Real-time Board Research Articles

SE-CBAM-YOLOv7: An Improved Lightweight Attention Mechanism-Based YOLOv7 for Real-Time Detection of Small Aircraft Targets in Microsatellite Remote Sensing Imaging

Addressing real-time aircraft target detection in microsatellite-based visible light remote sensing video imaging requires considering the limitations of imaging payload resolution, complex ground backgrounds, and the relative positional changes between the platform and aircraft. These factors lead to multi-scale variations in aircraft targets, making high-precision real-time detection of small targets in complex backgrounds a significant challenge for detection algorithms. Hence, this paper introduces a real-time aircraft target detection algorithm for remote sensing imaging using an improved lightweight attention mechanism that relies on the You Only Look Once version 7 (YOLOv7) framework (SE-CBAM-YOLOv7). The proposed algorithm replaces the standard convolution (Conv) with a lightweight convolutional squeeze-and-excitation convolution (SEConv) to reduce the computational parameters and accelerate the detection process of small aircraft targets, thus enhancing real-time onboard processing capabilities. In addition, the SEConv-based spatial pyramid pooling and connected spatial pyramid convolution (SPPCSPC) module extracts image features. It improves detection accuracy while the feature fusion section integrates the convolutional block attention module (CBAM) hybrid attention network, forming the convolutional block attention module Concat (CBAMCAT) module. Furthermore, it optimizes small aircraft target features in channel and spatial dimensions, improving the model’s feature fusion capabilities. Experiments on public remote sensing datasets reveal that the proposed SE-CBAM-YOLOv7 improves detection accuracy by 0.5% and the mAP value by 1.7% compared to YOLOv7, significantly enhancing the detection capability for small-sized aircraft targets in satellite remote sensing imaging.

Lossless and Near-Lossless Compression Algorithms for Remotely Sensed Hyperspectral Images.

Rapid and continuous advancements in remote sensing technology have resulted in finer resolutions and higher acquisition rates of hyperspectral images (HSIs). These developments have triggered a need for new processing techniques brought about by the confined power and constrained hardware resources aboard satellites. This article proposes two novel lossless and near-lossless compression methods, employing our recent seed generation and quadrature-based square rooting algorithms, respectively. The main advantage of the former method lies in its acceptable complexity utilizing simple arithmetic operations, making it suitable for real-time onboard compression. In addition, this near-lossless compressor could be incorporated for hard-to-compress images offering a stabilized reduction at nearly 40% with a maximum relative error of 0.33 and a maximum absolute error of 30. Our results also show that a lossless compression performance, in terms of compression ratio, of up to 2.6 is achieved when testing with hyperspectral images from the Corpus dataset. Further, an improvement in the compression rate over the state-of-the-art k2-raster technique is realized for most of these HSIs by all four variations of our proposed lossless compression method. In particular, a data reduction enhancement of up to 29.89% is realized when comparing their respective geometric mean values.

Real-Time Optimal States Estimation with Inertial and Delayed Visual Measurements for Unmanned Aerial Vehicles.

Motion estimation is a major issue in applications of Unmanned Aerial Vehicles (UAVs). This paper proposes an entire solution to solve this issue using information from an Inertial Measurement Unit (IMU) and a monocular camera. The solution includes two steps: visual location and multisensory data fusion. In this paper, attitude information provided by the IMU is used as parameters in Kalman equations, which are different from pure visual location methods. Then, the location of the system is obtained, and it will be utilized as the observation in data fusion. Considering the multiple updating frequencies of sensors and the delay of visual observation, a multi-rate delay-compensated optimal estimator based on the Kalman filter is presented, which could fuse the information and obtain the estimation of 3D positions as well as translational speed. Additionally, the estimator was modified to minimize the computational burden, so that it could run onboard in real time. The performance of the overall solution was assessed using field experiments on a quadrotor system, compared with the estimation results of some other methods as well as the ground truth data. The results illustrate the effectiveness of the proposed method.

Edge Artificial Intelligence-Based Facial Pain Recognition During Myocardial Infarction

Medical history highlights that Myocardial Infarction is one of the leading factors of death in human beings. Angina pectoris is a prominent vital sign of Myocardial Infraction. Medical reports suggests that experiencing a chest pain during heart attacks causes changes in facial muscles resulting in variations in patterns of facial expression. The present work intends to develop an automatic facial expression detection to identify the severity of chest pain as a vital signs of MI using algorithmic approach that is implemented with a state of art Convolution Neural Networks CNN. The advanced object detection light weight Convolutional Neural Network models: Single Shot Detector Mobile Net V2 and Single Shot Detector Inception V2 are utilized for designing the vital signs MI model from 500 Red Blue Green Color images private dataset. The authors develop a cardiac emergency health monitoring care using an Edge Artificial Intelligence, “Edge AI” using NVIDIA’s Jetson Nano embedded GPU platform. The proposed model is mainly focused on the low cost and less power consumption factors for onboard real time detection of vital signs of Myocardial infarction. The evaluated metrics achieves a mean Average Precision of 85.18%, Average Recall of 88.32% and 6.85 frames per second for the generated detections.

Enhancing the target visibility with synthetic target specific digitally reconstructed radiograph for intrafraction motion monitoring: A proof-of-concept study.

Intrafraction motion monitoring in External Beam Radiation Therapy (EBRT) is usually accomplished by establishing a correlation between the tumor and the surrogates such as an external infrared reflector, implanted fiducial markers, or patient skin surface. These techniques either have unstable surrogate-tumor correlation or are invasive. Markerless real-time onboard imaging is a noninvasive alternative that directly images the target motion. However, the low target visibility due to overlapping tissues along the X-ray projection path makes tumor tracking challenging. To enhance the target visibility in projection images, a patient-specific model was trained to synthesize the Target Specific Digitally Reconstructed Radiograph (TS-DRR). Patient-specific models were built using a conditional Generative Adversarial Network (cGAN) to map the onboard projection images to TS-DRR. The standard Pix2Pix network was adopted as our cGAN model. We synthesized the TS-DRR based on the onboard projection images using phantom and patient studies for spine tumors and lung tumors. Using previously acquired CT images, we generated DRR and its corresponding TS-DRR to train the network. For data augmentation, random translations were applied to the CT volume when generating the training images. For the spine, separate models were trained for an anthropomorphic phantom and a patient treated with paraspinal stereotactic body radiation therapy (SBRT). For lung, separate models were trained for a phantom with a spherical tumor insert and a patient treated with free-breathing SBRT. The models were tested using Intrafraction Review Images (IMR) for the spine and CBCT projection images for the lung. The performance of the models was validated using phantom studies with known couch shifts for the spine and known tumor deformation for the lung. Both the patient and phantom studies showed that the proposed method can effectively enhance the target visibility of the projection images by mapping them into synthetic TS-DRR (sTS-DRR). For the spine phantom with known shifts of 1 mm, 2 mm, 3 mm, and 4 mm, the absolute mean errors for tumor tracking were 0.11 ± 0.05 mm in the x direction and 0.25 ± 0.08 mm in the y direction. For the lung phantom with known tumor motion of 1.8 mm, 5.8 mm, and 9 mm superiorly, the absolute mean errors for the registration between the sTS-DRR and ground truth are 0.1 ± 0.3 mm in both the x and y directions. Compared to the projection images, the sTS-DRR has increased the image correlation with the ground truth by around 83% and increased the structural similarity index measure with the ground truth by around 75% for the lung phantom. The sTS-DRR can greatly enhance the target visibility in the onboard projection images for both the spine and lung tumors. The proposed method could be used to improve the markerless tumor tracking accuracy for EBRT.

A novel and lean data-based method to calculate the actual HVAC zone energy consumption and cooling load in sustainable smart cities using a single temperature sensor

Sustainability and energy savings are two intertwined research aims for humanity’s long-term survival, aligned with the Paris Agreement and the Egyptian vision of 2030. The purpose of this research is to minimize the cost needed to measure the HVAC energy consumption in educational and commercial buildings to save energy for energy efficiency strategies to serve the future smart and sustainable cities. These facilities are among the most energy-consuming loads, and this research proposes a technique to determine real HVAC energy consumption and cooling load using a single-sensor method. Calculating the as-built HVAC energy usage and real cooling load, especially in complex HVAC systems like VRV, which are some of the most challenging gaps, is achieved through a revolutionary and cost-effective approach. The proposed approach computes the actual HVAC energy consumption of each specific zone in the building using data from a single temperature sensor. Furthermore, the real and instantaneous cooling load of each zone was calculated, and the results show a promising agreement between the proposed techniques and the real measured consumption of the HVAC system. This approach can be integrated into the BMS building management system to determine the actual HVAC energy usage and cooling load for each zone individually in real time, enabling significant energy reduction decisions with optimal cost efficiency. Furthermore, it can be used by the BMS system as a real-time On-Board Diagnostic of the HVAC system.

Machine Learning and Case-Based Reasoning for Real-Time Onboard Prediction of the Survivability of Ships

The subject of damaged stability has greatly profited from the development of new tools and techniques in recent history. Specifically, the increased computational power and the probabilistic approach have transformed the subject, increasing accuracy and fidelity, hence allowing for a universal application and the inclusion of the most probable scenarios. Currently, all ships are evaluated for their stability and are expected to survive the dangers they will most likely face. However, further advancements in simulations have made it possible to further increase the fidelity and accuracy of simulated casualties. Multiple time domain and, to a lesser extent, Computational Fluid dynamics (CFD) solutions have been suggested as the next “evolutionary” step for damage stability. However, while those techniques are demonstrably more accurate, the computational power to utilize them for the task of probabilistic evaluation is not there yet. In this paper, the authors present a novel approach that aims to serve as a stopgap measure for introducing the time domain simulations in the existing framework. Specifically, the methodology presented serves the purpose of a fast decision support tool which is able to provide information regarding the ongoing casualty utilizing prior knowledge gained from simulations. This work was needed and developed for the purposes of the EU-funded project SafePASS.

Calculation of Swath Width and Swath Displacement for Uncrewed Aerial Spray Systems

Highlights Recent research has focused on the use of Uncrewed Aerial Spray Systems (UASS) for their potential to fill the gap between crewed aircraft and ground application equipment. The spray distribution in swath is highly variable to the point that using the typical metric of uniformity alone to define swath can no longer apply, we present a method that considers dose and uniformity. The swath was rarely found to be directly beneath the flightline, the swath displacement and offsetting can be significant and larger than the assumed swath width. This paper presents the development of an evidence-based, repeatable mathematical solution to the determination of swath width and swath displacement for UASS for calibration and targeting purposes. Abstract. Recent research has focused on the use of Uncrewed Aerial Spray Systems (UASS) for their potential to fill the gap between crewed aircraft and ground application, with UASS being able to be used over less accessible areas than ground equipment, being more appropriate to treat smaller, dispersed targets, and typically available at reduced cost and complexity when compared to crewed aircraft. However, there is limited literature focusing on the proper setup and use of these systems. The objective of this study was to design and conduct a series of large-scale, conceptually linked studies to provide data that is used to guide system optimization and the development of predictive models. An uncrewed system coupled with three nozzle types covering three droplet size classifications was used to conduct swath characterization and drift trials designed to establish effective swath widths, deposition variability, swath displacement, and drift. System and nozzle type, along with nozzle position and wind direction, significantly impacted the spray deposition patterns within and downwind of the effective swath. The spray distribution in a swath is highly variable, to the point that using the typical metric of uniformity alone to define swath can no longer apply. In addition, the swath was rarely found to be directly beneath the flightline, and swath offsetting can be significant and larger than the assumed swath width. An iterative solution has been developed that uses a combination of effective dose and uniformity to define swath width. The offsetting of the swath due to interactions with ambient air has also been defined using the Center of Deposition. The aim is to be able to distinguish between in-swath deposition and drift. The approach to defining swath width and the displacement of the swath is presented. The goal is to develop a real-time onboard navigation system that can reset the flight line in response to wind-driven swath displacement. This allows increased deposition within the target zone and reduces off-target losses. Keywords: Aerial application, Offset, Swath displacement, Swath width, Unmanned aerial spray system.

Azimuth Spectrum Reconstruction Algorithm Based on Updating Factors Regionally for Onboard Real-Time Multichannel SAR Imaging

Azimuth Spectrum Reconstruction Algorithm Based on Updating Factors Regionally for Onboard Real-Time Multichannel SAR Imaging

Real-time estimation and prediction of unsteady flows using reduced-order models coupled with few measurements

The estimation and prediction of unsteady flows in real time offers significant advantages for the monitoring and active control of complex hydrodynamic and aerodynamic systems, such as wind turbine blades, hydrofoils and aircraft wings. A new data assimilation algorithm is proposed for the estimation and prediction of unsteady flows, coupling in real time onboard measurements and fluid dynamics simulations at minimal computational expense. The procedure combines a Proper Orthogonal Decomposition Galerkin method, a model under location uncertainty stochastic closure, and a particle filtering scheme. The algorithm is validated using case studies of two- and three-dimensional wake flows at low and moderate Reynolds numbers respectively. Following an initial learning window to train the algorithm, and using only a single measurement point, our method is shown to perform well against conventional reduced data assimilation algorithms for up to 14 vortex shedding cycles.

Closed-form solution of attitude command generation for spin-to-spin maneuver

In recent earth observing missions, agile satellites enable various imaging modes beyond the traditional along-track strip imaging. However, it requires maneuvering with boundary conditions of considerable angular velocity, i.e., spin-to-spin maneuvering. This paper proposes an attitude command generation method for spin-to-spin maneuvering that can provide feedforward commands for the attitude control loop. A general solution for arbitrary flight time is provided which steers a satellite to the given final attitude and angular velocity at the prescribed time. In addition, an alternative method is proposed that further improves the maneuvering speed, which is applicable to small-angle maneuvering cases. The proposed solutions are both closed-form which are more intuitive and easier to comprehend than numerical solutions. It also has a great advantage in computational efficiency, which could enable its use on-board in real time. Numerical examples demonstrate the performance of the proposed methods in a single maneuvering case as well as in a consecutive maneuvering case integrated with a realistic earth observing scenario.

A continuous-time formulation for optimal task scheduling and quality-of-service assurance in nanosatellites

Satellite scheduling concerns an operations research problem that aims at planning the execution of a given set of tasks, either in real-time onboard the spacecraft or offline in the ground station. In particular, the task scheduling problem for nanosatellites has been the focus of recent research, given the unique set of constraints and applications, and considering their limited power resources. This paper applies the continuous-time methodology to deliver a novel scheduling formulation for the nanosatellite scheduling problem with increased flexibility and versatility to the decision-maker. Here, we adopt the concept of priority slots and follow the Multi-Operation Sequencing with Synchronized Start Times (MOS-SST) representation to yield a Mixed-Integer Linear Programming (MILP) formulation that considers constraints on time synchronization, mission quality-of-service, and management of shared resources. By comparing our continuous-time strategy with existing discrete-time alternatives, we showed that the proposed method can solve representative problem instances in a considerably shorter time, while being able to deal with real-valued constraint functions.

ROLL-SENSITIVE ONLINE CAMERA ORIENTATION DETERMINATION ON THE STRUCTURED ROAD

Abstract. Online camera calibration technology can estimate the pose of the camera onboard in real time, playing an important role in many fields such as HD map production and autonomous vehicles. Some researchers use one vanishing point (VP) to calculate the pitch and yaw angle of the onboard camera. However, this method assumes that the roll angle is zero, which is impractical because of the inevitable installation error. This paper proposes a novel online camera orientation determination method based on a longitudinal vanishing point without the zero-roll hypothesis. The orientation of the camera is determined in two steps: calculating the pitch and yaw angles according to vanishing point theory, and then obtaining the roll angle with lane widths constraint which is modeled as an optimization problem. To verify the effectiveness of our algorithm, we evaluated it on the nuScenes dataset. As a result, the rotation error of the roll and pitch angle can achieve 0.154° and 0.116° respectively. Also, we deployed our method in the “Tuyou”, an autonomous vehicle developed by Wuhan University, and then tested it in the urban structured road. Our proposed method can reconstruct the ground space accurately compared with previous methods with zero-roll hypothesis.

Precise Onboard Time Synchronization for LEO Satellites

<h3>Abstract</h3> Onboard time synchronization is an important requirement for a wide range of low Earth orbit (LEO) missions such as altimetry or communication services, and extends to future position, navigation, and timing (PNT) services in LEO. For GNSS-based time synchronization, continuous knowledge about the satellite’s position is required and, eventually, the quality of the position solution defines the timing precision attainable through GNSS measurements. Previous research has shown that real-time GNSS orbit determination of LEO satellites can achieve decimeter-level accuracy. This paper characterizes the performance of GNSS-based real-time clock synchronization in LEO using the satellite Sentinel-6A as a real-world case study. The satellite’s ultra-stable oscillator (USO) and triple-frequency GPS/Galileo receiver provide measurements for a navigation filter representative of real-time onboard processing. Continuous evaluation of actual flight data over 14 days shows that a 3D orbit root-mean-square (RMS) error of 11 cm and a 0.9-ns clock standard deviation can be achieved.

Direct Power and Voltage Oriented Control Strategies of Grid-Connected Wind Energy Conversion System Based on Permanent Magnet Synchronous Generator

This article deals with the control techniques of a low-voltage grid-connected to wind power conversion system based on a permanent magnet synchronous generator (PMSG) using an indirect matrix converter (IMC). Details of the proposed strategies for both the rectifier and inverter stages of the IMC are presented. Thus, a rectifier control strategy based on voltage-oriented control using space vector modulation is proposed. In addition, the control objective of the direct power control (DPC) inverter is the regulation of the active powers of the PMSG according to references established on the basis of the maximum power point tracker (MPPT) of the wind turbine, and also a good tracking of the output reactive power to its reference ensures unit power factor (UPF). A numerical simulation investigation is conducted to investigate the fast-dynamic performance of the proposed control systems during the wind speed variation. The obtained results in simulation are then complemented with tests in laboratory environment, the DPC control system is implemented on a dSpace DS1104 real time board. Selective experimental results are presented using a laboratory prototype of the wind energy conversion system to demonstrate the resulting improvements of the developed system. The results achieved have been clearly responded to the follow-up of references even under fluctuating wind conditions, and show promising relevance of the proposed method.

RTOB SLAM: Real-Time Onboard Laser-Based Localization and Mapping

RTOB-SLAM is a new low-computation framework for real-time onboard simultaneous localization and mapping (SLAM) and obstacle avoidance for autonomous vehicles. A low-resolution 2D laser scanner is used and a small form-factor computer perform all computations onboard. The SLAM process is based on laser scan matching with the iterative closest point technique to estimate the vehicle’s current position by aligning the new scan with the map. This paper describes a new method which uses only a small subsample of the global map for scan matching, which improves the performance and allows for a map to adapt to a dynamic environment by partly forgetting the past. A detailed comparison between this method and current state-of-the-art SLAM frameworks is given, together with a methodology to choose the parameters of the RTOB-SLAM. The RTOB-SLAM has been implemented in ROS and perform well in various simulations and real experiments.

Data driven interference source localization based on train real-time onboard interference monitoring

Interference is an important factor affecting railway mobile communications, which leads to deterioration of communication quality. In serious cases, the link connection interruption will lead to degraded operation of train control system, then affect the operation efficiency of the railway system. In order to reduce the impact of interference on railway communications, the interference source should be localized and eliminated timely. However, the traditional interference localization methods require auxiliary equipment to be arranged along the track. In this paper, a data driven interference source localization method based on train real-time onboard interference monitoring is proposed, which can reduce the interference localization cost. Based on the collected Received Signal Strength (RSS) of interference signal, the particle filter principle is used to locate the target interference source combined with the data driven path-loss models. Besides, the modified whale optimization algorithm (MWOA) is introduced to further improve the positioning accuracy. The simulation and experiment results show that the proposed data driven interference source localization method outperforms the traditional localization method, and the positioning accuracy is improved from tens of meters degree to meters degree, which can meet the requirements of engineering practice to find the interference source.

Responsive manipulation of neural circuit pathology by fully implantable, front-end multiplexed embedded neuroelectronics

Responsive neurostimulation is increasingly required to probe neural circuit function and treat neuropsychiatric disorders. We introduce a multiplex-then-amplify (MTA) scheme that, in contrast to current approaches (which necessitate an equal number of amplifiers as number of channels), only requires one amplifier per multiplexer, significantly reducing the number of components and the size of electronics in multichannel acquisition systems. It also enables simultaneous stimulation of arbitrary waveforms on multiple independent channels. We validated the function of MTA by developing a fully implantable, responsive embedded system that merges the ability to acquire individual neural action potentials using conformable conducting polymer-based electrodes with real-time onboard processing, low-latency arbitrary waveform stimulation, and local data storage within a miniaturized physical footprint. We verified established responsive neurostimulation protocols and developed a network intervention to suppress pathological coupling between the hippocampus and cortex during interictal epileptiform discharges. The MTA design enables effective, self-contained, chronic neural network manipulation with translational relevance to the treatment of neuropsychiatric disease.

The Real-Time Approach to Solving the Problems for the Multicriterial Choice of Alternatives in the Knowledge Bases of Onboard Real-Time Advisory Expert Systems

The Real-Time Approach to Solving the Problems for the Multicriterial Choice of Alternatives in the Knowledge Bases of Onboard Real-Time Advisory Expert Systems

RGDiNet: Efficient Onboard Object Detection with Faster R-CNN for Air-to-Ground Surveillance

An essential component for the autonomous flight or air-to-ground surveillance of a UAV is an object detection device. It must possess a high detection accuracy and requires real-time data processing to be employed for various tasks such as search and rescue, object tracking and disaster analysis. With the recent advancements in multimodal data-based object detection architectures, autonomous driving technology has significantly improved, and the latest algorithm has achieved an average precision of up to 96%. However, these remarkable advances may be unsuitable for the image processing of UAV aerial data directly onboard for object detection because of the following major problems: (1) Objects in aerial views generally have a smaller size than in an image and they are uneven and sparsely distributed throughout an image; (2) Objects are exposed to various environmental changes, such as occlusion and background interference; and (3) The payload weight of a UAV is limited. Thus, we propose employing a new real-time onboard object detection architecture, an RGB aerial image and a point cloud data (PCD) depth map image network (RGDiNet). A faster region-based convolutional neural network was used as the baseline detection network and an RGD, an integration of the RGB aerial image and the depth map reconstructed by the light detection and ranging PCD, was utilized as an input for computational efficiency. Performance tests and evaluation of the proposed RGDiNet were conducted under various operating conditions using hand-labeled aerial datasets. Consequently, it was shown that the proposed method has a superior performance for the detection of vehicles and pedestrians than conventional vision-based methods.