Debris Detection Research Articles

Machine vision system for real-time debris detection on mechanical wild blueberry harvesters

Improving fruit quality is important to wild blueberry producers. Plant debris like leaves and stems caused a reduction in fruit quality during mechanical harvesting. A debris detection system was developed using two Logitech C920 webcam cameras mounted before and after the blower fan on a commercial mechanical wild blueberry harvester. Images were collected from two commercially managed wild blueberry fields located in central Nova Scotia to develop a dataset of 1000 images. Two convolutional neural networks (CNNs), YOLOv3 and YOLOv3-SPP, were used and compared for performance analysis. The CNNs were trained using no augmented images, images with five augmentations (sharpening, brightness, contrast, gamma correction, and saturation), and images with five augmentations that were more heavily weighted towards gamma. Four different computer hardware packages (Hewlett-Packard, Shuttle XPC, Jetson TX2, and GPU-based Desktop) were used to determine the appropriate hardware and CNN model combination for real-time performance. YOLOv3 and YOLOv3-SPP were trained to mAP scores of 72.87 and 74.38% using the dataset with more gamma-augmented images. This was an improvement over the dataset with no augmentation (67.75; 68.49%) and equally numbered augmentations (71.26%; 73.03%). YOLOv3-SPP combined with an Intel® Core™ i9-7900X CPU and Nvidia GeForce RTX™ 2080 Ti GPU in a desktop computer achieved the fastest detection rate of 33.30 ms. The detection speed on all other hardware configurations exceeded 33.30 ms, indicating that a powerful desktop GPU is required for real-time performance of this task. With adequate processing hardware, the developed technology could be integrated into a control system to automatically adjust brushes based on conveyor information from mechanical wild blueberry harvesters to make cleaning berries easier and enhance fruit quality.

Bidirectional YOLO: improved YOLO for foreign object debris detection on airport runways

Foreign object debris (FOD) on airport runways has always been a major problem in maintaining airport security. Currently, there are two main challenges in FOD detection based on computer vision. First, FOD is small and inconspicuous, which makes it difficult for the detector to find and categorize the object correctly. Second, airport pavements at night present a low-light situation, which makes FOD detection more difficult. To solve these problems, we propose an improved real-time detector bidirectional YOLO (Bi-YOLO), constructed by first adding a bidirectional PANet to YOLOv5. This adds a BiFPN-like weighted bidirectional operation to the PANet, allowing the network to improve the focus on small objects adaptively. Then, we use the anchor-free manner, SimOTA label assignment, and multibranch head to reduce the complexity of our model and improve the model’s performance in detecting small objects. Finally, we use special data augmentation strategies during training to improve the model’s performance on small objects in low-light situations. Experiments on the public dataset FOD-A and our own dataset FODInSues show that, compared with the popular object detectors YOLOv5, YOLOv3, CenterNet, and EfficientDet-D4, Bi-YOLO achieves the best performance in FOD detection, especially for small FOD in low-light situations.

A Permanent Magnet Ferromagnetic Wear Debris Sensor Based on Axisymmetric High-Gradient Magnetic Field.

The detection of wear debris in lubricating oil is effective for determining current equipment operating conditions for fault diagnosis. In this paper, a permanent magnet ferromagnetic wear debris sensor is proposed that is composed of a compact structure and a detection coil that generates an induced voltage when wear debris passes through a magnetic field. A three-dimensional model of the sensor is established, the internal axisymmetric high-gradient magnetic field of the sensor is analyzed, and a mathematical model of the sensor signal is proposed. The effects of the air gap structure of the sensor and the relative permeability, velocity, and volume of the wear debris on the sensor performance are analyzed. The correctness of the theoretical results is proven by single particle experiments, and the sensor is calibrated to achieve quantitative analysis of the wear debris.

A novel evaluation method for in situ space debris detection based on conductive traces

To enable the detection of micrometeoroids and small-sized space debris (MMSD) in the sub-mm range, in situ detectors aboard a spacecraft are the tool of choice. Unfortunately, only a few projects have been sent to space until today. However, knowledge of the MMSD population is important to keep the reference models up-to-date and gain more insights into factors like the amount of debris and its distribution along certain orbits. This will be crucial for the safety of current and future spaceflight missions. Present-day in situ detection systems mostly rely on impact recognition and characterization using different methods. One of them is the perforation of a special detection area during such an event. These areas consist of one or more layers provided with conductive traces. Any interruption of one of these lines can be recognized using some kind of electrical continuity testing method or the determination of the resistance. This goes along with some drawbacks, like the difficult or even impossible multi-event recognition along one line. The proposed concept relies on a reflectometric approach. In doing so, for example, pulses are being sent along a well-defined transmission line, which is a part of the detection area. Any alteration in the characteristic line impedance, for instance, due to an impact, will generate reflections back into the generator. Their evaluation can provide the location as well as the complex impedance of the perturbation.

Co-Correcting: Combat Noisy Labels in Space Debris Detection

Space debris detection is vital to space missions and space situation awareness. Convolutional neural networks are introduced to detect space debris due to their excellent performance. However, noisy labels, caused by false alarms, exist in space debris detection, and cause ambiguous targets for the training of networks, leading to networks overfitting the noisy labels and losing the ability to detect space debris. To remedy this challenge, we introduce label-noise learning to space debris detection and propose a novel label-noise learning paradigm, termed Co-correcting, to overcome the effects of noisy labels. Co-correcting comprises two identical networks, and the predictions of these networks serve as auxiliary supervised information to mutually correct the noisy labels of their peer networks. In this manner, the effect of noisy labels can be mitigated by the mutual rectification of the two networks. Empirical experiments show that Co-correcting outperforms other state-of-the-art methods of label-noise learning, such as Co-teaching and JoCoR, in space debris detection. Even with a high label noise rate, the network trained via Co-correcting can detect space debris with high detection probability.

MOVE-III: A CubeSat for the detection of sub-millimetre space debris and meteoroids in Low Earth Orbit

The Munich Orbital Verification Experiment (MOVE) is a CubeSat student project housed at the Scientific Workgroup for Rocketry and Spaceflight at the Technical University of Munich. MOVE-III is the fourth CubeSat under development, and the first 6U mission of the MOVE project that will carry a dedicated scientific payload in orbit. The mission aims at acquiring in-situ observations of sub-millimetre space debris and meteoroids in Low Earth Orbit, with the objective of compiling a dataset of flux, as well as object mass and velocity measurements that can be used for the validation of the small object estimates of space debris models and support further studies related to the characterisation of the space environment. The MOVE-III CubeSat employs the MOVE-BEYOND platform and is planned to carry three Debris Density Retrieval and Analysis (DEDRA) plasma ionization sensors. The Preliminary Design Review has been completed in early 2022, with the next milestone being the Critical Design Review, planned for 2023. The paper elaborates on the scientific objectives of the mission and the expected data products, provides an overview of the detector operation principle and presents the overall system architecture, the platform configuration and the subsystem interaction. Considerations on the debris mitigation aspects of the mission are additionally discussed.

Olfactory receptors in macrophages and inflammation.

Olfactory receptors (ORs) that bind odorous ligands are the largest family of G-protein-coupled receptors. In the olfactory epithelium, approximately 400 and 1,100 members are expressed in humans and mice, respectively. Growing evidence suggests the extranasal functions of ORs. Here, we review OR expression and function in macrophages, specialized innate immune cells involved in the detection, phagocytosis, and destruction of cellular debris and pathogens as well as the initiation of inflammatory responses. RNA sequencing data in mice suggest that up to 580 ORs may be expressed in macrophages. Macrophage OR expression is increased after treatment with the Toll-like receptor 4 ligand lipopolysaccharide, which also induces the transcription of inflammasome components. Triggering human OR6A2 or its mouse orthologue Olfr2 with their cognate ligand octanal induces inflammasome assembly and the secretion of IL-1β, which exacerbates atherosclerosis. Octanal is positively correlated with blood lipids like low-density lipoprotein –cholesterol in humans. Another OR, Olfr78, is activated by lactate, which promotes the generation of tumor-associated macrophages that dampen the immune response and promote tumor progression. Olfactory receptors in macrophages are a rich source of untapped opportunity for modulating inflammation. It is not known which of the many ORs expressed in macrophages promote or modulate inflammation. Progress in this area also requires deorphanizing more ORs and determining the sources of their ligands.

The Optimization of Parallel Resonance Circuit for Wear Debris Detection by Adjusting Capacitance

Wear debris in lubrication oil provides important information for marine engine condition monitoring and faults diagnosis. Inductive sensors have been widely used to detect wear debris in lubrication oil. To improve the sensitivity, the inductive coil is always connected with a capacitor in parallel to form parallel LC resonance-sensing circuit. A previous study optimized the parallel resonance circuit by adjusting the excitation frequency. However, multiple parameters (namely, excitation signal, signal detection circuits, and signal-processing program, etc.) need to be adjusted accordingly for a series of the testing frequencies. To simplify the optimization, we propose a method based on adjusting the parallel capacitance in this work. The impedance (inductance and internal resistance) of the sensing coil and its variation induced by particles are first measured, which are the necessary parameters for establishing the function relationship between the parallel capacitance and the relative impedance variation. With the function relationship, the relative impedance variation is calculated directly, and the optimal capacitance is located at the highest absolute value of it. The experimental results for the ferrous and nonferrous particles match the calculation results well. Interestingly, the optimal capacitance for the nonferrous particle was larger than that of the ferrous particle. We speculate that the difference is generated due to the increased resistance induced by the eddy current effect.

Research on the Influence of Coil LC Parallel Resonance on Detection Effect of Inductive Wear Debris Sensor.

The coil structure of the inductive wear debris sensor plays a significant role in the effect of wear debris detection. According to the characteristics of LC parallel resonance, the capacitor and coil are connected in parallel to make sensor coils in the LC parallel resonance state, which is beneficial to improve the ability to detect wear particles. In this paper, the mathematical model of output-induced electromotance of the detection coil is established to analyze the influence of the structure on the detection sensitivity and enhance the sensor’s current rate of change to the disturbance magnetic field, which is essential to resist noise interference. Based on the coherent demodulation principle, the AD630 lock-in amplifier is applied to the test platform to amplify and identify weak signals. In addition, experiments are designed to test the output signals of debris under the condition of different original output voltages of the sensor with a parallel structure. Meanwhile, the near-resonance state of the detection coil with LC parallel circuit is tested by output signal information. Results show that the sensor detection sensitivity will be effectively improved with the LC parallel coil structure. For the sensor structure parameters designed in this paper, the optimal raw output amplification voltage for abrasive particle detection is 4.49 V. The detection performance of ferromagnetic particles and non-ferromagnetic particles is tested under this condition, realizing the detection ability of 103.33 μm ferromagnetic abrasive particles and 320.74 μm non-ferromagnetic abrasive particles.

Remote detection of marine debris using Sentinel-2 imagery: A cautious note on spectral interpretations.

Remote detection of marine debris (also called marine litter) has received increased attention in the past decade, with the Multispectral Instruments (MSI) onboard the Sentinel-2A and Sentinel-2B satellites being the most used sensors. However, because of their mixed band resolutions and small sub-pixel coverage of debris within a pixel (e.g., <10%), caution is required when interpreting the spectral shapes of MSI pixels. Otherwise, the spectrally distorted shapes may be misused as spectral endmembers (signatures) or interpreted as from certain types of floating matters. Here, using simulations and MSI data, I show the origin of the spectral distortions and emphasize why both pixel averaging and pixel subtraction are critical in algorithm design and spectral interpretation for the purpose of remote detection of marine debris using Sentinel-2 MSI sensors.

Simulation and Observational Evaluation of Space Debris Detection by Sanya Incoherent Scatter Radar

AbstractThe Sanya incoherent scatter radar (SYISR) is a newly built active digital phased array, all solid‐state transmitting and digital receiving incoherent scatter radar in Sanya (18.3°N, 109.6°E). The radar frequency band is from 430 to 450 MHz. The Sanya site is a low latitude station in China dedicated for ionospheric investigation. Meanwhile, SYISR is also suitable for detecting a wide range of space debris because of its high power and flexible beam steering ability. In this paper, we first calculate the detectable lower limit size of space debris with respect to integration time and range based on SYISR parameters through theoretical simulation. Then, we selected several typical space debris, with a size near the theoretical detectable lower limit, to perform the experiment. We found that the estimated radar cross section versus range accorded well with the theoretical curve, which confirmed our simulation. Specifically, the detectable lower limit size of space debris is ∼8 cm in a range of 1,000 km given a threshold signal‐to‐noise ratio of 14 dB. This value decreases to ∼3 cm if a 200‐ms coherent integration is implemented. We further performed several experiments on objects with different inclinations using signals with 0.3 and 4 MHz under both static staring and tracking modes. In comparison with the two‐line element file predicted raw orbit, the tracking error of 0.3 and 4 MHz are 7 km and 400 m, respectively, without coherent integration in the processing. The study expands the function of the SYISR and should be beneficial to our ionospheric data inversion given the frequent occurrence of space debris around the SYISR.

Towards optimal foreign object debris detection in an airport environment

Foreign object debris (FOD) can critically damage aircraft engines as well as injure personnel in an airport environment. Airfield inspectors routinely inspect runways for the presence of FOD items, which differ in material, shape, and color, using conventional and automated methods. The major shortcoming of the current methods is their inability to detect all types of foreign objects in an accurate and timely manner for removal from the airport runways. In this study, we address this shortcoming, i.e., the lack of accuracy and timeliness in detection, by developing an object detection framework to detect FOD for quick removal from the airfields. Our proposed FOD detection framework consists of (i) unmanned aerial system (UAS) for inspecting and collecting data from the airfields, (ii) data preprocessing and augmentation techniques to counter the issue of learning on limited types of foreign objects, weather conditions, and airport surface materials that are present in the data sets, and (iii) a computer vision-based object detection model to attain high accuracy and faster inference time for deployment in a real-world airport environment. We generated the training data with the UAS at an air force range and developed various models, including the You Only Look Once (YOLO) object detector family of models (one-stage object detectors) in our framework. Our models are evaluated on previously unseen data collected by the UAS and a publicly available data set of FOD images. The experiment results demonstrate that our proposed approach with a version of the YOLO model (YOLOv4) with transfer learning provides a faster inference time for FOD detection and outperforms the other models in the precision and recall metric values.

Faint Space Debris Detection Algorithm Based on Small Aperture Telescope Detection System

Ground-based optical observation has unique advantages in space target observation. However, due to the weak light-gathering ability of small-aperture optoelectronic observation telescopes, the space debris in the image is weak and easily drowned in noise. In order to solve the above problems, we use digital image processing technology to extract faint space debris. We propose a high detection rate space debris automatic extraction algorithm, aiming to automatically detect space debris. We first establish a new space target description model. Our algorithm is mainly divided into two stages. The purpose of the first stage is to reduce the influence of a large number of stars. We perform wavelet transform and guided filtering for three consecutive frames, and the reconstructed wavelet that takes the median value can achieve the effect of eliminating stars. In the second stage, we adopt the method of robust principal component analysis and attribute the problem of target detection to the problem of separating the target and background of a single frame of image. After a large number of experimental results analysis, it is proved that the algorithm can effectively detect faint debris in the monitoring system of small aperture telescope, and has high precision and low computational complexity.

Monitoring of Plastic Islands in River Environment Using Sentinel-1 SAR Data

Plastics in the river environment are of major concern due to their potential pathways into the ocean, their persistence in the environment, and their impacts on human and marine health. It has been documented that plastic concentrations in riparian environments are higher following major rain events, where plastic can be moved through surface runoff. Considering the hazard that plastic waste poses to the environment, monitoring techniques are needed to aid in locating, monitoring, and remediating plastic waste within these systems. Dams are known to trap sediments and pollutants, such as metals and Polychlorinated Biphenyls (PCBs). While there is an established background on the monitoring of dams using the synoptic coverage provided by satellite imaging to observe water quality and volume, the detection of marine debris in riparian systems remains challenging, especially in cloudy conditions. Herein, we exploit the use of Synthetic Aperture Radar (SAR) to understand its capabilities for monitoring marine debris. This research focuses on detecting plastic islands within the Drina River system in Bosnia and Herzegovina and Serbia. Here, the results show that the monitoring of these plastic accumulations is feasible using Sentinel-1 SAR data. A quantitative analysis of detection performance is presented using traditional and state-of-the-art change detectors. The analysis of these detectors indicates that detectors that can utilise the coherent data from Single Look Complex (SLC) acquisitions are perform better when compared with those that only utilise incoherent data from Ground Range-Detected (GRD) acquisitions, with true positive detection ratings of ~95% with 0.1% false alarm rates seen in the best-performing detector. We also found that that the cross-pol VH channel provides better detection than those based on single-pol VV polarisation.

A Pixel-Wise Foreign Object Debris Detection Method Based on Multi-Scale Feature Inpainting

In the aviation industry, foreign object debris (FOD) on airport runways is a serious threat to aircraft during takeoff and landing. Therefore, FOD detection is important for improving the safety of aircraft flight. In this paper, an unsupervised anomaly detection method called Multi-Scale Feature Inpainting (MSFI) is proposed to perform FOD detection in images, in which FOD is defined as an anomaly. This method adopts a pre-trained deep convolutional neural network (CNN) to generate multi-scale features for the input images. Based on the multi-scale features, a deep feature inpainting module is designed and trained to learn how to reconstruct the missing region masked by the multi-scale grid masks. During the inference stage, an anomaly map for the test image is obtained by computing the difference between the original feature and its reconstruction. Based on the anomaly map, the abnormal regions are identified and located. The performance of the proposed method is demonstrated on a newly collected FOD dataset and the public benchmark dataset MVTec AD. The results show that the proposed method is superior to other methods.

A Detection Approach for Floating Debris Using Ground Images Based on Deep Learning

Floating debris has a negative impact on the quality of the water as well as the aesthetics of surface waters. Traditional image processing techniques struggle to adapt to the complexity of water due to factors such as complex lighting conditions, significant scale disparities between far and near objects, and the abundance of small-scale floating debris in real existence. This makes the detection of floating debris extremely difficult. This study proposed a brand-new, effective floating debris detection approach based on YOLOv5. Specifically, the coordinate attention module is added into the YOLOv5 backbone network to help the model detect and recognize objects of interest more precisely so that feature information of small-sized and dense floating debris may be efficiently extracted. The previous feature pyramid network, on the other hand, summarizes the input features without taking into account their individual importance when fusing features. To address this issue, the YOLOv5 feature pyramidal network is changed to a bidirectional feature pyramid network with effective bidirectional cross-scale connection and weighted feature fusion, which enhances the model’s performance in terms of feature extraction. The method has been evaluated using a dataset of floating debris that we built ourselves (SWFD). Experiments show that the proposed method detects floating objects more precisely than earlier methods.

Research on the influence of inductive wear particle sensor coils on debris detection

The debris detection characteristics of the inductive wear monitoring are researched by the method of combining theoretical research and simulation analysis in this paper. The mathematical model of the change in inductance is established based on the change in the coil magnetic field by the abrasive particles. By the COMSOL simulation software, the physical model of the three-coil wear monitoring is established, and the influence of the coil structure parameters on the output induced electromotance is compared and analyzed, resulting in the optimization of the coil parameters. For metal particles with different properties and sizes, the changes in the induced electromotance during the process of passing through the coil are analyzed, obtaining the mapping relationship between each particle size and the output induced electromotance. The simulation results show that the output voltage corresponding to the particles is related to the coil structure parameters, and the larger the particle size, the larger the output voltage. Finally, through experiments, the designed sensor coil structure has been proved to have a better detection effect on metal particles, realizing the detection of ferromagnetic abrasive particles above 100 µm and non-ferromagnetic abrasive particles above 200 µm.

In orbit testing of SOLID debris detector

The number of artificial objects in space increases due to past and present space activities. To analyse the quantity of the small (diameter >100 μm up to cm) space debris and meteoroids, an innovative in-situ impact detection method has been developed at DLR (German Aerospace Center) in Bremen, Germany. The method Solar panel-based Impact Detector “SOLID” uses solar panels for impact detection. Since solar panels provide large detection areas and exist on nearly all satellites, this method enables for the collection of large amounts of data in different orbits. An impacting object generates a permanent damage on a panel. The damage can be determined during analysis scan as well as confirmed or refuted in the frame of subsequent scans of the panels. Those properties of the sensor system can significantly improve the amount as well as the quality of measurement data to be used for environmental model validation. The SOLID method was successfully verified on ground by Hypervelocity Impact (HVI) tests at Fraunhofer EMI, Freiburg, Germany. The ability of the detection method SOLID for impact detection of space debris and meteoroids was clearly demonstrated on ground. Since July 2017, the SOLID sensor system is placed in a 600 km Sun-synchronous orbit on the microsatellite mission TechnoSat of Technische Universität Berlin (TUB). Four solar panels equipped with SOLID technology are installed on the satellite for in-orbit testing and environmental exploration. The total detection area of all panels is about 0.0755 m2. The system was designed to detect space debris or meteoroid objects with a diameter larger than 100 μm. In total 15,570,047 scans were performed over the four years in space. By means of measurement data changes were identified on one panel. However, so far, the telemetry data shows no clear evidence for an impact.

Development of Fault Diagnostics and Prognosis System Based on Digital Twin and Blockchain

In this paper, a development of fault diagnostics and prognosis system based on digital twin and blockchain is demonstrated. The main focus is to provide cheaper solution for maintenance operations, data safety, and machines’ life control. Initially, various details of prerequisites required by an engineer to conduct machinery condition monitoring is discussed. This include concepts of instrumentation, signal processing techniques such as vibration monitoring, motor volume signature analysis, and thermography where debris analysis and detection techniques are discussed. Furthermore, principles on how to operate maintenance operations in particular conditions illustrating the best techniques available for making a good maintenance decisions known as FEMCA (Failure Mode Effects and Criticality Analysis) are described. The experimental evaluation is performed to monitor the alignment of shaft and missing gear tooth using a simple locking mechanism using a sensor.

A Correction Method to Systematic Phase Drift of a High Resolution Radar for Foreign Object Debris Detection

Due to the small size and various types of foreign object debris (FOD), radar detection of FOD on airport runways is a great challenge, and there are often a large number of false alarms in the detection results. Arc-scanning synthetic aperture radar (AS-SAR) is an emerging method for detecting FOD targets, which achieves omnidirectional coverage with a very high azimuth resolution. However, this method faces a similar challenge. A direct way to reduce false alarms is to increase the detection threshold based on enhancing the target signal-to-noise ratio (SNR), and in this paper, the coherent accumulation of multiple images is used to improve the target SNR. The stable phase is also an important feature of the target distinguishing background. Therefore, it is important to maintain the stability of the target phase. Aiming at the systematic phase drift (SPD) caused by atmospheric disturbance and system hardware, a spatial and temporal model is established, a corresponding correction approach is proposed, and the performance of the correction approach is validated by field experiments.