Debris Detection Research Articles

Design of automatic tobacco trash detection system based on quadratic fuzzy theory

Abstract Fuzzy sets and deep learning models have accurate recognition accuracy in automatic detection. To be able to accurately identify tobacco debris and improve the quality of cigarettes, this paper proposes the design of a tobacco debris detection system with a deep learning model and fuzzy quadratic theory. The collected data is stored to AL422B by quadratic fuzzy set timing conversion, the cached image data is read by the microcontroller, the image pixel points are output, and the external controller and internal registers are set to read the tobacco image. The integrated Thumb extended instruction set to obtain the CPU clock frequency makes the controller interrupt and ensures PWM output. Integrate the internal fixed oscillator and external integrated control circuit to debug the program interface circuit to prevent power on and off misoperation. The negative log-likelihood function is obtained by following the activation rules given by the visible layer and hidden layer activation functions. The RBM is trained by quadratic fuzzy set estimation to optimize the parameters; test sample sets appear overfitting, combined with DBN pre-training and fine-tuning, iterative output, and labeling target data to meet the preset requirements to achieve intelligent detection of tobacco debris. The result analysis shows that the deep learning model and the quadratic fuzzy set generalization ability and accuracy are high, the highest F-value in tobacco clutter detection reaches 100%, and the system is designed to detect tobacco clutter automatically with high accuracy and good detection of clutter.

Detection of Floating Debris in the Lake Using Statistical Properties of Synthetic Aperture Radar Pulses

This study developed the European Space Agency (ESA) Setinel-1 Ground Range Detected (GRD) time series analysis model for monitoring floating debris in lake areas through Google Earth Engine Application Programming Interface. The study aims to monitor floating debris caused by heavy rainfall efficiently. Regarding water resources and water quality management, floating debris from multipurpose dams requires continuous monitoring from the initial generation stage. In the study, a Synthetic Aperture Radar (SAR) time series analysis model that is easy to identify water bodies was developed due to low accessibility in large areas. Although SAR satellite images could be used to observe inland water environments, debris detection on water surface surfaces has yet to be studied. For the first time, this study detected floating debris patches in a wide range of lakes from GRD imagery acquired by ESA’s Sentinel-1 satellite. It demonstrated the potential to distinguish them from naturally occurring materials such as invasive floating plants. In this study, the case of Daecheong Dam, in which predicted floating debris was detected after heavy rain using Sentinel-1 GRD data, is presented. It could quickly detect various floating debris flowing into dams used as a source of drinking water and serve as a reference for establishing a collection plan.

Motion simulation analysis of wear debris in an integrated detection unit for lubricating oil

Accurate wear debris detection is vital for diagnosing engine wear. However, due to uncertainties in debris behavior, size, and operating conditions, identifying different materials with a single sensor is challenging. To improve sensitivity and accuracy, we propose an integrated detection unit for wear debris in lubricating oil, emphasizing multifunction integration and active intervention. This unit includes a static mixer, a flared transition zone, and a sensor-equipped detection zone. Parametric analysis reveals that debris mixed in the static mixer tends to aggregate toward the center, forming three distinct distribution rings at the detection unit's outlet. A 90° blade angle and a 1:1 aspect ratio enhance the difference in debris quantity between inner and outer rings. To enhance detection reliability, installing capacitive sensors at the front and electromagnetic sensors at the rear of the detection zone can improve the accuracy of detecting different materials debris. This concept offers a multifunctional solution for precise wear debris detection, addressing complex wear scenarios in engines.

Cross-Contamination of Ignitable Liquid Residues on Wildfire Debris—Detection and Characterization in Matrices Commonly Encountered at Wildfire Scenes

Ignitable liquid residue (ILR) samples play an important role in fire investigations. Similar to other types of forensic evidence, maintaining sample integrity depends on the prevention of cross-contamination during both storage and transport. This study examines cross-contamination in ILR samples on various sample matrices (gravel, soil, wood). After inducing leaks in a controlled environment, sample analysis by GC×GC-ToF MS allowed for sensitive detection and in-depth characterization of cross-contamination processes. The potential for false positive identification of ILR is notably present due to cross-contamination. Compound transmission for a mid-range ILR (gasoline), for instance, was detectable after a 1 h exposure, with a complete profile transfer occurring after 8 h regardless of the matrix type. Visual comparisons and uptake rate calculations further confirmed matrix interaction effects taking place in the form of inherent native compound interference and adsorbate–adsorbate interaction during transmission and extraction processes for soil and wood matrices. Chemometric analysis highlighted the advantage of employing statistical analysis when investigating samples under matrix interactions by identifying several statistically significant compounds for reliably differentiating cross-contamination from background and simulated positive samples in different volatility ranges and compound classes. Untargeted analysis tentatively identified three additional compounds of interest within compound classes not currently investigated in routine analysis. The resulting classification between background, contaminated, and simulated positive samples showed no potential for false positive ILR identification and improved false negative errors, as evidenced by classification confidences progressing from 88% for targeted and 93% for untargeted to 95% for a diagnostic ratio analysis of three ratios deployed in tandem.

Observations of plasma waves generated by charged space objects

A sampling of the environment around inert space objects has determined, which linear and nonlinear waves are created by moving space debris of all sizes. Plasma waves excited by satellites and space debris moving through the Earth's plasma in low earth orbit have been measured with in situ electric field sensors on other satellites. These orbit driven plasma waves are of interest for proximity detection of space debris and sources of electrostatic and electromagnetic noise on spacecraft. Satellites and other space objects moving through the near-earth ionosphere between 200 and 1000 km altitude become electrically charged by both electron collection and photo emission in sunlight. These hypersonic, charged objects can excite a wide range of plasma waves. Measurements with the Radio Receiver Instrument (RRI) on the Swarm-E satellite have shown that electromagnetic plasma waves from known objects can be observed out to ranges of tens of kilometers. The amplitude, spectral, and polarization changes of the RRI data are consistent with electromagnetic, compressional Alfvén waves launched by charged space objects traveling across magnetic field lines. In addition, electrostatic lower hybrid waves or nonlinear ion acoustic pinned oscillations may have been self-generated and measured on the Swarm-E satellite. It is proposed that measurements of these waves with local electric field measurements or remote electromagnetic wave scatter may be useful to design systems for the location of orbiting objects. Spatial and temporal details of spacecraft charging are key to understanding the extent of waves associated with the object motion in space plasmas.

Space Surveillance payload camera breadboard: Star tracking and debris detection algorithms

Space debris threatens space activities, demanding continuous observation and tracking by the Space Surveillance Network (SSN) to secure the Earth’s orbits. However, SST efforts are limited by the size and brightness of the debris, detecting only a small amount of the total. Seeking to overcome such limitations, this study proposes an alternative payload camera capable of extracting the attitude of a satellite in orbit and detecting under-catalogued debris. This work is a sequential study of previous research, where the camera breadboard was designed and implemented. The contribution of this paper is the evaluation of star tracking and space debris algorithms to be implemented in the payload camera, the development and implementation of a new hybrid algorithm and the elaboration of performance metrics for comparison between the algorithms. The observation data of the previous research was used as input for the algorithms’ tests. For star identification and, consequently, attitude extraction, the chosen algorithm was Tetra. The results were compared to the standard star identification software, Astrometry.net, to assess the attitude accuracy. For debris detection, ASTRiDE and the Hybrid time-index image algorithms were used. A comparison of the results was made to establish a performance evaluation metric in terms of detectability, time, and computational cost.

Dim Staring Debris Targets Detection Method with Dense Long Trailing Star

With the gradual increase in spacecraft in orbit, space debris monitoring has become the key to the sustainable development of space missions. A staring debris detection method is proposed for high-density stars with long tails. In order to solve the problem that the gray level of a long trailing image is not stable and continuous, rectangular fitting is used to complete the aggregation of the trailing image and reduce the influence of noise on the trailing information. The occluded state of the target was analyzed, the feature calculation method was improved, the semi-occluded scene was statistically classified, the fully connected network (FCN) based finite point feature was accurately classified, and the semi-occluded image was extracted. Based on the extracted semi-occluded image, the inter-frame association can improve the success probability of target association and realize the effective detection and tracking of debris. The detection accuracy was tested for the changing inter-frame interval and signal-to-noise ratio (SNR), and the relationship between the index parameters and key parameters was given. Compared with previous literature, this design can detect and track the occluded target with a detection rate of more than 90% and a false alarm rate of less than 10%.

On-orbit optical detection of lethal non-trackable debris

Resident space objects in the size range of 0.1 mm–3 cm are not currently trackable but have enough kinetic energy to have lethal consequences for spacecraft. The assessment of small orbital debris, potentially posing a risk to most space missions, requires the combination of a large sensor area and large time coverage. For example, a sensor with a time•area product of 3 m2-years is considered sufficient to make a significant contribution to our understanding of the near-Earth small debris population. Deploying large sensors, however, is generally resource intensive, due to their size and weight. The lightsheet sensor concept, allows the creation of a “virtual witness plate”, which is created without any supporting physical structure and therefore presents an attractive opportunity for the detection small debris anywhere between low Earth orbit and interplanetary space. This sensor project is called Lightsheet Anomaly Resolution And Debris Observation (LARADO). Recent technology maturation efforts in the laboratory have successfully detected small debris (1.6 mm diameter) moving at 6.38 km/s. NRL is building the NASA funded the LARADO instrument as a technology maturation effort for a flight demonstration on STPSat-7 in 2025. In this presentation, we will describe the LARADO instrument, present the laboratory data and analysis, and describe the instrument details for the STPSat-7 spacecraft slated for launch via the DoD Space Test Program in CY2025.

Seismic urban damage map generation based on satellite images and Gabor convolutional neural networks

Rapid assessment of urban damages after a strong earthquake is a necessary and crucial task to reduce the number of fatalities and recover socioeconomic services. In this paper, a novel deep-learning-based framework is proposed for detecting and mapping damages in urban buildings and roads using post-earthquake high-resolution satellite imagery. The method begins with overlaying a pre-event vector map on an input image to extract the building and road objects. The core machine learning components include two separate convolutional neural networks (CNN), integrated with Gabor filters, which extract debris pixels associated with building and road objects. These debris pixels are analyzed to generate the final damage maps, which show multiple damage degrees for buildings and roads. Two different datasets were used to thoroughly evaluate the proposed method's overall effectiveness. The overall accuracy of 95% for detecting the debris pixels in building and road areas proves the effectiveness of the proposed CNN models for debris detection in comparison to the traditional Machine Learning (ML) methods. The proposed method successfully labelled 84% of the buildings and 87% of the roads when compared with a manually generated multiple damage map.

Magnetic coupling properties of multiple metal wear particles for high-precision electromagnetic debris detection applications

The electromagnetic wear particle detector is one of effective method to monitor wear debris in lubricating oil for assessing the wear condition of mechanical equipment. However, the motion of wear particles, especially the aggregation behavior in both fluid field and magnetic field, may make the particle detector generate false wear signals. Therefore, to estimate the impact on the detection accuracy of wear debris by the particle aggregation effect, the magnetic coupling model of multiple wear particles is established for studying the magnetic coupling effect between adjacent metal particles. The research results show that the effect changes the total magnetic energy variation induced by the particles and then affects the amplitude of particle signal. Meanwhile, the variation degree is closely associated with the frequency of magnetic field of particle detectors. Overall, the aggregation of wear particles with the same magnetic properties (both ferromagnetic or non-ferromagnetic) leads to false alarms of particle detectors; and the aggregation of wear particles with different magnetic properties causes missing alarms of particle detectors. Meanwhile, increasing the field frequency may increases the probability of missing alarm failure of particle detectors.

A robust FOD acoustic detection method for rocket tank final assembly process

The presence of Foreign Object Debris (FOD) during the assembly of rocket tanks poses a significant risk to the success of rocket launches. The current manual listening method which relies on the human ear for detecting FOD in rocket tanks is limited by its low level of automation and poor robustness. To overcome these limitations, this study presents a Robust Foreign Object Debris Detection (RFODD) method that utilizes an Adaptive Wiener Filter (EDAWF) based on energy variation and an Adaptive Forgetting Factor Gaussian Mixture Model (AFFGMM). EDAWF improves the input signal quality, while AFFGMM addresses the challenge of updating parameters under time-varying signals. FOD detection is then performed through a multi-segment counting method and a criterion based on the anomaly percentage index. The proposed RFODD method was evaluated through an experimental study on a rocket tank and was found to offer a more robust and automated solution for FOD detection with engineering applications.

Research on Enhanced Orbit Prediction Techniques Utilizing Multiple Sets of Two-Line Element

Acquiring accurate space object orbits is crucial for many applications such as satellite tracking, space debris detection, and collision avoidance. The widely used two-line element (TLE) method estimates the position and velocity of objects in space, but its accuracy can be limited by various factors. A combination of multiple TLEs and advanced modeling techniques such as batch least squares differential correction and high-precision numerical propagators can significantly improve TLE accuracy and reliability, ensuring better space object surveillance. Previous studies analyzed additional factors that may influence TLE accuracy and evaluated the accuracy of Starlink TLE using precise ephemeris data from SpaceX. The results indicate that utilizing multiple TLEs for precise orbit determination can significantly enhance the performance of orbit prediction methods, particularly when compared to SGP4. By leveraging 10-day Starlink TLEs, the accuracy of 5-day predictions can be improved by approximately twofold. Additionally, producing two pseudo-observations within an orbital period near the TLE epoch yields the greatest effect on prediction accuracy, with this distribution of pseudo-observations increasing accuracy by approximately 10% compared to a uniform distribution. Further research can explore more data fusion and machine learning approaches to optimize operations in space.

Satellite Star Tracker Breadboard with Space Debris Detection Capability for LEO

This paper evaluates the possibility of having a star tracker device running space debris algorithms. A simple star tracker breadboard was developed to evaluate the possibility of having a device running both stellar identification and space debris algorithms. The breadboard was built with commercial off-the-shelf components, representing the current star tracker resolution and field of view. A star tracker device and space debris algorithms were implemented and tested, respectively: Tetra and ASTRiDE. The device concept was tested by taking pictures of the night sky with satellite streaks. Seeking to overcome such limitations, a dual-purpose star tracker with stars detection and optical debris detection capability is proposed. Star trackers are usually used in satellites for attitude determination and therefore have a vast potential to be a major tool for space debris detection. The rapid increase of space debris poses a risk to space activities, so it is vital to detect it. Ground-based radar and optical telescope techniques used for debris detection are limited by a size threshold, detecting only a tiny amount of the total, reason why evaluating the possibility of detecting them in space is of major importance.

Application of a Wear Debris Detection System to Investigate Wear Phenomena during Running-In of a Gasoline Engine

When a tribological system is operated for the first time, the first hours of operation are of the utmost importance as the surfaces of the contacting elements mate to each other, involving significant wear processes until the surfaces reach stable topological characteristics. This initial phase in a combustion engine is known as running-in and is of critical importance in the study of friction and wear phenomena. Despite this, there is little information in the literature dedicated to running-in and, therefore, data improving its understanding is greatly anticipated. In this work, a novel wear debris detection system measuring in real time was employed to investigate the running-in of an inline 4-cylinder gasoline engine; it consists primarily of an optical sensor with the capability of detecting very small particles from 4 μm. For the tests, the engine was mounted on a test bench and operated under stationary working conditions. The results of the wear debris measurements showed interesting insights into the engine running-in process; although in general, the results followed the expected trend, they also showed an unexpected behavior: it was expected to obtain the highest amounts of wear debris at the beginning of the running-in, but instead the number of debris stagnated and only started to increase after about 20 h to then decrease again. The best operating conditions to run-in the engine were identified at the middle of the running-in period, without the presence of large wear debris that could lead to severe wear. Finally, it was found that the engine running-in was not finished until at least 75 h of operation, although commonly, a running-in time of 10 h is used in the industry.

Deep space debris—Detection of potentially hazardous asteroids and objects from the southern hemisphere

Space debris are composed of both natural and human made objects, some in near Earth orbits while others are passing through deep space. Asteroids may represent one form of near Earth and deep space debris. In this article we report on a set of asteroid observations from the southern hemisphere. We indicate that Apollo and Aten class asteroids represent another form of deep space debris of a potentially hazardous nature to orbiting spacecraft and/or Earth based locations. We also show some of the operational challenges, types of facilities and the importance of geographic diversity, that is, necessary for detecting, observing and characterising asteroids, especially PHA’s. For many years, space agencies and institutions have observed and monitored near Earth asteroids and objects (NEO’s) using high gain radio frequency antennas and optical telescopes in the northern hemisphere (GSSR, Arecibo, Catalina, Pan-STARRS, Atlas and Linear) 1) However a regular operational system to monitor the southern skies does not have the same level of maturity and is where a percentage of asteroids and various human made objects are not detected until they pass into northern skies. To fill that gap the Southern Hemisphere Asteroid Radar Program (SHARP) 2) located in Australia uses available antenna time on either a 70 or 34 m beam waveguide antenna located at the Canberra Deep Space Communication Complex (CDSCC) to transmit a Doppler compensated continuous radio wave at 2.114 GHz (14.2 cm) and 7.15945 GHz (4.2 cm) toward the NEO and receive its echoes at the 64 m Parkes or 6 m × 22 m Australia Telescope Compact Array (ATCA) antennas at Narrabri in Australia. This mode of NEO observation is termed a deep space bistatic radar. The southern hemisphere program has also recently been joined by the 12 m University of Tasmania antennas at Hobart (Tasmania) and Katherine (Northern Territory). Combining SHARPS bistatic radar with small optical apertures located at the University of New South Wales (UNSW) and University of Western Australia (UWA) allows combined optical/RF NEO detections. Whilst sub-metre class optical instruments have contributed independently to asteroid detection over decades, the use of coordinated small 0.3–0.5 m instruments synchronized to large asteroid radars offers an observational flexibility and adaptability when larger optical systems 3) are dedicated to other forms of professional optical astronomy. Since 2015, SHARP has illuminated and tracked over 30 NEO’s ranging in diameter from 7 to 5000 m at ranges of 0.1–18 lunar distances (LD) from Australia.

High-precision density mapping of marine debris and floating plastics via satellite imagery

The last couple of years has been ground-breaking for marine pollution monitoring purposes. It has been suggested that combining multi-spectral satellite information and machine learning approaches are effective to monitor plastic pollutants in the ocean environment. Recent research has made theoretical progress in identifying marine debris and suspected plastic (MD&SP) through machine learning whereas no study has fully explored the application of these methods for mapping and monitoring marine debris density. Therefore, this article consists of three main components: (1) the development and validation of a supervised machine learning marine debris detection model, (2) to map the MD&SP density into an automated tool called MAP-Mapper and finally (3) evaluation of the entire system for out-of-distribution (OOD) test locations. Developed MAP-Mapper architectures provide users with options to achieve high precision (abbv. -HP) or optimum precision-recall (abbv. -Opt) values in terms of training/test dataset. Our MAP-Mapper-HP model greatly increases the MD&SP detection precision to 95%, while the MAP-Mapper-Opt achieves 87–88% precision–recall pair. To efficiently measure density mapping findings at OOD test locations, we propose the Marine Debris Map (MDM) index, which combines the average probability of a pixel belonging to the MD&SP class and the number of detections in a given time frame. The high MDM findings of the proposed approach are found to be consistent with existing marine litter and plastic pollution areas, and these are presented with available evidence citing literature and field studies.

Mapping of marine litter on the seafloor using WASSP S3 multibeam echo sounder and Chasing M2 ROV

Marine litter is a growing threat to the marine environment. Mapping of marine litter is becoming increasingly important to detect its potential hotspots and prevent their spread. In this paper, the applicability of the multibeam echo sounder (MBES) WASSP S3 and remotely operated underwater vehicle (ROV) Chasing M2 was tested in the detection and mapping of marine litter on the seafloor within the wider area of the St. Ante Channel (Šibenik, Croatia). Also, the precision assessment of WASSP S3 was tested at different cruising speeds. Results have shown that Chasing M2 can be used effectively for the initial detection of marine debris in shallow waters. However, if the underwater navigation and positioning system and auxiliary measurement scales are not used, the ROV has limited capabilities in deriving morphometric parameters of marine litter on the seafloor. This was determined by comparing the 3D model of a tire which was derived using video photogrammetry captured with ROV and the 3D model of a tire which was produced using a hand-held 3D scanner. Furthermore, the results have shown the WASSP S3 is not suitable for identifying marine litter smaller than 1 m at depths up to 10 m. The MBES WASSP S3 can detect marine litter that has a minimum area of 100 * 100 cm and a height of around 40 cm at depths up to 10 m. The results pointed to the need for caution when choosing an adequate sensor to detect and map marine litter on the seafloor. In addition, MBES interval measurements have shown that WASSP S3 precision is in the centimeter range (<10 cm) at different cruising speeds. The obtained results have helped to establish the guidelines for the integrated use of MBES, ROV, and UAV in the detection of marine litter on the seafloor.

Design of an optical system for a Multi-CubeSats debris surveillance mission

The detection and observation of space debris in Low Earth Orbit is generally carried out through the use of ground based radars and telescopes. These instruments allow for a precise reconstruction of the space debris trajectories, and therefore represent a key asset for planning avoidance maneuvers when threats of collisions are predicted.The recent deployment of mega-constellations, with the consequent increase of the number of satellites, imposes new challenges in terms of simultaneous tracking capability and readiness of the current space situational awareness systems. This adds to the current need to track small and dull objects to further mitigate the probability of triggering cascade collisions. However, ground based observations are limited due to their intrinsic sensibility to atmospheric refraction, their diurnal inoperability and their dependence on meteorological hazards.This paper proposes to study the feasibility and the benefits of a potential deployment of a constellation of CubeSats in Low Earth Orbit, to acquire optical observations of space debris with enhanced accuracy, as part of the ORCA mission: Orbit Refinement for Collision Avoidance. Here, the focus is on the optical design of the payload instrument to be integrated onboard of the orbiting platforms.The study trades-off the current state-of-art of optical detection technologies, by assessing their performance against a set of specific requirements: (a) the minimization of the uncertainty associated to the image resolution; (b) a field of view that maximizes the extent of the monitored area; (c) an optimal exposure time to avoid under or overexposure of the image; (d) minimization of the effects of light diffraction and above all, (e) the maximization of the signal to noise ratio to detect the smallest and dullest objects possible.Several configurations of optical systems are then chosen as suitable for the ORCA constellation, also considering the system design implications of its integration into a CubeSat, such as size requirements. Commercial Off-The-Shelf hardware are explored and performances of the optical system are evaluated through numerical simulations in order to estimate the detectable sizes of space debris while taking into account their potential distances from the sensor. This paper concludes with estimates of the impact of the ORCA mission on space situational awareness for decades to come.

SDebrisNet: A Spatial–Temporal Saliency Network for Space Debris Detection

The rapidly growing number of space activities is generating numerous space debris, which greatly threatens the safety of space operations. Therefore, space-based space debris surveillance is crucial for the early avoidance of spacecraft emergencies. With the progress in computer vision technology, space debris detection using optical sensors has become a promising solution. However, detecting space debris at far ranges is challenging due to its limited imaging size and unknown movement characteristics. In this paper, we propose a space debris saliency detection algorithm called SDebrisNet. The algorithm utilizes a convolutional neural network (CNN) to take into account both spatial and temporal data from sequential video images, which aim to assist in detecting small and moving space debris. Firstly, taking into account the limited resource of the space-based computational platform, a MobileNet-based space debris feature extraction structure was constructed to make the overall model more lightweight. In particular, an enhanced spatial feature module is introduced to strengthen the spatial details of small objects. Secondly, based on attention mechanisms, a constrained self-attention (CSA) module is applied to learn the spatiotemporal data from the sequential images. Finally, a space debris dataset was constructed for algorithm evaluation. The experimental results demonstrate that the method proposed in this paper is robust for detecting moving space debris with a low signal-to-noise ratio in the video. Compared to the NODAMI method, SDebrisNet shows improvements of 3.5% and 1.7% in terms of detection probability and the false alarm rate, respectively.

Enhancing Spatial Debris Material Classifying through a Hierarchical Clustering-Fuzzy C-Means Integration Approach

This paper presents a novel approach for clustering spectral polarization data acquired from space debris using a fuzzy C-means (FCM) algorithm model based on hierarchical agglomerative clustering (HAC). The effectiveness of the proposed algorithm is verified using the Kosko subset measure formula. By extracting characteristic parameters representing spectral polarization from laboratory test data of space debris samples, a characteristic matrix for clustering is determined. The clustering algorithm’s parameters are determined through a random selection of points in the external field. The resulting algorithm is applied to pixel-level clustering processing of spectral polarization images, with the clustering results rendered in color. The experimental results on field spectral polarization images demonstrate a classification accuracy of 96.92% for six types of samples, highlighting the effectiveness of the proposed approach for space debris detection and identification. The innovation of this study lies in the combination of HAC and FCM algorithms, using the former for preliminary clustering, and providing a more stable initial state for the latter, thereby improving the effectiveness, adaptability, accuracy, and robustness of the algorithm. Overall, this work provides a promising foundation for space debris classification and other related applications.