Small Detector Research Articles

Beam quality correction factors for dose measurements around 192Ir brachytherapy sources.

To provide beam quality correction factors ( ) for detectors used in 192Ir brachytherapy dosimetry measurements. Ten detectors were studied, including the PTW 30013 and Exrading12 Farmer large cavity chambers, seven medium (0.1-0.3cm3) and small(<0.1cm3) cavity chambers, and a synthetic microdiamond detector. The kQ,Qo correction factors were calculated at distances from 1 to 10cm away from an 192Ir source, using the EGSnrc Monte Carlo (MC) code. All detectors were calibrated in a 60Co 10×10cm2 reference field provided by standard calibration laboratories. The impact of the central electrode, stem and wall on the detectors' responses in 192Ir photon energies was investigated. An experimental procedure was additionally applied for dose measurements around a microSelectron-v2 192Ir high dose rate (HDR) brachytherapy source using a motorized water phantom. Farmer chambers underestimated the dose near the source due to signal volume averaging effects, resulting in kQ,Qo values ranging from 1.177 and 1.317 at 1cm, decreasing with distance to between 0.980 and 1.005 at 10cm. Small cavity volume detectors should be used close to the source. The kQ,Qo for the studied small and medium cavity volume detectors were found to be close to unity (within 1.3%), showing also a small dependence on source-to-detector distance, except for ion chambers containing high-Z materials in their construction. The presence of high-Z materials caused an overresponse in these detectors, resulting in kQ,Qo values ranging from 0.950 at 1cm to 0.729 at 10cm away from the source. A dose rate constant of (1.114±0.023)cGyh-1U-1 was found in agreement with the literature (within 0.5%). kQ,Qo values were calculated for dose measurements around 192Ir brachytherapy sources. Farmer chambers should be preferred for measurements at increased distances, whereas small or medium cavity volume detectors, not containing high-Z materials, should be used close to the source.

Toward Versatile Small Object Detection with Temporal-YOLOv8.

Deep learning has become the preferred method for automated object detection, but the accurate detection of small objects remains a challenge due to the lack of distinctive appearance features. Most deep learning-based detectors do not exploit the temporal information that is available in video, even though this context is often essential when the signal-to-noise ratio is low. In addition, model development choices, such as the loss function, are typically designed around medium-sized objects. Moreover, most datasets that are acquired for the development of small object detectors are task-specific and lack diversity, and the smallest objects are often not well annotated. In this study, we address the aforementioned challenges and create a deep learning-based pipeline for versatile small object detection. With an in-house dataset consisting of civilian and military objects, we achieve a substantial improvement in YOLOv8 (baseline mAP = 0.465) by leveraging the temporal context in video and data augmentations specifically tailored to small objects (mAP = 0.839). We also show the benefit of having a carefully curated dataset in comparison with public datasets and find that a model trained on a diverse dataset outperforms environment-specific models. Our findings indicate that small objects can be detected accurately in a wide range of environments while leveraging the speed of the YOLO architecture.

Rigid propagation of visual motion in the insect’s neural system

In the pursuit of developing an efficient artificial visual system for visual motion detection, researchers find inspiration from the visual motion-sensitive neural pathways in the insect’s neural system. Although multiple proposed neural computational models exhibit significant performance aligned with those observed from insects, the mathematical basis for how these models characterize the sensitivity of visual neurons to corresponding motion patterns remains to be elucidated. To fill this research gap, this study originally proposed that the rigid propagation of visual motion is an essential mathematical property of the models for the insect’s visual neural system, meaning that the dynamics of the model output remain consistent with the visual motion dynamics reflected in the input. To verify this property, this study uses the small target motion detector (STMD) neural pathway — one of the visual motion-sensitive pathways in the insect’s neural system — as an exemplar, rigorously demonstrating that the dynamics of translational visual motion are rigidly propagated through the encoding of retinal measurements in STMD computational models. Numerical experiment results further substantiate the proposed property of STMD models. This study offers a novel theoretical framework for exploring the nature of the visual motion perception underlying the insect’s visual neural system and brings an innovative perspective to the broader research field of insect visual motion perception and artificial visual systems.

YOLO-ResTinyECG: ECG-based lightweight embedded AI arrhythmia small object detector with pruning methods

ObjectiveThis study presents a YOLO-ResTinyECG, a novel model for small object detection in electrocardiogram (ECG) images, emphasizing longer time-window lengths for improving the throughput of arrhythmia detection. Methods: The proposed ResTinyECG backbone consists of four-stage Res-blocks (2/4/3/2) with input ECG image sizes of 320 × 320 × 1 pixels and 160 × 160 × 1 pixels, with a significant parameter reduction of around 20 %/95 %/74 % compared to existing backbones like Shufflenet-v2/CSPDarknet53-tiny and the latest YOLOv7-tiny structure. Moreover, this study applied magnitude-based filter pruning and dependency graph (DepGraph) pruning for parameter optimization. The ECG images undergo processing with time-window lengths of 5/10/15/20 s, accompanied by min–max normalization, and weighted loss is applied for class balance during learning, and non-maximum suppression with edge removal is used to compute and select the final output bounding boxes of ECG heartbeats. Experiments: Experiments conducted on the PhysioNet MIT-BIH arrhythmia ECG database focus on nine classes, including normal (N), atrial premature beat (A), ventricular premature beat (V), left bundle branch block (L), right bundle branch block (R), fusion of ventricular beat (FVN), paced beat (P), fusion of paced and normal beat (FPN), and others (remaining heartbeats). Results: The proposed ResTinyECG-320 exhibits impressive mean Average Precision (mAP) scores of 94.76 %/94.85 %/93.96 %/87.12 % in 6-class detection and 92.35 %/91.96 %/90.58 %/83.34 % in 9-class detection across different time-window lengths. The model demonstrates only a marginal 7 %∼9% decrease in performance when utilizing longer time-window lengths. After applying magnitude-based filter pruning, ResTinyECG can be reduced to a minimal 0.1 million parameters. Furthermore, ResTinyECG-160 achieves a competitive mAP of 93.92 % in 6-class detection and a faster processing speed of 100.6 ECG segments per second (SPS) on a PC compared to Shufflenet-v2 (77.3 SPS). In conclusion, YOLO-ResTinyECG surpasses existing backbones, exhibiting superior mAP in both 6/9-class detection scenarios, and its deployment on an embedded AI platform validates its real-time detection capabilities.

AF-DETR: efficient UAV small object detector via Assemble-and-Fusion mechanism

AF-DETR: efficient UAV small object detector via Assemble-and-Fusion mechanism

Enhanced and lightweight design of small object detector based on YOLOv5s model

Enhanced and lightweight design of small object detector based on YOLOv5s model

A hyper-fast gas chromatograph coupled to an ion mobility spectrometer with high repetition rate and flow-optimized ion source to resolve the short chromatographic peaks

By combining the high selectivity of a gas chromatograph (GC) with the high sensitivity and decent selectivity of an ion mobility spectrometer (IMS), GC-IMS have become increasingly popular in many applications. However, most GC suffer from long analysis times. In contrast, an hyper-fast GC allows for extremely fast analysis in the tens of seconds while reaching comparably high resolution. In turn, coupling such hyper-fast GC with IMS requires sufficiently high repetition rate of recording full IMS spectra to resolve the short GC peaks. Therefore, we present a drift tube IMS with 100 Hz repetition rate. Key is a small effective detector volume combined with short drift length. Therefore, the ion source of the IMS combines a small reaction region with an extended field-switching ion shutter and optimized gas flows. To resolve even the shortest GC peaks with a full width at half maximum of 100 ms, a short drift length of just 41 mm was used, achieving a measurement time of 10 ms per spectrum and hence ten data points across the shortest GC peak. To avoid condensation of the sample, the entire IMS was heated isothermally to 120 °C. Despite short drift times and high temperatures, the IMS still reaches high resolving power of Rp = 60. The hyper-fast GC-IMS reaches low detection limits in the low ppbV range. For demonstration, ketone mixes and three different hop varieties were analyzed in <30 s.

AID-YOLO: An Efficient and Lightweight Network Method for Small Target Detector in Aerial Images

The progress of object detection technology is crucial for obtaining extensive scene information from aerial perspectives based on computer vision. However, aerial image detection presents many challenges, such as large image background sizes, small object sizes, and dense distributions. This research addresses the specific challenges relating to small object detection in aerial images and proposes an improved YOLOv8s-based detector named Aerial Images Detector-YOLO(AID-YOLO). Specifically, this study adopts the General Efficient Layer Aggregation Network (GELAN) from YOLOv9 as a reference and designs a four-branch skip-layer connection and split operation module Re-parameterization-Net with Cross-Stage Partial CSP and Efficient Layer Aggregation Networks (RepNCSPELAN4) to achieve a lightweight network while capturing richer feature information. To fuse multi-scale features and focus more on the target detection regions, a new multi-channel feature extraction module named Convolutional Block Attention Module with Two Convolutions Efficient Layer Aggregation Net-works (C2FCBAM) is designed in the neck part of the network. In addition, to reduce the sensitivity to position bias of small objects, a new function, Normalized Weighted Distance Complete Intersection over Union (NWD-CIoU_Loss) weight adaptive loss function, was designed in this study. We evaluate the proposed AID-YOLO method through ablation experiments and comparisons with other advanced models on the VEDAI (512, 1024) and DOTAv1.0 datasets. The results show that compared to the Yolov8s baseline model, AID-YOLO improves the mAP@0.5 metric by 7.36% on the VEDAI dataset. Simultaneously, the parameters are reduced by 31.7%, achieving a good balance between accuracy and parameter quantity. The Average Precision (AP) for small objects has improved by 8.9% compared to the baseline model (YOLOv8s), making it one of the top performers among all compared models. Furthermore, the FPS metric is also well-suited for real-time detection in aerial image scenarios. The AID-YOLO method also demonstrates excellent performance on infrared images in the VEDAI1024 (IR) dataset, with a 2.9% improvement in the mAP@0.5 metric. We further validate the superior detection and generalization performance of AID-YOLO in multi-modal and multi-task scenarios through comparisons with other methods on different resolution images, SODA-A and the DOTAv1.0 datasets. In summary, the results of this study confirm that the AID-YOLO method significantly improves model detection performance while maintaining a reduced number of parameters, making it applicable to practical engineering tasks in aerial image object detection.

Localized and Long-Lasting Adaptation in Dragonfly Target-Detecting Neurons.

Some visual neurons in the dragonfly (Hemicordulia tau) optic lobe respond to small, moving targets, likely underlying their fast pursuit of prey and conspecifics. In response to repetitive targets presented at short intervals, the spiking activity of these "small target motion detector" (STMD) neurons diminishes over time. Previous experiments limited this adaptation by including intertrial rest periods of varying durations. However, the characteristics of this effect have never been quantified. Here, using extracellular recording techniques lasting for several hours, we quantified both the spatial and temporal properties of STMD adaptation. We found that the time course of adaptation was variable across STMD units. In any one STMD, a repeated series led to more rapid adaptation, a minor accumulative effect more akin to habituation. Following an adapting stimulus, responses recovered quickly, though the rate of recovery decreased nonlinearly over time. We found that the region of adaptation is highly localized, with targets displaced by ∼2.5° eliciting a naive response. Higher frequencies of target stimulation converged to lower levels of sustained response activity. We determined that adaptation itself is a target-tuned property, not elicited by moving bars or luminance flicker. As STMD adaptation is a localized phenomenon, dependent on recent history, it is likely to play an important role in closed-loop behavior where a target is foveated in a localized region for extended periods of the pursuit duration.

Evaluation of the usefulness of small detectors made of Gafchromic EBT3 film for measurements in areas with high dose gradient and without charged-particle equilibrium (CPE)

Evaluation of the usefulness of small detectors made of Gafchromic EBT3 film for measurements in areas with high dose gradient and without charged-particle equilibrium (CPE)

First Results of the CREDO-Maze Cosmic Ray Project

The CREDO-Maze project is the concept for a network of stations recording local, extensive cosmic ray air showers. Each station consists of four small scintillation detectors and a control unit that monitors the cosmic ray flux 24 h a day and transmits the results to the central server. The modular design of each array allows the results to be used in educational classes on nuclear radiation, relativistic physics, and particle physics and as a teaching aid in regular school classrooms and more. As an example, we present here some preliminary results from the CREDO-Maze muon telescope missions to the Arctic and down into a deep salt mine, as well as the first shower-particle correlation measurements from a table-top experiment at Walailak University. These experiments show that the different geometric configurations of the CREDO-Maze detector set can be used for projects beyond the scope of the secondary school curriculum, and they can form the basis of student theses and dissertations at universities.

Clinical boundary conditions for propagation-based X-ray phase contrast imaging: from bio-sample models targeting to clinical applications.

Typical propagation-based X-ray phase contrast imaging (PB-PCI) experiments using polyenergetic sources are tested in very ideal conditions: low-energy spectrum (mainly characteristic X-rays), small thickness and homogeneous materials considered weakly absorbing objects, large object-to-detector distance, long exposure times and non-clinical detector. Explore PB-PCI features using boundary conditions imposed by a low power polychromatic X-ray source (X-ray spectrum without characteristic X-rays), thick and heterogenous materials and a small area imaging detector with high low-detection radiation threshold, elements commonly found in a clinical scenario. A PB-PCI setup implemented using a microfocus X-ray source and a dental imaging detector was characterized in terms of different spectra and geometric parameters on the acquired images. Test phantoms containing fibers and homogeneous materials with close attenuation characteristics and animal bone and mixed soft tissues (bio-sample models) were analyzed. Contrast to Noise Ratio (CNR), system spatial resolution and Kerma values were obtained for all images. Phase contrast images showed CNR up to 15% higher than conventional contact images. Moreover, it is better seen when large magnifications (>3) and object-to-detector distances (>13 cm) were used. The influence of the spectrum was not appreciable due to the low efficiency of the detector (thin scintillator screen) at high energies. Despite the clinical boundary condition used in this work, regarding the X-ray spectrum, thick samples, and detection system, it was possible to acquire phase contrast images of biological samples.

PS-YOLO: a small object detector based on efficient convolution and multi-scale feature fusion

PS-YOLO: a small object detector based on efficient convolution and multi-scale feature fusion

Image scanning microscopy reconstruction by autocorrelation inversion

Abstract Confocal laser scanning microscopy (CLSM) stands out as one of the most widely used microscopy techniques thanks to its three-dimensional imaging capability and its sub-diffraction spatial resolution, achieved through the closure of a pinhole in front of a single-element detector. However, the pinhole also rejects useful photons, and beating the diffraction limit comes at the price of irremediably compromising the signal-to-noise ratio (SNR) of the data. Image scanning microscopy (ISM) emerged as the rational evolution of CLSM, exploiting a small array detector in place of the pinhole and the single-element detector. Each sensitive element is small enough to achieve sub-diffraction resolution through the confocal effect, but the size of the whole detector is large enough to guarantee excellent collection efficiency and SNR. However, the raw data produced by an ISM setup consists of a 4D dataset, which can be seen as a set of confocal-like images. Thus, fusing the dataset into a single super-resolved image requires a dedicated reconstruction algorithm. Conventional methods are multi-image deconvolution, which requires prior knowledge of the system point spread functions (PSFs), or adaptive pixel reassignment (APR), which is effective only on a limited range of experimental conditions. In this work, we describe and validate a novel concept for ISM image reconstruction based on autocorrelation inversion. We leverage unique properties of the autocorrelation to discard low-frequency components and maximize the resolution of the reconstructed image without any assumption on the image or any knowledge of the PSF. Our results push the quality of the ISM reconstruction beyond the level provided by APR and open new perspectives for multi-dimensional image processing.

Visually guided swarm motion coordination via insect-inspired small target motion reactions

Despite progress developing experimentally-consistent models of insect in-flight sensing and feedback for individual agents, a lack of systematic understanding of the multi-agent and group performance of the resulting bio-inspired sensing and feedback approaches remains a barrier to robotic swarm implementations. This study introduces the small-target motion reactive (STMR) swarming approach by designing a concise engineering model of the small target motion detector (STMD) neurons found in insect lobula complexes. The STMD neuron model identifies the bearing angle at which peak optic flow magnitude occurs, and this angle is used to design an output feedback switched control system. A theoretical stability analysis provides bi-agent stability and state boundedness in group contexts. The approach is simulated and implemented on ground vehicles for validation and behavioral studies. The results indicate despite having the lowest connectivity of contemporary approaches (each agent instantaneously regards only a single neighbor), STMR achieves collective group motion. STMR group level metric analysis also highlights continuously varying polarization and decreasing heading variance.

Prototype Cherenkov detector characterization for muon tomography applications

Muography is an innovative imaging technique using naturally produced elementary particles – atmospheric muons – used to determine the distribution of density inside massive objects. The modification of the particles flux – by scattering or absorption – reflects the contrasts in density within the medium and therefore offers the possibility for an image of the crossed volumes. In most muography setups the imaging process is based on the tracking of the particles which accounts for the absorption or the scattering of the muons trajectories. Neither the energy nor the identity of the particles (the so-called PID) is exploited since this information traditionally relies on the use of calorimeters and/or high intensity magnetic fields. Both these techniques hinder detector portability which in the case of muography is important and this renders them impractical for its purpose. In this paper we characterize the performance of a simple and small water Cherenkov detector capable of providing some insights on the energy of muons and the PID for the crossing particles that could potentially improve the background rejection for a muography survey when operating in conjunction with a muon telescope. We tested a prototype of such water Cherenkov detector in combination with two small muon hodoscopes. Both systems are using the same opto-electronics chain – optical fibers and pixellized photosensors – and the same data acquisition (DAQ) readout system which ensures an easy integration and implementation within presently running systems. This article presents the test setup, the detector response to cosmic muons and its performance evaluation against a basic simulation of its geometry and detection principle.

EL-YOLO: An efficient and lightweight low-altitude aerial objects detector for onboard applications

Existing deep learning-based low-altitude small object detectors are typically complex in model architecture and demand substantial computational resources, making deployment for real-time detection tasks on edge computing devices challenging. To address this issue, we proposed EL-YOLO, an efficient and lightweight onboard applications object detector. Initially, in order to maintain a lightweight design and improve model accuracy, we propose a novel approach called Sparsely Connected Asymptotic Feature Pyramid Network(SCAFPN). This approach aims to eliminate inter-layer interference during feature fusion, thereby enhancing the model’s performance. Furthermore, to establish long-range contextual relationships for small object scale information, we devise a Cross-Space Learning Multi-Head Self-Attention mechanism (CSL-MHSA). To assess EL-YOLO capability for onboard small object detection, we deploy it on the embedded NVIDIA Jetson Xavier Nx platform and employ NVIDIA TensorRT FP16 quantization acceleration. On the VisDrone2019-DET and AI-TOD datasets, EL-YOLO demonstrates a 12.4% and 1.3% improvement in mAP50 compared to YOLOv5s. In comparison with the state-of-the-art YOLOv8s proposed in 2023, it achieves a respective 2.8% and 10.7% increase in mAP50. Moreover, the inference speed for the Small model reaches 24 frames per second, while the Nano model achieves 35 frames per second. This method holds promise for direct integration onto unmanned aerial vehicles for aerial small object detection tasks in the future.

Feasibility study of shielded diode detector for small field dosimetry.

Improved imaging techniques and modern radiotherapy treatment delivery in the treatment field are reduced to the precise size of the tumor, which necessitates the need for small-field dosimetry. Dosimetry in small-field dosimetry is challenging because most of the available code of practice for dosimetry is based on the cavity theory concept. Some small-sized detectors show good spatial resolution and sensitivity. Of the available small detectors, the diamond detector's performance is remarkably good. Most of the centers for radiotherapy lack diamond detectors. In this situation, if a diode detector is available, we can use it for small-field dosimetry by applying the Daisy Chaining method correction methods. In this study, the diode detector's response is not over-responding because of the defective diode. So this diode cannot be used for further measurements, and we have to regularly check the performance of the diode before using it for measurements.

Classification of Ice Particle Shapes Using Machine Learning on Forward Light Scattering Images

Abstract Machine learning (ML) has rapidly transitioned from a niche activity to a mainstream tool for environmental research applications including atmospheric science cloud microphysics studies. Two recently developed cloud particle probes measure the light scattered in the near forward direction and save digital images of the scattering light. Scattering pattern images collected by the Particle Phase Discriminator mark 2, Karlsruhe edition (PPD-2K), and the Small Ice Detector, version 3 (SID-3) provide valuable information for particle shape and size characterization. Since different particle shapes have distinctly different light scattering characteristics, the images are ideally suited for ML. Here, results of a ML project to characterize ice particle shapes sampled by the PPD-2K in ice fog and diamond dust during a 3-yr project in Fairbanks, Alaska. About 2.15 million light-scattering pattern images were collected during 3 years of measurements with the PPD-2K. Visual Geometry Group (VGG) convolutional neural network (CNN) was trained to categorize light-scattering patterns into eight categories. Initial training images (120 each category) were selected by human visual examination of data, and the training dataset was augmented using an automated iterative method for image identification of further images which were all visually inspected by a human. Results were well correlated to similar categories identified from previously developed classification algorithms. ML identifies characteristics not included in automated analysis such as sublimation. Of the 2.15 million images analyzed, 1.3% were categorized as spherical (liquid), 43.5% were categorized as having rough surfaces, 15.3% were pristine, 16.3% were categorized as sublimating, and the remaining 23.6% did not fit into any of those categories (irregular or saturated). Significance Statement The shapes and sizes of cloud particles can be extremely important for understanding the conditions that exist in the cloud. In this study, we show that more information about cloud particle characteristics can be identified by using machine learning than by traditional means. To demonstrate this, data are analyzed from a 3-yr study of ice fog and diamond dust events in Fairbanks, Alaska. The Particle Phase Discriminator instrument collected 2.15 million light-scattering pattern images of cloud particles during ground-based measurements. Neither traditional techniques nor machine learning were able to identify all categories, but a combination of both techniques led to a more complete view of ice particle shapes.

Detection Based on Semantics and a Detail Infusion Feature Pyramid Network and a Coordinate Adaptive Spatial Feature Fusion Mechanism Remote Sensing Small Object Detector

In response to the challenges of remote sensing imagery, such as unmanned aerial vehicle (UAV) aerial imagery, including differences in target dimensions, the dominance of small targets, and dense clutter and occlusion in complex environments, this paper optimizes the YOLOv8n model and proposes an innovative small-object-detection model called DDSC-YOLO. First, a DualC2f structure is introduced to improve the feature-extraction capabilities of the model. This structure uses dual-convolutions and group convolution techniques to effectively address the issues of cross-channel communication and preserving information in the original input feature mappings. Next, a new attention mechanism, DCNv3LKA, was developed. This mechanism uses adaptive and fine-grained information-extraction methods to simulate receptive fields similar to self-attention, allowing adaptation to a wide range of target size variations. To address the problem of false and missed detection of small targets in aerial photography, we designed a Semantics and Detail Infusion Feature Pyramid Network (SDI-FPN) and added a dedicated detection scale specifically for small targets, effectively mitigating the loss of contextual information in the model. In addition, the coordinate adaptive spatial feature fusion (CASFF) mechanism is used to optimize the original detection head, effectively overcoming multi-scale information conflicts while significantly improving small target localization accuracy and long-range dependency perception. Testing on the VisDrone2019 dataset shows that the DDSC-YOLO model improves the mAP0.5 by 9.3% over YOLOv8n, and its performance on the SSDD and RSOD datasets also confirms its superior generalization capabilities. These results confirm the effectiveness and significant progress of our novel approach to small target detection.