A Visual Indoor Localization Method Based on Efficient Image Retrieval

The task of indoor visual localization, utilizing camera visual information for user pose calculation, was a core component of Augmented Reality (AR) and Simultaneous Localization and Mapping (SLAM). Existing indoor localization technologies generally used scene-specific 3D representations or were trained on specific datasets, making it challenging to balance accuracy and cost when applied to new scenes. Addressing this issue, this paper proposed a universal indoor visual localization method based on efficient image retrieval. Initially, a Multi-Layer Perceptron (MLP) was employed to aggregate features from intermediate layers of a convolutional neural network, obtaining a global representation of the image. This approach ensured accurate and rapid retrieval of reference images. Subsequently, a new mechanism using Random Sample Consensus (RANSAC) was designed to resolve relative pose ambiguity caused by the essential matrix decomposition based on the five-point method. Finally, the absolute pose of the queried user image was computed, thereby achieving indoor user pose estimation. The proposed indoor localization method was characterized by its simplicity, flexibility, and excellent cross-scene generalization. Experimental results demonstrated a positioning error of 0.09 m and 2.14° on the 7Scenes dataset, and 0.15 m and 6.37° on the 12Scenes dataset. These results convincingly illustrated the outstanding performance of the proposed indoor localization method.

Adaptive Recurrent Iterative Updating Stereo Matching Network

When training a stereo matching network with a single training dataset, the network may overly rely on the learned features of the single training dataset due to differences in the training dataset scenes, resulting in poor performance on all datasets. Therefore, feature consistency between matched pixels is a key factor in solving the network’s generalization ability. To address this issue, this paper proposed a more widely applicable stereo matching network that introduced whitening loss into the feature extraction module of stereo matching, and significantly improved the applicability of the network model by constraining the variation between salient feature pixels. In addition, this paper used a GRU iterative update module in the disparity update calculation stage, which expanded the model’s receptive field at multiple resolutions, allowing for precise disparity estimation not only in rich texture areas but also in low texture areas. The model was trained only on the Scene Flow large-scale dataset, and the disparity estimation was conducted on mainstream datasets such as Middlebury, KITTI 2015, and ETH3D. Compared with earlier stereo matching algorithms, this method not only achieves more accurate disparity estimation but also has wider applicability and stronger robustness.

Single Image Desnow Based on Vision Transformer and Conditional Generative Adversarial Network for Internet of Vehicles

With the increasing popularity of artificial intelligence applications,machine learning is also playing an increasingly important role in the Internet of Things(IoT)and the Internet of Vehicles(IoV).As an essential part of the IoV,smart transportation relies heavily on information obtained from images.However,inclement weather,such as snowy weather,negatively impacts the process and can hinder the regular operation of imaging equipment and the acquisition of conventional image information.Not only that,but the snow also makes intelligent transportation systems make the wrong judgment of road conditions and the entire system of the Internet of Vehicles adverse.This paper describes the single image snowremoval task and the use of a vision transformer to generate adversarial networks.The residual structure is used in the algorithm,and the Transformer structure is used in the network structure of the generator in the generative adversarial networks,which improves the accuracy of the snow removal task.Moreover,the vision transformer has good scalability and versatility for larger models and has a more vital fitting ability than the previously popular convolutional neural networks.The Snow100K dataset is used for training,testing and comparison,and the peak signal-to-noise ratio and structural similarity are used as evaluation indicators.The experimental results show that the improved snow removal algorithm performs well and can obtain high-quality snow removal images.

Single Image Deraining Using Dual Branch Network Based on Attention Mechanism for IoT

Extracting useful details from images is essential for the Internet of Things project.However,in real life,various external environments,such as badweather conditions,will cause the occlusion of key target information and image distortion,resulting in difficulties and obstacles to the extraction of key information,affecting the judgment of the real situation in the process of the Internet of Things,and causing system decision-making errors and accidents.In this paper,we mainly solve the problem of rain on the image occlusion,remove the rain grain in the image,and get a clear image without rain.Therefore,the single image deraining algorithm is studied,and a dual-branch network structure based on the attention module and convolutional neural network(CNN)module is proposed to accomplish the task of rain removal.In order to complete the rain removal of a single image with high quality,we apply the spatial attention module,channel attention module and CNN module to the network structure,and build the network using the coder-decoder structure.In the experiment,with the structural similarity(SSIM)and the peak signal-to-noise ratio(PSNR)as evaluation indexes,the training and testing results on the rain removal dataset show that the proposed structure has a good effect on the single image deraining task.

Design of Indoor Security Robot based on Robot Operating System

The design and implementation of indoor security robot can well integrate the two fields of indoor navigation and object detection, in order to achieve a more powerful robot system, the development of this project has certain theoretical research significance and practical application value. The project development is completed in ROS (Robot Operating System). The main tools or frameworks used include AMCL (Adaptive Monte Carlo Localization) package, SLAM (Simultaneous Localization and Mapping) algorithm, Darknet deep learning framework, YOLOv3 (You Only Look Once)algorithm, etc. The main development methods include odometer information fusion, coordinate transformation, localization and mapping, path planning, YOLOv3 model training, function package configuration and deployment. Indoor security robot has two main functions: first, it can complete real-time localization, mapping and navigation of indoor environment through sensors such as lidar and camera;Second, object detection is accomplished through USB camera. Through the detailed analysis and research of the functional design of the two modules, the expected function is finally realized, which can meet the daily use needs.

Online 3D Packing Problem Based on Bi-Value Guidance

The online 3D packing problem has received increasing attention in recent years due to its practical value. However, the problem itself possesses some peculiar properties, such as sequential decision-making and the large size of the state space, which have made the use of reinforcement learning with Markov decision processes a popular approach for solving this problem. In this paper, we focus on the problem of high variance in value estimation caused by reward uncertainty in the presence of highly uncertain dynamics. To address this, proposed a solution based on auxiliary tasks and intrinsic rewards for the online 3D bin packing problem, guided by a binary-valued network, to assist the agent in learning the policy within the framework of actor-critic deep reinforcement learning. Specifically, the maintenance of two-valued networks and the utilization of multi-valued network estimates are employed to replace the original value estimates, aiming to provide better guidance for the learning of policy networks. Experimentally, it has been demonstrated that our model can achieve more robust learning and outperform previous works in terms of performance.

UWB Positioning System Based on Genetic Algorithm

In order to enhance the positioning accuracy, a UWB positioning system based on genetic algorithm is proposed. Firstly, it uses the DW1000 module to measure the distance, and preprocesses the measured data to remove noise. Then, a positioning equation is established according to the processed distance information, and the genetic algorithm is used to solve the equation to obtain the coordinates of the unknown node. The experimental results show that the measured positioning accuracy is within 30 cm, which means that the system can obtain a good positioning effect and meet the need for precise positioning.

Hybrid Location Algorithm Based on Cuckoo and Statistical Manifold

To improve the location accuracy, a hybrid location algorithm based on cuckoo and statistical manifold method is proposed. It combines the cuckoo algorithm's strong global optimization ability and the statistical manifold’s accurate positioning ability fully. The simulation results show that the hybrid location algorithm has higher accuracy and reduces the influence of initial value selection on location accuracy.

A Semi-Supervised WLAN Indoor Localization Method Based on l1-Graph Algorithm

For indoor location estimation based on received signal strength( RSS) in wireless local area networks( WLAN),in order to reduce the influence of noise on the positioning accuracy,a large number of RSS should be collected in offline phase. Therefore,collecting training data with positioning information is time consuming which becomes the bottleneck of WLAN indoor localization. In this paper,the traditional semisupervised learning method based on k-NN and ε-NN graph for reducing collection workload of offline phase are analyzed,and the result shows that the k-NN or ε-NN graph are sensitive to data noise,which limit the performance of semi-supervised learning WLAN indoor localization system. Aiming at the above problem,it proposes a l1-graph-algorithm-based semi-supervised learning( LG-SSL) indoor localization method in which the graph is built by l1-norm algorithm. In our system,it firstly labels the unlabeled data using LG-SSL and labeled data to build the Radio Map in offline training phase,and then uses LG-SSL to estimate user's location in online phase. Extensive experimental results show that,benefit from the robustness to noise and sparsity ofl1-graph,LG-SSL exhibits superior performance by effectively reducing the collection workload in offline phase and improving localization accuracy in online phase.

Silver Nanowires Contained Nanofluids with Enhanced Optical Absorption and Thermal Transportation Properties

Two kinds of silver nanowires(100 nm in diameter, 20 μm and 100 μm in length) are prepared. The thermo-physical characteristics, viscosity, and photothermal conversion performance of the silver nanowires(AgNWs)contained ethylene glycol nanofluids are investigated in detail. It is found that thermal conductivity of 100 μm AgNWs contained nanofluids is higher than that of 20 μm AgNWs with the same diameters of 100 nm. Viscosity test shows that the nanofluid is a Newtonian fluid, and the longer silver nanowires, the greater viscosity. In addition, photothermal conversion efficiency of silver nanowires contained nanofluid is studied. We can observe that the 100 μm AgNWs contained nanofluid has a higher photothermal conversion efficiency than that containing 20 μm AgNWs. Moreover, we find that there is a certain correlation between heat transfer and photothermal conversion of nanofluid. It demonstrates that the high heat transfer property of nanofluid will benefit for its photothermal conversion efficiency and the mechanism is proposed. This work provides a new idea to improve photothermal conversion efficiency. We can choose materials with high thermal conductivity and strong light absorption ability to enhance the photothermal conversion performance of nanofluids.

Point mutations of homologs as an adaptive solution to the gene loss

Gene loss is common and influences genome evolution trajectories.Multiple adaptive strategies to compensate for gene loss have been observed,including copy number gain of paralogous genes and mutations in genes of the same pathway.By using the Ubl-specific protease 2(ULP2)eviction model,we identify compensatory mutations in the homologous gene ULP1 by laboratory evolution and find that these mutations are capable of rescuing defects caused by the loss of ULP2.Furthermore,bioinformatics analysis of genomes of yeast gene knockout library and natural yeast isolate datasets suggests that point mutations of a homologous gene might be an additional mechanism to compensate for gene loss.

Influence of construction-induced damage on the degradation of freeze—thawed lightweight cellular concrete

During the construction of lightweight cellular concrete(LCC),material damage frequently occurs,causing the degradation and deterioration of the mechanical performance,durability,and subgrade quality of LCC.The construction-induced damage can be more significant than those from the service environment of LCC,such as freeze-thaw(F-T)action in cold regions.However,the effect of construction-induced damage on LCC during F-T cycles is often ignored and the deterioration mechanisms are not yet clarified.In this study,we investigated the factors causing damage during construction using a sample preparation method established to simulate the damage in the laboratory setting.We conducted F-T cycle tests and microstructural characterization to study the effect of microstructural damage on the overall strength of LCC with different water contents under F-T actions.We established the relationship between the pore-area ratio and F-T cycle times,pore-area ratio,and strength,as well as the F-T cycle times and strength under different damage forms.The damage evolution is provided with the rationality of the damage equation,verified by comparing the measured and predicted damage variables.This study would serve as a guide for the construction and performance of LCC in cold regions.