Efficient Localization Method Research Articles

LettuceNet: A Novel Deep Learning Approach for Efficient Lettuce Localization and Counting

Traditional lettuce counting relies heavily on manual labor, which is laborious and time-consuming. In this study, a simple and efficient method for localization and counting lettuce is proposed, based only on lettuce field images acquired by an unmanned aerial vehicle (UAV) equipped with an RGB camera. In this method, a new lettuce counting model based on the weak supervised deep learning (DL) approach is developed, called LettuceNet. The LettuceNet network adopts a more lightweight design that relies only on point-level labeled images to train and accurately predict the number and location information of high-density lettuce (i.e., clusters of lettuce with small planting spacing, high leaf overlap, and unclear boundaries between adjacent plants). The proposed LettuceNet is thoroughly assessed in terms of localization and counting accuracy, model efficiency, and generalizability using the Shanghai Academy of Agricultural Sciences-Lettuce (SAAS-L) and the Global Wheat Head Detection (GWHD) datasets. The results demonstrate that LettuceNet achieves superior counting accuracy, localization, and efficiency when employing the enhanced MobileNetV2 as the backbone network. Specifically, the counting accuracy metrics, including mean absolute error (MAE), root mean square error (RMSE), normalized root mean square error (nRMSE), and coefficient of determination (R2), reach 2.4486, 4.0247, 0.0276, and 0.9933, respectively, and the F-Score for localization accuracy is an impressive 0.9791. Moreover, the LettuceNet is compared with other existing widely used plant counting methods including Multi-Column Convolutional Neural Network (MCNN), Dilated Convolutional Neural Networks (CSRNets), Scale Aggregation Network (SANet), TasselNet Version 2 (TasselNetV2), and Focal Inverse Distance Transform Maps (FIDTM). The results indicate that our proposed LettuceNet performs the best among all evaluated merits, with 13.27% higher R2 and 72.83% lower nRMSE compared to the second most accurate SANet in terms of counting accuracy. In summary, the proposed LettuceNet has demonstrated great performance in the tasks of localization and counting of high-density lettuce, showing great potential for field application.

Node Localization Method in Wireless Sensor Networks Using Combined Crow Search and the Weighted Centroid Method.

Node localization is critical for accessing diverse nodes that provide services in remote places. Single-anchor localization techniques suffer co-linearity, performing poorly. The reliable multiple anchor node selection method is computationally intensive and requires a lot of processing power and time to identify suitable anchor nodes. Node localization in wireless sensor networks (WSNs) is challenging due to the number and placement of anchors, as well as their communication capabilities. These senor nodes possess limited energy resources, which is a big concern in localization. In addition to convention optimization in WSNs, researchers have employed nature-inspired algorithms to localize unknown nodes in WSN. However, these methods take longer, require lots of processing power, and have higher localization error, with a greater number of beacon nodes and sensitivity to parameter selection affecting localization. This research employed a nature-inspired crow search algorithm (an improvement over other nature-inspired algorithms) for selecting the suitable number of anchor nodes from the population, reducing errors in localizing unknown nodes. Additionally, the weighted centroid method was proposed for identifying the exact location of an unknown node. This made the crow search weighted centroid localization (CS-WCL) algorithm a more trustworthy and efficient method for node localization in WSNs, with reduced average localization error (ALE) and energy consumption. CS-WCL outperformed WCL and distance vector (DV)-Hop, with a reduced ALE of 15% (from 32%) and varying communication radii from 20 m to 45 m. Also, the ALE against scalability was validated for CS-WCL against WCL and DV-Hop for a varying number of beacon nodes (from 3 to 2), reducing ALE to 2.59% (from 28.75%). Lastly, CS-WCL resulted in reduced energy consumption (from 120 mJ to 45 mJ) for varying network nodes from 30 to 300 against WCL and DV-Hop. Thus, CS-WCL outperformed other nature-inspired algorithms in node localization. These have been validated using MATLAB 2022b.

YOLIC: An efficient method for object localization and classification on edge devices

In the realm of Tiny AI, we introduce “You Only Look at Interested Cells” (YOLIC), an efficient method for object localization and classification on edge devices. Through seamlessly blending the strengths of semantic segmentation and object detection, YOLIC provides improved computational efficiency and precision compared to traditional methods. By adopting Cells of Interest for classification instead of individual pixels, YOLIC encapsulates relevant information, reduces computational load, and enables rough object shape inference. Importantly, the need for bounding box regression is obviated, as YOLIC capitalizes on the predetermined cell configuration that provides information about potential object location, size, and shape. To tackle the issue of single-label classification limitations, a multi-label classification approach is applied to each cell for effectively recognizing overlapping or closely situated objects. This paper presents extensive experiments on multiple datasets to demonstrate that YOLIC achieves detection performance comparable to the state-of-the-art YOLO algorithms while surpassing in speed, exceeding 30fps on a Raspberry Pi 4B CPU.

An Efficient and Robust Fingerprint-Based Localization Method for Multifloor Indoor Environment

An Efficient and Robust Fingerprint-Based Localization Method for Multifloor Indoor Environment

Detection and Localization of Albas Velvet Goats Based on YOLOv4.

In order to achieve goat localization to help prevent goats from wandering, we proposed an efficient target localization method based on machine vision. Albas velvet goats from a farm in Ertok Banner, Ordos City, Inner Mongolia Autonomous Region, China, were the main objects of study. First, we proposed detecting the goats using a shallow convolutional neural network, ShallowSE, with the channel attention mechanism SENet, the GeLU activation function and layer normalization. Second, we designed three fully connected coordinate regression network models to predict the spatial coordinates of the goats. Finally, the target detection algorithm and the coordinate regression algorithm were combined to localize the flock. We experimentally confirmed the proposed method using our dataset. The proposed algorithm obtained a good detection accuracy and successful localization rate compared to other popular algorithms. The overall number of parameters in the target detection algorithm model was only 4.5 M. The average detection accuracy reached 95.89% and the detection time was only 8.5 ms. The average localization error of the group localization algorithm was only 0.94 m and the localization time was 0.21 s. In conclusion, the method achieved fast and accurate localization, which helped to rationalize the use of grassland resources and to promote the sustainable development of rangelands.

Efficient Localization Method Based on RSSI for AP Clusters.

The localization accuracy is susceptible to the received signal strength indication (RSSI) fluctuations for RSSI-based wireless localization methods. Moreover, the maximum likelihood estimation (MLE) of the target location is nonconvex, and locating target presents a significant computational complexity. In this paper, an RSSI-based access point cluster localization (APCL) method is proposed for locating a moving target. Multiple location-constrained access points (APs) are used in the APCL method to form an AP cluster as an anchor node (AN) in the wireless sensor network (WSN), and the RSSI of the target is estimated with several RSSI samples obtained by the AN. With the estimated RSSI for each AN, the solution for the target location can be obtained quickly and accurately due to the fact that the MLE localization problem is transformed into an eigenvalue problem by constructing an eigenvalue equation. Simulation and experimental results show that the APCL method can meet the requirement of high-precision real-time localization of moving targets in WSN with higher localization accuracy and lower computational effort compared to the existing classical RSSI-based localization methods.

A fast LiDAR place recognition and localization method by fusing local and global search

Place recognition is an important branch of Simultaneous Localization and Mapping (SLAM), which finds revisited places, thereby reducing error accumulations. Most mainstream methods only concentrate on the similarity of two LiDAR scans and cannot obtain the pose information. In this paper, we design a descriptor named Occupied Place Description (OPD) and propose an efficient map-aided place recognition and localization method. Our method can effectively detect loop events, obtain the vehicle’s poses, and overcome the overlap dependence of pairwise point cloud registration. It is composed of four modules. First, the map data generation is designed to store the map database as binary files. Then, a trajectory initialization consisting of global search, local search, and trajectory score computation is proposed to determine the vehicle’s initial poses. Next, an online localization method is developed by combining descriptor similarity and Kalman Filtering, which only takes less than 5ms per localization. Finally, loop events are detected based on pose information. Exhaustive evaluations on KITTI and MulRan datasets demonstrate the superiority of our method. The average absolute trajectory error (ATE) is 0.5 m and the average relative rotation error is 2.7 degrees. F1 score measures the success rate of place recognition and our average maximum F1 score achieves nearly 0.987. The source code will be available in https://github.com/ShiPC-AI/Occupied-Place-Description.

Grid-guided localization network based on the spatial attention mechanism for synthetic aperture radar ship detection

Synthetic aperture radar (SAR) has become an important part of ship detection due to its all-day all-weather characteristics. Ship monitoring is important for coastal traffic control and territorial safety. Ship detection requires high accuracy, but the speed of ship detection is also an important parameter in making rapid decisions, such as those in maritime rescue and military strategy. However, fast networks tend to be less accurate. To address this problem, we propose an efficient localization method based on a spatial attention mechanism. This mechanism uses grid-guided localization instead of a frame regression mechanism, which makes the network faster but also lowers the accuracy to a level insufficient for direct application to SAR image target detection. A tested and selected spatial attention mechanism improves the detection accuracy while guaranteeing its speed. It is shown that four factors affect the design of the spatial attention mechanism, namely query and key content, query content and relative position, key content, and relative position. These factors are ordered, and the group with the best precision is added to the proposed network. The proposed network can achieve a good detection effect for sparsely distributed targets in SAR images, and the proposed algorithm can achieve AP50 ∶ 75, AP50, AP75, and APS values of 71.3%, 96.9%, 86.6%, and 72.1%, respectively, on the SAR ship detection dataset.

Efficient cooperative localization method with node selection based on position error bound

Cooperative Localization (CL) has become a promising solution that circumvents the needs for high-density anchor deployment, and offers additional localization accuracy in Wireless Sensor Networks (WSNs). However, it suffers from high computational complexity and increased network traffic problem. To alleviate this problem, we propose an iterative greedy node selection approach based on Position Error Bound (PEB) for Angle-of-arrival (AOA) based CL. We introduce a Boolean vector to formulate the node selection optimization problem that maximizes the Decrease of PEB (DPEB) from agents’ cooperation. Since the problem is NP-hard and difficult to solve, the iterative greedy algorithm is proposed to approach the sub-optimal solutions. Then, in order to improve the accuracy of localization phase, we derive the efficient closed-form solution of AOA CL problem and propose an iterative constrained Least Squares (LS) method. Moreover, the theoretical analysis shows that the localization estimator is very close to the Cramer Rao Lower Bound (CRLB) performance. Finally, simulation results show that the proposed node selection approach can greatly decrease the number of agents participating in the CL without significant degradation in localization accuracy. Besides, the proposed CL method outperforms the existing ones in terms of localization accuracy.

Indoor high-precision visible light positioning system using Jaya algorithm.

Several indoor positioning systems that utilize visible light communication (VLC) have recently been developed. Due to the simple implementation and high precision, most of these systems are dependent on received signal strength (RSS). The position of the receiver can be estimated according to the positioning principle of the RSS. To improve positioning precision, an indoor three-dimensional (3D) visible light positioning (VLP) system with the Jaya algorithm is proposed. In contrast to other positioning algorithms, the Jaya algorithm has a simple structure with only one phase and achieves high accuracy without controlling the parameter settings. The simulation results show that an average error of 1.06 cm is achieved using the Jaya algorithm in 3D indoor positioning. The average errors of 3D positioning using the Harris Hawks optimization algorithm (HHO), ant colony algorithm with an area-based optimization model (ACO-ABOM), and modified artificial fish swam algorithm (MAFSA) are 2.21 cm, 1.86 cm and 1.56 cm, respectively. Furthermore, simulation experiments are performed in motion scenes, where a high-precision positioning error of 0.84 cm is achieved. The proposed algorithm is an efficient method for indoor localization and outperforms other indoor positioning algorithms.

Performance Analysis and Sensor-Target Geometry Optimization for TOA and TDOA-Based Hybrid Source Localization Method

Currently, the performance analysis of positioning algorithms and optimization of ground station deployment schemes are predominantly based on pure TOA or TDOA measurement information, and the relevant theoretical analysis is primarily the geometric analysis of optimal station deployment for fixed point targets, with few placement ranges and amount of station constraints. In practice, however, there are typically several measurements from TOA and TDOA stations, with a focus on positioning precision within a certain region or line trajectory, as well as the necessity for constraints on the ground station placement range. This paper proposes an efficient method for hybrid source localization using TOA and TDOA measurement information, establishes a mathematical model for hybrid source localization based on TOA and TDOA measurement information, derives and simulates the Gauss–Newton iterative localization algorithm with the least squares criterion, and performs a theoretical analysis of the least squares error and CRLB boundary to improve the accuracy of target localization in the aforementioned scenarios. Taking the average CRLB value of target line trajectory positioning error as the objective function, the ground station placement scheme of TOA- and TDOA-receiving sensors is optimized by utilizing a Genetic Algorithm with strong global optimization capability under the constraints of station placement range and station quantities, and a station placement geometry with better performance than typical station placement is obtained. Meanwhile, we summarize the general placement principles for TOA and TDOA hybrid source localization of target line trajectories.

Angio Cone-Beam CT (Angio-CBCT) and 3D Road-Mapping for the Detection of Spinal Cord Vascularization in Patients Requiring Treatment for a Thoracic Aortic Lesion: A Feasibility Study.

Spinal cord ischemia is a major complication of treatment for descending thoracic aorta (DTA) disease. Our objectives were (1) to describe the value of angiographic cone-beam CT (angio-CBCT) and 3D road-mapping to visualize the Adamkiewicz artery (AA) and its feeding artery and (2) to evaluate the impact of AA localization on the patient surgical strategy. Between 2018 and 2020, all patients referred to our institution for a surgical DTA disorder underwent a dedicated AA evaluation by angio-CBCT. If the AA feeding artery was not depicted on angio-CBCT, selective artery catheterization was performed, guided by 3D road-mapping. Intervention modifications, based on AA location and one month of neurologic follow-up after surgery, were recorded. Twenty-one patients were enrolled. AA was assessable in 100% of patients and in 15 (71%) with angio-CBCT alone. Among them, 10 patients needed 3D road-mapping-guided DSA angiography to visualize the AA feeding artery. The amount of contrast media, irradiation dose, and intervention length were not significantly different whether the AA was assessable or not by angio-CBCT. AA feeding artery localization led to surgical sketch modification for 11 patients. Angio-CBCT is an efficient method for AA localization in the surgical planning of DTA disorders.

Efficient frequency domain method for holographic localization of rotating sound sources with arbitrary array configurations

Owing to the widespread use of rotating machinery, the localization of rotating sources and the prediction of associated sound fields were extensively studied in the past decades. Most of the previous studies employed beamforming techniques for the localization of rotating sources. These methods usually rely on the use of a virtual rotating array (VRA), in which the Doppler effects caused by source rotation can be eliminated. In this study, compressive sensing (CS) near-field acoustic holography (NAH), which has been extended to the reconstruction of rotating sources using the frequency domain (FD) VRA method, can provide reconstruction capabilities that beamforming techniques cannot offer, such as predictions of the source amplitude and phase information. Furthermore, an improved resolution of spatial reconstructions at low frequencies was achieved. In addition to the direct combination of the FD-VRA method and recently developed stationary source CS acoustical holography techniques, a more efficient algorithm for FD-VRA was developed to address the shortcomings of the traditional approach, such as higher computational cost and the requirement of a circular array with equally spaced microphones. The proposed FD-VRA method only involves a direct summation of the rotating sidebands of signals measured on a stationary array, which effectively reduces the computational load. More importantly, an arbitrary array of optimized microphones can be used. The proposed algorithm works accurately for narrowband sources without overlapping frequency components in the rotating sidebands.

Application of locating supratrochlear artery and supraorbital artery in combined transfrontal and intranasal endoscopic approaches

Objective: To investigate the localization methods of supratrochlear artery (STA) and supraorbital artery (SOA), and to explore the clinical benefit of locating nerve via accompanying vascular localization in combined transfrontal and intranasal endoscopic approaches. Methods: From June 2019 to May 2021, 14 patients, including 11 males and 3 females, aging from 18 to 69 years old, were underwent frontal sinus surgery through the combined transfrontal and intranasal endoscopic approaches in the Department of Otorhinolaryngology Head and Neck Surgery of the Third Affiliated Hospital of Sun Yat-sen University. Before the surgery, localization of STA and SOA was determined by color doppler flow imaging (CDFI), computerized topographic angiography (CTA) and contrast enhanced magnetic resonance angiography (CE-MRA) respectively, and the distances between STA and SOA from facial midline were measured on 28 eyebrows. The position of external incision was determined according to the preoperative localization of STA and SOA. The examination time, cost and postoperative complications of the three methods were recorded. The accuracy of localization at 14 sides was verified by the surgery. GraphPad Prism 8.3 software was used for statistical analysis. Results: STA and SOA could be located by CDFI, CTA and CE-MRA. There was no significant difference in the measurement of the distance between STA and SOA from the facial midline among 3 methods (all P>0.05). Determining the position of external incision according to the localization of STA and SOA could protect both the blood vessels and accompanying nerves. No postoperative complications such as numbness of the forehead skin occurred. The measurement time of CDFI, CTA and CE-MRA was 22.50 (15.75, 30.00), 30.00 (28.00, 34.25) and 48.00 (44.00, 52.75) min (M (Q1, Q3)), respectively (all P<0.05). CDFI incurred the lowest costs and took the shortest time. Conclusions: CDFI is an efficient and economic localization method. The localization of STA and SOA facilitates the precise selection of the position of external incision, protects the accompanying nerve and reduces postoperative complications.

Marine Application Evaluation of Monocular SLAM for Underwater Robots.

With the development of artificial intelligence technology, visual simultaneous localization and mapping (SLAM) has become a cheap and efficient localization method for underwater robots. However, there are many problems in underwater visual SLAM, such as more serious underwater imaging distortion, more underwater noise, and unclear details. In this paper, we study these two problems and chooses the ORB-SLAM2 algorithm as the method to obtain the motion trajectory of the underwater robot. The causes of radial distortion and tangential distortion of underwater cameras are analyzed, a distortion correction model is constructed, and five distortion correction coefficients are obtained through pool experiments. Comparing the performances of contrast-limited adaptive histogram equalization (CLAHE), median filtering (MF), and dark channel prior (DCP) image enhancement methods in underwater SLAM, it is found that the DCP method has the best image effect evaluation, the largest number of oriented fast and rotated brief (ORB) feature matching, and the highest localization trajectory accuracy. The results show that the ORB-SLAM2 algorithm can effectively locate the underwater robot, and the correct distortion correction coefficient and DCP improve the stability and accuracy of the ORB-SLAM2 algorithm.

An Efficient Geolocation Method for Malicious LBSD Users Based on Dynamic Adjustment of Probes

The integration of the Internet of Things (IoT) and social networks is a promising trend of network technology. However, the diversity of social networks also poses potential risks to IoT security. Researching on the geolocation of social network users can verify the effectiveness of location protection mechanisms adopted by service providers, as well as provide a means for geolocating miscreants in social networks. Most current research focuses on how to infer the true location of a target within a specific region, such as within a city, while less research has been done on how to achieve fast and accurate localization of targets under long-range conditions. In this manuscript, an efficient localization method for LBSD users at long distances based on dynamic adjustment of probes (DAPL) is proposed. Based on the analysis of factors that affect the accuracy and efficiency of the target location approximation, DAPL can approach the real location sustainability of the target by dynamically generating probe locations. By identifying abnormal fluctuations of the target’s reported distance, timely corrections of probe location are made to improve efficiency. In experimental results for Momo, a global popular LBSD social platform with more than 115 million active users show that even the initial probe is thousands of miles away from the target, DAPL can geolocate the target with a success rate close to 100% (99.5%), which is much higher than 70.6% of the existing method. Only about 12 times of LBSD service queries are needed, and DAPL can geolocate 88.9% of targets within 40 meters with an average error of 22.1 meters, which has higher efficiency and approximate accuracy compared with the existing typical method.

An efficient regression method for 3D object localization in machine vision systems

&lt;p&gt;Machine vision or robot vision plays is playing an important role in many industrial systems and has a lot of potential applications in the future of automation tasks such as in-house robot managing, swarm robotics controlling, product line observing, and robot grasping. One of the most common yet challenging tasks in machine vision is 3D object localization. Although several works have been introduced and achieved good results for object localization, there is still room to further improve the object location determination. In this paper, we introduce a novel 3D object localization algorithm in which a checkerboard pattern-based method is used to initialize the object location and followed by a regression model to regularize the object location. The proposed object localization is employed in a low-cost robot grasping system where only one simple 2D camera is used. Experimental results showed that the proposed algorithm significantly improves the accuracy of the object localization when compared to the relevant works.&lt;/p&gt;

Leak Localization in Looped Pipe Networks Based on a Factorized Transient Wave Model: Theoretical Framework

AbstractUrban water distribution systems are often made of loops to increase redundancy and improve reliability. The inherent feature of multipath wave propagation in looped networks has been the main obstacle to directly derive a factorized wave propagation model with decoupled leak location and size, which is essential for developing a robust and efficient leak localization method. To address this problem, this article proposes an efficient algorithm to estimate the transient hydraulic pressure and discharge at all nodes of a looped network using boundary measurements. Given these hydraulic properties, a factorized wave propagation model is formulated by applying conservation laws to a tree‐shaped control volume of the looped network. Based on this factorized model, a fast and efficient one‐dimensional search of the leak location along all pipes of a looped network is realized by the matched‐field processing technique. Numerical experiments demonstrate that an unknown leak anywhere in a five‐loop network with 13 pipes can be accurately and efficiently localized by the proposed method.

Relative localization of swarm robotics based on the polar method

This article proposed a simple and efficient method for relative localization of swarm robotics. Firstly, the relative localization module of the micro-robot is designed to be composed of a compass and several pairs of infrared transceiver sensors evenly arranged on the edge of the robot. Based on the existing relative localization method and combined with the relative localization module, an improved relative localization method for swarm robots named as polar method is proposed, which includes distance calculation, relative direction calculation, and coordinates conversion. After that, a set of localization rules is designed to apply this method to the swarm system, which mainly include establishment of reference coordinate system, localization of the adjacent layer of the seed robot, and localization between layers, so that the initial coordinates of all robots can be obtained directly with only one seed robot. Then we described the implementation process of dynamic localization of swarm robots based on the initial static localization in the edge detour motion mode. Finally, the feasibility and flexibility of this localization method are verified by experiments on the swarm robotic platform, and the localization method is applied to realize the shape formation of swarm robots.

An Efficient Localization and Avoidance Method of Jammers in Vehicular Ad Hoc Networks

An Efficient Localization and Avoidance Method of Jammers in Vehicular Ad Hoc Networks