SoftPOSIT: Simultaneous Pose and Correspondence Determination

In order to solve the problem of autonomous localization and navigation caused by the loss of the position information of the mobile robot in a complex environment, a method for autonomous navigation of a mobile robot based on ROS is proposed in this paper. The ROS platform is used to avoid the problems of code redundancy, poor portability and so on. In this method, firstly, monte carlo algorithm is used to realize the autonomous localization of the robot, raster map is constructed with lidar data, and the concept of raster occupancy is introduced to reduce the influence of sensor noise. Then an improved ant colony algorithm is proposed for global path planning to realize autonomous navigation of the robot. At the end of this paper, the robot control system is combined with ROS navigation system for map construction and autonomous navigation experiments. The experimental results show that the improved ant colony algorithm can effectively shorten the number of iterations, reduce the number of iterations by 38%, improve the adaptability to the environment, facilitate the fast finding of the shortest path, and accurately realize the autonomous navigation task of the robot.

Autonomous navigation within airport environments presents significant challenges, mostly due to the scarcity of accessible and labeled data for training autonomous systems. This study introduces an innovative approach to assess the performance of vision-based models trained on synthetic datasets, with the goal of determining whether simulated data can train and validate navigation operations in complex airport environments. The methodology includes a comparative analysis employing image processing techniques and object detection algorithms. A comparative analysis of two different datasets was conducted: a synthetic dataset that mirrors real airport scenarios, generated using the Microsoft Flight Simulator 2020®video game, and a real-world dataset. The results indicate that models trained on a combination of both real and synthetic images perform much better in terms of adaptability and accuracy compared to those trained only on one type of dataset. This analysis makes a significant contribution to the field of autonomous airport navigation and offers a cost-effective and practical solution to overcome the challenges of dataset acquisition and algorithm validation. It is thus believed that this study lays the groundwork for future advancements in the field.

Iterative algorithms are gaining clinical acceptance in CT. We performed objective phantom-based image quality evaluation of five commercial iterative reconstruction algorithms available on four different multi-detector CT (MDCT) scanners at different dose levels as well as the conventional filtered back-projection (FBP) reconstruction. Using the Catphan500 phantom, we evaluated image noise, contrast-to-noise ratio (CNR), modulation transfer function (MTF) and noise-power spectrum (NPS). The algorithms were evaluated over a CTDIvol range of 0.75-18.7 mGy on four major MDCT scanners: GE DiscoveryCT750HD (algorithms: ASIR™ and VEO™); Siemens Somatom Definition AS+ (algorithm: SAFIRE™); Toshiba Aquilion64 (algorithm: AIDR3D™); and Philips Ingenuity iCT256 (algorithm: iDose4™). Images were reconstructed using FBP and the respective iterative algorithms on the four scanners. Use of iterative algorithms decreased image noise and increased CNR, relative to FBP. In the dose range of 1.3-1.5 mGy, noise reduction using iterative algorithms was in the range of 11%-51% on GE DiscoveryCT750HD, 10%-52% on Siemens Somatom Definition AS+, 49%-62% on Toshiba Aquilion64, and 13%-44% on Philips Ingenuity iCT256. The corresponding CNR increase was in the range 11%-105% on GE, 11%-106% on Siemens, 85%-145% on Toshiba and 13%-77% on Philips respectively. Most algorithms did not affect the MTF, except for VEO™ which produced an increase in the limiting resolution of up to 30%. A shift in the peak of the NPS curve towards lower frequencies and a decrease in NPS amplitude were obtained with all iterative algorithms. VEO™ required long reconstruction times, while all other algorithms produced reconstructions in real time. Compared to FBP, iterative algorithms reduced image noise and increased CNR. The iterative algorithms available on different scanners achieved different levels of noise reduction and CNR increase while spatial resolution improvements were obtained only with VEO™. This study is useful in that it provides performance assessment of the iterative algorithms available from several mainstream CT manufacturers.

Precise localization for achieving next-generation autonomous navigation: State-of-the-art, taxonomy and future prospects

Integrity monitoring (IM) in autonomous navigation has been extensively researched, but currently available solutions are mainly applicable to specific algorithms and sensors, or limited by linearity or 'Gaussianity' assumptions. This study investigates a Solution Separation (SS) based framework for universal IM, scalable to multi-sensor fusion as each hypothesis assumes a whole sensor measurement set as faulty. Architecturally we consider that: 1) multi sensor systems must account for various sensor noise models which lead to inconsistent estimates of uncertainties, 2) a module must be able to detect sensor failure or sensor noise mismodeling and suggest better bounds for the error, without being constantly conservative, 3) some algorithms are computationally heavy to monitor in the SS setting or the provided covariances cannot be interpreted in IM. A hybrid SS architecture can be practical, where some solutions are evaluated with a navigation algorithm with known characteristics, although the all-sensor-in solution is evaluated with the monitored algorithm. Experiments are run on filter and smoothing-based navigation algorithms. In addition, we experiment with hybrid SS monitoring and time-correlated noise to evaluate the appropriability of our framework in the context of the above-mentioned requirements. This is a novel framework in the IM domain, directly integrable in existing navigation solutions and, in our opinion, it will facilitate the quantification of the effect of different sensors in navigation safety.

Object detection and tracking are two critical tasks in computer vision, widely applied in security surveillance, autonomous vehicles, and behavioral analysis. Strong performance in object detection has been demonstrated by recent Transformer-based models, such as RT-DETR (Real-Time Detection Transformer), due to their global context modeling and high accuracy. However, an inherent tracking mechanism is lacking in RT-DETR, which requires additional components to maintain identity consistency across frames. To address this limitation, an integration of RT-DETR with DeepSORT is proposed, leveraging the strengths of both models to enhance real-time object detection and tracking. A comparative evaluation with YOLOv8, a widely used real-time detector, is conducted to highlight the advantages of the proposed approach in tracking accuracy and robustness. Experiments show that effective performance is achieved in challenging scenarios such as object occlusion and intersection. Specifically, an IDF1 score of 60.0%, a MOTA of 42.4%, and a MOTP of 43.3% are obtained by RTl+DeepSORT on the MOT17-02-DPM dataset, outperforming YOLOv8x+DeepSORT. These results indicate that significant improvements in tracking accuracy are attained while real-time efficiency is maintained, making the proposed approach well-suited for applications such as intelligent surveillance and autonomous navigation.

In this work, the effect of noise on the precision in the modulation transfer function (MTF) calculation using different phantoms is investigated. Three different techniques are studied, based on three different phantoms: edge, bar, and star bar. For each technique, theoretical expressions for the standard deviation and the signal to noise ratio (SNR) of the MTF are derived. In addition, Monte Carlo simulations are carried out to study the accuracy and precision of all the three techniques. Using the analytic expressions for the MTF calculation, statistical fluctuations of noise in the phantom images are propagated to MTF values. Then, for each frequency the standard deviation and the SNR of the MTF are calculated. Monte Carlo simulations are carried out for each phantom image and for different noise level. Images are artificially generated following a procedure that simulates sampling, blurring, and noise present in a real phantom image and takes into account the attenuation of each phantom. Then, oversampling procedures are applied to these images to obtain presampled MTFs. In all three techniques the standard deviation of the MTF is proportional to that of the noise in the image. For the edge image, the standard deviation is proportional to the frequency f, whereas for the bar and star bar techniques it is proportional to the square root of f. Regarding the precision, theoretical expressions and simulations results agree that the bar technique shows the best precision for all the frequencies and all the noise levels analyzed in this study. In addition, simulation results show how, for large levels of noise, the edge technique gives rise to large bias errors at high and medium frequencies. Finally, the precision of the star bar technique is similar to that of the bar technique for isotropic systems, but worse for nonisotropic ones. The uncertainties in the MTF calculation with the edge technique are larger than with the bar technique, and the differences increase with the frequency. On the one hand, the stronger dependency on the frequency shown by the standard deviation of the MTF makes the precision gets worse faster in the edge technique. On the other hand, in the case of the edge and for high levels of noise, differentiation produces line spread functions (LSF) with a poor SNR, increasing erroneously the MTF and worsening accuracy.

A robust method for multi object tracking in autonomous ship navigation systems

This work performs an analysis of basic optical properties of zoom lenses with a fixed distance between object and image points and a fixed position of the image-space focal point. Formulas for the calculation of paraxial parameters of such optical systems are derived and the calculation is presented on examples.

Automatic navigation of agricultural machinery is an important aspect of Smart Farming. Intelligent agricultural machinery applications increasingly rely on machine vision algorithms to guarantee enhanced in-field navigation accuracy by precisely locating the crop lines and mapping the navigation routes of vehicles in real-time. This work presents an overview of vision-based tractor systems. More specifically, this work deals with (1) the system architecture, (2) the safety of usage, (3) the most commonly faced navigation errors, (4) the navigation control system of tractors and presents (5) state-of-the-art image processing algorithms for in-field navigation route mapping. In recent research, stereovision systems emerge as superior to monocular systems for real-time in-field navigation, demonstrating higher stability and control accuracy, especially in extensive crops such as cotton, sunflower, maize, etc. A detailed overview is provided for each topic with illustrative examples that focus on specific agricultural applications. Several computer vision algorithms based on different optical sensors have been developed for autonomous navigation in structured or semi-structured environments, such as orchards, yet are affected by illumination variations. The usage of multispectral imaging can overcome the encountered limitations of noise in images and successfully extract navigation paths in orchards by using a combination of the trees’ foliage with the background of the sky. Concisely, this work reviews the current status of self-steering agricultural vehicles and presents all basic guidelines for adapting computer vision in autonomous in-field navigation.

To create a robust means to remove noise pixels using complex data. A receiver operating characteristic (ROC) curve was used to determine the appropriate choice of magnitude and phase thresholds as well as connectivity values to determine what pixels represent noise in the image. To fine-tune the results, a spike removal and hole replacement operator is applied to reduce Type I error and remove small islands of noise. The use of phase information improves the magnitude-only thresholding approach by further recognizing pixels that contain only noise. The performance of the method is enhanced using local connectivity of magnitude and phase data. An ROC analysis on simulated data shows that the Type I and Type II errors are less than 10(-4) and 10(-3), respectively, without connectivity and 0 and 10(-3), respectively, with connectivity for a signal-to-noise ratio (SNR) of 3:1 or higher. The joint use of both magnitude and phase images helps to improve the removal of noise points in magnetic resonance images. This can prove useful in automating the visualization of phase images without the highly distractive phase noise in noise regions. Also, it is useful in susceptibility weighted imaging when taking the minimum intensity projections of variably sized regions.

Accurate registration is a key step for precise and real-time measurement of appearance phenotype using the forward intersection method. For example, in order to reconstruct the details of the plant organs (leaf, fruit, stem, etc.), precisely matched image points from varied object points should be of high density in the image region of a target organ in each image. However, this task is not achieved stably with relevant methods in current literature. In this paper, the multiple basic parameters for affine registration are obtained by estimating the distance reference value, obtaining the camera attitude from the inertial module, calibrating the internal parameters of the camera, calibrating the structure parameters of the vision system, aberration modelling, and other methods. The basic parameters are used to express the vectors of object points to be measured, the optical vectors of the image points to be matched and the scale factors of the optical projection in varied camera coordinate systems. In the registration process, these vectors are affine operated to map the first target image point to each image via the strategy of mapping. The system error of the approximately matched pixel is eliminated in the micro-region of error centred around the approximately matched pixel. Research shows that this affine registration algorithm is able to obtain a large number of highdensity and accurate matched image points that correspond to different target points in the leaf region of each image. This is suitable for forward intersection measurement of the plant appearance phenotype details with a real-time vision system based on our results. The proposed registration method is highly robust, efficient and precise; and requires relatively little computation resources.

To determine the relative pose between an object and a single camera using 2D-to-3D point correspondences, a kind of iterative methods based on inverse projection ray approach is proposed. An iterative algorithm which is divided into depth recovery stage and absolute orientation stage is also proposed. In the first stage, the optimal translation vector is first computed in terms of rotation matrix via least square method, then the depths of the observed points are estimated by projecting the estimated point orthogonally to the inverse projection ray defined by the image point, and finally 3D points are reconstructed using the estimated depths from previous step. In the second stage, the optimal rotation matrix is estimated by applying Umeyama algorithm to fitting of the 3D model points and 3D estimated points. The above two stages are repeated until the result converges. The global convergence of the two-stage iterative algorithm is proven based on the global convergence theorem. Finally, a spacecraft docking application is implemented to test the effectiveness and convergence of the proposed algorithm by mathematical simulation and physical simulation.

Accurate state estimation of dynamic objects is critical for safe and reliable autonomous navigation in dynamic urban settings. Real-world scenarios may include occlusions, drifting in pose estimation, data sparsity, or abrupt appearances, representing complexity in multi-object tracking. This paper addresses the challenges of estimating the states of non-ego vehicles during autonomous navigation using multimodal visual-LiDAR perception, without any need to global navigation systems. The proposed estimation framework integrates detection and tracking through an optimal variance filter. The first stage incorporates instance segmentation and point cloud association, followed by an L-shape fitting method to estimate 3D Bounding Boxes. Object tracking is then performed using a modified multiobject tracking algorithm augmented by the initialization of motion models. This enables estimation of consistent surrounding vehicle velocities and positions while keeping track of them in the 3D space, enhancing situational awareness for motion planning, and supporting collision avoidance using predictive models. Comprehensive experiments on the KITTI dataset demonstrate the effectiveness and accuracy of the proposed framework compared to current benchmarks and state-of-the-art methods.

We evaluated the feasibility of using quantitatively measured thoracic components, as compared to body mass index (BMI), for predicting the image noise of coronary computed tomography angiography (CCTA). One hundred subjects (M:F=64:36; mean age, 55±8.8years) who underwent prospective electrocardiography-gated CCTA and low-dose chest computed tomography (CT) were analyzed retrospectively. The image noise of the CCTA was determined by the standard deviation of the attenuation value in a region of interest on the aortic root level. On the low-dose chest CT, the areas of the thoracic components were measured at the aortic root level. An auto-segmentation technique with the following threshold levels was used: quantitatively measured area of total thorax [QMAtotal: -910 to 1000 Hounsfield units (HU)], lung (QMAlung: -910 to -200 HU), fat (QMAfat: -200 to 0 HU), muscle (QMAmuscle: 0-300 HU), soft tissue (fat+muscle, QMAsoft tissue: -200 to 300 HU), bone (QMAbone: 300-1000 HU) and solid tissue (fat+muscle+bone, QMAsolid tissue: -200 to 1000 HU). The relationship between image noise and variable biometric parameters including QMA was analyzed, and the linear correlation coefficients were used as indicators of the strength of association. Among the variable biometric parameters, including BMI, QMAsolid tissue showed the highest correlation coefficient with image noise in all subjects (r=0.804), males (r=0.716), females (r=0.889), the overweight (r=0.556), and the non-overweight subgroups (r=0.783). QMAsolid tissue can be used as a potential surrogate predictor of the image noise level in low tube voltage CCTA.