy and transition of LULC maps using User Accuracy (UA), Producer Accuracy (PA), and Kappa Coefficient (KC), the analysis included changes in LULC, Enhanced Vegetation Index (EVI), and LST, as well as the relationship among them when vegetation cover was at its peak. Moreover, a one-way analysis of variance (ANOVA) test was performed to group these variables using Duncan's test. The results showed that the accuracy of LULC maps were more than 84% for all the years. Furthermore, the conversion of croplands to rangelands showed the most significant changes, with a total of 1311.38 km2 during 2001–2021. Average EVI remained almost stable across the total area, whereas average LST generally increased by 0.65 °C. Barelands consistently exhibited the highest temperatures in all the years, followed by urban areas. While no significant changes were observed in the EVI averages, significant changes were observed in the LST across all LULC classes in different years. The results also indicated a consistent negative correlation between LST and EVI, stronger in croplands than rangelands, with Spearman's correlation coefficient of −0.714, −0.674, and −0.623 over the total area in 2001, 2011, and 2021, respectively. The findings are crucial for land planners to comprehend the effects of LULC changes on LST to adopt appropriate strategies in the TBM lakes basin.

Fast stability enhancement of inverter‐based microgrids using NGO‐LSTM algorithm

AbstractTo improve the stability of the inverter‐based microgrid (MG), this paper employs a novel data‐driven based method to coordinately adjust control parameters of inverters in a fast local manner. During the design process, an offline eigenvalue based optimization problem that is used to calculate the optimal control parameters under various operating conditions is first constructed. In order to reduce reliance on full system information, a feature selection algorithm is utilized to extract the most relevant local measurements that influence the adjustment of each control parameter. Then, regarding local measurements as input variables and optimal control parameters as output variables, based on northern goshawk optimization (NGO) and long short‐term memory (LSTM) network, a novel deep learning algorithm is proposed to train the local parameter adjustment model (LPAM) by learning the mapping relationship between them. During the application, to guarantee the stability of MG all the time, a security region based shielding mechanism is developed, where the improper control parameter adjustment will be replaced by a safe one. The case study indicates that the proposed algorithm has better mapping accuracy than traditional LSTM neural networks and also faster calculation speed than the traditional offline optimization‐based method. The effectiveness and advantages of the proposed method are demonstrated in a modified 9‐bus MG.

Assessing critical flood-prone districts and optimal shelter zones in the Brahmaputra Valley: Strategies for effective flood risk management

Frequent flooding has become a persistent issue in floodplain regions, causing significant disasters during each rainy season due to insufficient disaster management planning. This study proposes a methodology to prioritize flood susceptibility areas at the district level and identify suitable sites for flood shelters using a combination of machine learning algorithms and multi-criteria analysis, supported by geospatial technology. Flood shelter suitability mapping was conducted using the Analytical Hierarchy Process (AHP), while flood susceptibility zones were assessed using four different machine learning models: Support Vector Machine (SVM), Random Forest, Decision Tree, and Naive Bayes. The integration of machine learning models with the AHP technique is vital in situations where conventional numerical models face challenges due to limited data, such as river discharge and water levels. The methodology includes a multicollinearity assessment to ensure the independence of selected flood-causing factors, information gain ratio to identify the most influential factors, Spearman's rho test to verify correlations between the machine learning models, and ROC-AUC along with statistical regression for validating the accuracy of the flood susceptibility maps. The findings indicate that the SVM algorithm, given its strong performance and effective training datasets, is recommended for areas with similar physical characteristics. The district-wise priority map generated from the weighted results of flood susceptibility assessments will be useful for flood management and mitigation strategies. Additionally, the study found that applying the AHP technique to determine flood shelter suitability, after assessing flood-prone areas, enhanced the efficiency of the flood management process. This research offers valuable insights for authorities to better address flooding and improve flood prevention and management efforts in floodplain regions, contributing to broader climate change adaptation strategies.

Forest Change Mapping using Multi-Source Satellite SAR, Optical, and LiDAR Remote Sensing Data

Abstract. This study highlights the efficacy of leveraging multi-source satellite remote sensing for precise and dependable forest change mapping. Forests play a crucial role as carbon reservoirs and are indispensable components of the global carbon and water cycle, providing essential ecosystem services. Despite their significance, forests face deforestation, diseases, and climate change threats. Recent satellite remote sensing technology advancements have facilitated accurate, persistent, and large-scale forest dynamics monitoring. New generation satellite LiDAR systems, such as GEDI and ICESat-2, offer frequent and global height information at high spatial resolutions. This research presents a processing framework for mapping forest changes by integrating SAR and optical features from Sentinel-1 and Sentinel-2 imagery with canopy heights derived from GEDI and ICESat-2 datasets. Multiple experiments and analyses were conducted in two study areas. The findings underscore the significant impact of incorporating canopy height information in enhancing the accuracy of forest change mapping, resulting in a 15% improvement in precision and a 13% enhancement in F1-score in the experimental setups. Furthermore, the developed model exhibits increased reliability and confidence in identifying correctly changed and unchanged areas while being less confident in incorrect predictions.

Estimation of above-ground biomass in dry temperate forests using Sentinel-2 data and random forest: a case study of the Swat area of Pakistan

Accurate mapping of above-ground biomass (AGB) is essential for carbon stock quantification and climate change impact assessment, particularly in mountainous areas. This study applies a random forest (RF) regression model to predict the spatial distribution of AGB in Usho (site A) and Utror (site B) forests located in the northern mountainous region of Pakistan. The predicted maps elucidate AGB variations across these sites, with non-forest areas excluded based on an normalized difference vegetation index (NDVI) threshold value of <0.4. Three different combinations of input datasets were used to predict the biomass, including spectral bands (SBs) only, vegetation indexes (VIs) only, and a combination of both spectral bands and vegetation indexes (SBVIs). Utilizing SBs, the biomass ranged between 150 and 286 mg/ha in site A and 99 and 376 mg/ha in site B. Meanwhile, using VIs indicated a biomass range of 163 Mg/ha–337 Mg/ha and 131–392 Mg/ha for sites A and B, respectively. The combination of spectral bands and vegetation indexes yielded AGB values of 145–290 Mg/ha in site A and 116–389 Mg/ha in site B. The northern and western regions of site A, characterized by higher altitudes and lower forest density, notably showed lower biomass values than other regions. Conversely, similar regions in site B, situated at lower latitudes, demonstrated different biomass ranges. The RF model exhibited robust accuracy, with R2 values of 0.74 and 0.83 for spectral bands and vegetation indexes, respectively. However, with a combination of both, an R2 of 0.79 was achieved. Furthermore, altitudinal gradients significantly influence the biomass distribution across both sites, with specific elevation ranges yielding optimal results. The AGB variation along the slope further corroborated these findings. In both sites, the western aspects showed the highest biomass across all combinations of input datasets. The variable importance analysis highlighted that ARVI8a, NDI45, Band12, Band11, TSAVI8, and ARVI8a are significant predictors in sites A and B. This comprehensive analysis enhances our understanding of AGB distribution in the mountainous forests of Pakistan, offering valuable insights for forest management and ecological studies.

Unsupervised Bushfire Burn Severity Mapping Using Aerial and Satellite Imagery

Abstract. It is critical to assess bushfire impact rapidly and accurately because bushfires play a significant role in forest degradation and present a threat to ecosystems and human lives. Over the past decades, several supervised algorithms of burn severity mapping have been proposed, facing the significant drawback of time-consuming labeling. Moreover, there is no robust framework for burn severity mapping through fusing multi-sensor, multi-resolution, and multi-temporal remote sensing imagery from satellite and aerial platforms. Therefore, this paper presents an unsupervised two-step pipeline: processing 2D data followed by 3D data for burn severity mapping, both of which are acquired from either aircraft or satellites. For the 2D data processing, our proposed unsupervised burned area detection (UsBA detection) model enhances burned area mapping accuracy by integrating Ultra-High Resolution (UHR) aerial imagery with bi-temporal medium-resolution PlanetScope imagery, using a Segment Anything Model (SAM)-assisted UNetFormer (pre-trained on the target-style public dataset – LoveDA Rural) for refinement. The model demonstrates superior burned area segmentation, evidenced by improved evaluation metrics calculated from labeled test sites. For the 3D analysis, the burned areas extracted from 2D processing are further assessed using pre- and post-event airborne laser data. We implement a voxel-based workflow, including necessary steps such as ground filtering through Superpoints in RANSAC Planes (SiRP) method and biomass change analysis. The results indicate that the 3D branch provides a reliable lower bound of the actual damage map, because the vegetation growth between two measurements remains, in essence, undetected. The proposed framework offers a more accurate and robust solution for burn severity mapping utilizing combined 2D and 3D data, evaluated on a multi-source dataset from a real bushfire event that occurred in Bushland Park, South Australia.

Visual SLAM system based on dynamic semantic features

Aiming at the problem that dynamic objects (such as pedestrians, vehicles, and animals) in real scenes affect the positioning and mapping accuracy of visual SLAM (Simultaneous Localization and Mapping), a YOLOv3-ORB-SLAM3 algorithm is proposed based on ORB-SLAM3 (Oriented FAST and Rotated BRIEF-Simultaneous Localization and Mapping 3). The algorithm adds a semantic thread on the basis of ORB-SLAM3, and adopts a dual-thread mechanism for dynamic and static scene feature extraction: the semantic thread uses YOLOv3 to perform semantic recognition target detection on dynamic objects in the scene, and removes outliers from the extracted dynamic area feature points; the tracking thread extracts scene area features through ORB features, and obtains static scene features combined with semantic information and sends them to the backend, thereby eliminating the interference of dynamic scenes on the system and improving the positioning accuracy of the visual SLAM algorithm. Verified using the TUM (Technical University of Munich) dataset, the results show that the ATE (Average Treatment Effect) index of the YOLOv3-ORB-SLAM3 algorithm in the monocular mode is about 30% lower than that of the ORB-SLAM3 algorithm, and the ATE index of the dynamic sequence in the RGB-D (Red, Green and Blue-Depth) mode is reduced 10%, while the static sequence has no significant decrease.

Advancing remote sensing: a unified deep learning approach with pretrained and custom architectures for high-precision classification

Advancement of remote sensing is vital for accurate land cover mapping and ecological surveillance. This research proposes a cutting-edge deep learning framework that integrates a meticulously designed customary network architecture with the effectiveness of pre-trained models, namely GoogleNet, VGG16, and InceptionV3. Our approach captures the complex features of RGB satellite images throughout various land cover categories using diverse EuroSAT datasets. Our system achieves an impressive 99.40% test accuracy by implementing feature extraction through effective models with a customized deep learning network in an intuitive manner. High class-wise accuracies are observed, ranging from 96.00% to 100.00%, whereas F1-scores, precision, and recall all converge at 99.40%. The aforementioned results demonstrate our approach’s perspective to significantly improve analysis while also confirming its superiority. These results not only confirm the performance of our algorithm but also show that it could be used to redesign satellite visual analysis behavior. These results open the window to further improve and accurate remote sensing systems, giving a helpful viewpoint for researchers as well as professionals.

Accuracy Assessment of NOAA IMS 4 km Products on the Tibetan Plateau with Landsat-8 OLI Images

The NOAA IMS (Interactive Multisensor Snow and Ice Mapping System) is a blended snow and ice product based on active and passive satellite sensors, ground observation, and other auxiliary information, providing the daily cloud-free snow cover extent in the Northern Hemisphere (NH) and having great application potential in snow cover monitoring and research in the Tibetan Plateau (TP). However, accuracy assessment of products is crucial for various aspects of applications. In this study, Landsat-8 OLI images were used to evaluate and validate the accuracy of IMS products in snow cover monitoring on the TP. The results show that (1) average overall accuracy of IMS 4 km products is 76.0% and average mapping accuracy is 88.3%, indicating that IMS 4 km products are appropriate for large-scale snow cover monitoring on the TP. (2) IMS 4 km products tend to overestimate actual snow cover on the TP, with an average commission rate of 45.4% and omission rate of 11.7%, and generally present that the higher the proportion of snow-covered area, the lower the probability of omission rate and the higher the probability of commission rate. (3) Mapping accuracy of IMS 4 km snow cover on the TP generally is higher at the high altitudes, and commission and omission errors increase with the decrease of elevation. (4) Compared with less regional representativeness of ground observations, the spatial characteristics of snow cover based on high-resolution remote sensing data are much more detailed, and more reliable verification results can be obtained. (5) In addition to commission and omission error metrics, the overall accuracy and mapping accuracy based on the reference image instead of classified image can better reveal the general monitoring accuracy of IMS 4 km products on the TP area.

Improving the accuracy of honey bee forage class mapping using ensemble learning and multi-source satellite data in Google Earth Engine

In semi-arid agro-pastoral environments of Africa, beekeeping is widely recognized as an important activity to improve and diversify livelihoods. Although the scientific identification of suitable honey bees (Apis mellifera ssps.) forages may guide beekeepers to set up apiaries or to timely move honey bee colonies to exploit bee forage resources available in various landscapes, the characterization and mapping of bee forage classes is challenging. We evaluated how various data sources and classification algorithms in Google Earth Engine (GEE) affect the accuracy of honey bee forage class mapping in a semi-arid region of Ethiopia. Predictors derived from multi-source satellite data, such as high-resolution Planet imagery (P), Sentinel 1 RADAR (S1), Sentinel 2 multispectral (S2), and Shuttle Radar Topographic Mission (SRTM) Digital Elevation Model (DEM) were tested and best predictors were identified using Forward Feature Selection (FFS). Four machine learning algorithms (Gradient Tree Boost (GTB), Random Forest (RF), Classification and Regression Trees (CART), and Support Vector Machine (SVM)), all available in GEE, were compared and ensembled for honey bee forage class mapping. The results show that the highest accuracy is obtained by all four algorithms when combining P, S1, S2, and DEM compared to using predictors from a single data source or any other combinations. GTB had higher overall accuracy (90.9 %) than RF (88.2 %), CART (85.5 %), or SVM (79.9 %). Nonetheless, the highest overall accuracy (94.7 %) was obtained when integrating the four machine learning algorithms in an Ensemble Learning Approach (ELA). Applying ELA improved the classification accuracy by 3.8 %, 6.5 %, 9.2 %, and 14.8 % compared to single learner classification algorithms (i.e., GTB, RF, CART, and SVM, respectively). This study demonstrates an improved classification accuracy for honey bee forage class mapping in tropical rangeland by applying ELA, which can provide a better approach for monitoring and managing bee forage resources.

Depth-prior-based range-gated 3D imaging method: integration of optical property into visual learning.

3D Range-gated Imaging (3DRGI) has great potential for long-range detection in adverse weather conditions. Recently, vision-guided 3DRGI has brought new perspectives to this area as it overcomes hardware limitations and greatly increases flexibility. However, existing vision-guided methods do not consider the optical properties of range-gated imaging, which results in low accuracy. This paper proposes a depth-prior-based 3DRGI method to combine the advantages of optical-based and vision-guided methods. In this method, depth-prior is firstly deduced from principles of range-gated imaging and provides effective depth signals. Then, adaptive depth intervals are estimated using statistical methods, and a depth-prior-guided loss function is designed. The integration of the depth-prior-guided loss function within a vision-guided model enables focused attention on pixels with depth estimations that are inconsistent with the depth prior, thereby refining the overall accuracy of the depth map. To prove the feasibility of the proposed method, comparison experiments and ablation studies have been performed. The results show that the root mean square error improved by more than 12% under adverse weather conditions.

A Crowded Object Counting System with Self-Attention Mechanism

Traditional object counting systems use object detection methods to count objects. However, when objects are small, crowded, and dense, object detection may fail, leading to inaccuracies in counting. To address this issue, we propose a crowded object counting system based on density map estimation. While most density map estimation models employ encoder–decoder or multi-branch approaches to generate feature maps at different scales for obtaining an accurate density map, improving the accuracy of crowded object counting remains a challenge. In this paper, we propose a novel model that can generate more accurate density maps, utilizing the context-aware network as the primary structure and integrating the self-attention mechanism. There are three main contributions in this paper. Firstly, the self-attention mechanism is employed to improve the accuracy of density map estimation. Secondly, the missing vehicle labels in the TRANCOS database are relabeled, ensuring that the ground truth data are more complete than the original TRANCOS database, thus enabling the proposed novel model to have higher crowded object counting accuracy. Thirdly, the parameters of the self-attention mechanism are analyzed to obtain the optimum parameter combination. The experimental results demonstrate that the accuracy of crowded object counting can reach 85.9%, 90.0%, 83.4%, and 92.6% for the TRANCOS, relabeled TRANCOS, ShanghaiTech Part A, and Part B datasets, respectively. Furthermore, the ablation study for the context-aware network with self-attention mechanism analyzes the optimum parameter combination.