Small Objects Research Articles

The Lightweight Fracture Segmentation Algorithm for Logging Images Based on Fully 3D Attention Mechanism and Deformable Convolution

The challenge of fracture segmentation remains a significant obstacle in imaging logging interpretation within the current oil and gas exploration and development field. However, existing image segmentation algorithms still encounter issues related to accuracy, speed, and robustness, as well as a tendency to misdetect or overlook small fractures when applied to logging image fracture segmentation tasks. To address these challenges comprehensively, this paper proposes an end-to-end fracture segmentation algorithm named SWSDS-Net. This algorithm is built upon the UNet architecture and incorporates the SimAM with slicing (SWS) attention mechanism along with the deformable strip convolution (DSCN) module. The SWS introduces a fully 3D attention mechanism that effectively learns the weights of each neuron in the feature map, enabling better capture of fracture features while ensuring fair attention and enhancement for both large and small objects. Additionally, the deformable properties of DSCN allow for adaptive sampling based on fracture shapes, effectively tackling challenges posed by varying fracture shapes and enhancing segmentation robustness. Experimental results demonstrate that SWSDS-Net achieves optimal performance across all evaluation metrics in this task, delivering superior visual results in fracture segmentation while successfully overcoming limitations present in existing algorithms such as complex shapes, noise interference, and low-quality images. Moreover, serving as a lightweight network solution enables SWSDS-Net’s deployment on mobile devices at remote sites—an advancement that lays a solid foundation for interpreting logging data and promotes deep learning technology application within traditional industrial scenarios.

DMFR-YOLO: an infrared small hotspot detection algorithm based on double multi-scale feature fusion

Abstract Hotspot automatic detection is an effective strategy to realize intelligent maintenance of photovoltaic (PV) modules. However, it is challenging to detect small hotspots accurately using deep learning-based object detection methods due to the weak information and small area of the target. This study presents a double multi-scale feature reconstruction (DMFR)-YOLO to detect small hotspots in PV modules. In the proposed DMFR-YOLO, the backbone of YOLOv8n is improved by eliminating redundant deep layers and introducing a shallow detection head to enhance its perception and recognition ability for small objects. Moreover, a weighted multi-layer feature reconstruction (MLFR) module is introduced to fuse the features of different depths and a multi-receptive field feature reconstruction (MRFR) module is designed to fuse the information of different receptive fields. Finally, ablation and comparison experiments are conducted to evaluate the performance of the proposed method. The model with both MLFR and MRFR can achieve a recall rate of 88.6%, with a mean average precision (mAP@0.5) of 93.3%. Experimental results demonstrate that the proposed DMFR-YOLO is able to achieve small hotspot detection in IR images with high accuracy.

Preliminary report: Reduced hand sensory and motor function in persons living with heart failure.

Despite the growing evidence highlighting reduced functional independence in persons living with heart failure (PwHF), the underlying mechanisms that lead to reduced functional independence in this patient population are unknown. Given the association between functional independence and fine motor skills, which are functionally related to hand sensory and motor functions, we hypothesized that PwHF exhibit reduced sensory and motor function of hands compared to healthy individuals. We recruited a total of 10 PwHF (age: 57.6 ± 12.5 years old, four females) and a total of age- & sex-matched healthy control individuals (age: 58.2 ± 12.2 years old, four females). Participants performed a wide range of tests assessing the level of independence, fitness, cognitive function, and hand sensorimotor function. While the level of independence was comparable between two groups, PwHF exhibited reduced sensory and motor function. Compared to healthy participants, the ability to identify an object via tactile and proprioceptive inputs was reduced in PwHF, though the tactile mechanoreceptor function showed normal integrity. Similarly, PwHF exhibited a decline in manipulating small objects and steady grip force production. Heart failure seems to have repercussions that extend to the sensorimotor control of hand actions in advance to a decline in functional independence. These results underscore the need of further investigation as to the underlying mechanisms of reduced sensorimotor function, potential intervention targets, and determine whether assessments of hand sensorimotor function can serve as a vehicle to quantify restoration of self-care functionality.

ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection

ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection

GreenFruitDetector: Lightweight green fruit detector in orchard environment.

Detecting green fruits presents significant challenges due to their close resemblance in color to the leaves in an orchard environment. We designed GreenFruitDetector, a lightweight model based on an improved YOLO v8 architecture, specifically for green fruit detection. In the Backbone network, we replace ordinary convolution with Deformable Convolution to enhance the extraction of geometric features. Additionally, we designed MCAG-DC (Multi-path Coordinate Attention Guided Deformer Convolution) to replace the convolution in C2f, enhancing the Backbone's feature extraction capability when encountering occlusion problems. For the Neck part of the algorithm, we designed a Fusion-neck structure that integrates spatial detail information from feature maps at different scales, thereby enhancing the network's ability to extract multi-scale information. Additionally, we devised a new detection head that incorporates multi-scale information, significantly improving the detection of small and distant objects. Finally, we applied channel pruning techniques to reduce the model size, parameter count, and FLOPs to 50%, 55%, and 44% of the original, respectively. We trained and evaluated the improved model on three green fruit datasets. The accuracy of the improved model reached 94.5%, 84.4%, and 85.9% on the Korla Pear, Guava, and Green Apple datasets, respectively, representing improvements of 1.17%, 1.1%, and 1.77% over the baseline model. The mAP@0.5 increased by 0.72%, 6.5%, and 0.9%, respectively, and the recall rate increased by 1.97%, 1.1%, and 0.49%, respectively.

Strength and dexterity of less affected hand of children with unilateral cerebral palsy: a comparison study with normal peers.

A key aspect of hand function is dexterity, which is described as fine voluntary movements used to manipulate small objects during a specific task. The contralateral hand in children with unilateral cerebral palsy (U-CP); is commonly referred to as a "good" and "unimpaired" hand, while others have noted that it has subtle limitations. Therefore, this study aimed to assess and compare between the strength and dexterity of less-affected hand of children with U-CP and the dominant hand of normal peers. A sample of 120 volunteer children from both sexes and age ranged from 6 to 10 years participated in this study. Out of the 120 children, sixty were normal typically developing (TD) and sixty children with U-CP. Assessment of fine motor dexterity and grip and pinch strength were carried out by the Functional dexterity test (FDT) and Pneumatic squeeze Blub Dynamometer respectively. The results showed that there was a significant lower in pinch and grip strength (p < 0.01) and significant higher FDT scores of children with U-CP compared with that of TD children (p = 0.001). Moreover, there was a significant higher functional levels in TD children compared with that of children with U-CP (p < 0.001) with no significant difference between groups in penalty distribution (p > 0.05). Children with U-CP underperformed with their less-affected hand than the dominant hand of TD age matched peers. Future researches on bilateral hand function may be used to determine the best rehabilitation interventions.

Target-aware cross-modality unsupervised domain adaptation for vestibular schwannoma and cochlea segmentation.

There is growing interest in research on segmentation for the vestibular schwannoma (VS) and cochlea using high-resolution T2 (hrT2) imaging over contrast-enhanced T1 (ceT1) imaging due to the contrast agent side effects. However, the hrT2 imaging remains a problem of insufficient annotated data, which is fatal for building more robust segmentation models. To address the issue, recent studies have adopted unsupervised domain adaptation approaches that translate ceT1 images to hrT2 images. However, previous studies did not consider the size and visual characteristics of the target objects, such as VS and cochlea, during image translation. Specifically, those works simply performed normalization on the entire image without considering its significant impact on the quality of the translated images. These approaches tend to erase the small target objects, making it difficult to preserve the structure of these objects when generating pseudo-target images. Furthermore, they may also struggle to accurately reflect the unique style of the target objects within the images. Therefore, we propose a target-aware unsupervised domain adaptation framework, designed for translating target objects, each tailored to their unique visual characteristics and size using target-aware normalization. We demonstrate the superiority of the proposed framework on a publicly available challenge dataset. Codes are available at https://github.com/Bokyeong-Kang/TANQ .

A Reparameterization Feature Redundancy Extract Network for Unmanned Aerial Vehicles Detection

In unmanned aerial vehicles (UAVs) detection, challenges such as occlusion, complex backgrounds, motion blur, and inference time often lead to false detections and missed detections. General object detection frameworks encounter difficulties in adequately tackling these challenges, leading to substantial information loss during network downsampling, inadequate feature fusion, and being unable to meet real-time requirements. In this paper, we propose a Real-Time Small Object Detection YOLO (RTSOD-YOLO) model to tackle the various challenges faced in UAVs detection. We further enhance the adaptive nature of the Adown module by incorporating an adaptive spatial attention mechanism. This mechanism processes the downsampled feature maps, enabling the model to better focus on key regions. Secondly, to address the issue of insufficient feature fusion, we employ combined serial and parallel triple feature encoding (TFE). This approach fuses scale-sequence features from both shallow features and twice-encoded features, resulting in a new small-scale object detection layer. While enhancing the global context awareness of the existing detection layers, this also enriches the small-scale object detection layer with detailed information. Since rich redundant features often ensure a comprehensive understanding of the input, which is a key characteristic of deep neural networks, we propose a more efficient redundant feature generation module. This module generates more feature maps with fewer parameters. Additionally, we introduce reparameterization techniques to compensate for potential feature loss while further improving the model’s inference speed. Experimental results demonstrate that our proposed RTSOD-YOLO achieves superior detection performance, with mAP50/mAP50:95 reaching 97.3%/51.7%, which represents improvement of 3%/3.5% over YOLOv8, and 2.6%/0.1% higher than YOLOv10. Additionally, it has the lowest parameter count and FLOPs, making it highly efficient in terms of computational resources.

Partial volume correction for Lu-177-PSMA SPECT.

The limited spatial resolution in SPECT images leads to partial volume effect (PVE), degrading the subsequent dosimetric accuracy. We aim to quantitatively evaluate PVE and partial volume corrections (PVC), i.e., recovery coefficient (RC)-PVC (RC-PVC), reblurred Van-Cittert (RVC) and iterative Yang (IY), in 177Lu-PSMA-617 SPECT images. We employed a geometrical cylindrical phantom containing five spheres (diameters ranging from 20 to 40mm) and 40 XCAT phantoms with various anatomical variations and activity distributions. SIMIND Monte Carlo code was used to generate realistic noisy projections. In the clinical study, sequential quantitative SPECT/CT imaging at 4 time-points post 177Lu-PSMA-617 injections were analyzed for 10 patients. Iterative statistical reconstruction methods were used for reconstruction with attenuation, scatter and geometrical collimator detector response corrections, followed by post-filters. The RC-curves were fit based on the geometrical phantom study and applied for XCAT phantom and clinical study in RC-PVC. Matched and 0.5-2.0 voxels (2.54-10.16mm) mismatched sphere masks were deployed in IY. The coefficient of variation (CoV) was measured on a uniform background on the geometrical phantom. RCs of spheres and mean absolute activity error (MAE) of kidneys and tumors were evaluated in simulation data, while the activity difference was evaluated in clinical data before and after PVC. In the simulation study, the spheres experienced significant PVE, i.e., 0.26 RC and 0.70 RC for the 20mm and 40mm spheres, respectively. RVC and IY improved the RC of the 20mm sphere to 0.37 and 0.75 and RC of the 40mm sphere to 0.96 and 1.04. Mismatch in mask increased the activity error for all spheres in IY. RVC increased noise and caused Gibbs ringing artifacts. For XCAT phantoms, both RVC and IY performed comparably and were superior to RC-PVC in reducing the MAE of the kidneys. However, IY and RC-PVC outperformed RVC for tumors. The XCAT phantom study and clinical study showed a similar trend in the kidney and tumor activity differences between non-PVC and PVC. PVE greatly impacts activity quantification, especially for small objects. All PVC methods improve the quantification accuracy in 177Lu-PSMA SPECT.

Scale-Adaptive Salience Supervision and Dynamic Token Filtering for Small Object Detection in Remote Sensing Images

Abstract Recently, DETR-like detectors, which have shown remarkable performance in general object detection, face limitations when dealing with remote sensing images primarily containing small objects. Mainstream two-stage DETR-like models employ a pipeline that selects and processes a small portion of informative tokens, which enhances performance but also shows a high dependency on token selection. The current static token selection strategies lead to inconsistencies between the static selection criteria and dynamic token updates. Additionally, in remote sensing images, the limited information available for small objects and their inherent sensitivity to pixel shifts further degrade detection performance. To address this, we propose Scale-Adaptive Salience DETR (SAS DETR), a two-stage DETR-like method. SAS DETR incorporates dynamic token filtering, which uses a global threshold predictor to determine the token filtering ratio for each layer of the encoder. This approach selects an appropriate filtering ratio for different network layers while maintaining consistency between the foreground confidence map and token updates. Furthermore, we introduce a novel scale-adaptive salience supervision mechanism that adaptively scales the salience computation area based on object size, ensuring the model more effectively supervises small objects and utilizes the information within tokens without compromising the detection performance for objects of other sizes. Finally, we employ Scale-Adaptive Intersection over Union to reduce the impact of pixel shifts on small objects. With these improvements, our proposed SAS DETR achieves 25.2% AP on the AI-TOD-V2 dataset with 24 training epochs and 50.4% AP on the COCO 2017 dataset with 12 training epochs.

An automatic detection method for cervical liquid‐based cells based on improved Yolov5s network

AbstractTo address the significant challenges of high false positive and false negative rates in existing algorithms for detecting cervical fluid‐based cells, an enhanced Yolov5s network is introduced. This paper details a novel approach that dynamically adjusts the weights of channels and the spatial attention in modules, substantially improving feature extraction from small objects and boosting the detection capabilities of the network. Furthermore, Mixup data augmentation technology is incorporated to counter the issue of imbalanced data categories in the custom dataset. The Complete Intersection over Union loss function is also employed to refine coordinate localization accuracy during training. Tested on the proprietary cervical cytology dataset, the modified Yolov5s achieves a mean Average Precision of 92.1%, surpassing the previous state‐of‐the‐art by 5.6%. This enhancement substantiates the efficacy of the proposed model. Code and models are accessible at https://github.com/youyi888/yolov5_CPCA.

TouchView: Mid-Air Touch on Zoomable 2D View for Distant Freehand Selection on a Virtual Reality User Interface

Selection is a fundamental interaction element in virtual reality (VR) and 3D user interfaces (UIs). Raycasting, one of the most common object selection techniques, is known to have difficulties in selecting small or distant objects. Meanwhile, recent advancements in computer vision technology have enabled seamless vision-based hand tracking in consumer VR headsets, enhancing accessibility to freehand mid-air interaction and highlighting the need for further research in this area. This study proposes a new technique called TouchView, which utilizes a virtual panel with a modern adaptation of the Through-the-Lens metaphor to improve freehand selection for VR UIs. TouchView enables faster and less demanding target selection by allowing direct touch interaction with the magnified object proxies reflected on the panel view. A repeated-measures ANOVA on the results of a follow-up experiment on multitarget selection with 23 participants showed that TouchView outperformed the current market-dominating freehand raycasting technique, Hybrid Ray, in terms of task performance, perceived workload, and preference. User behavior was also analyzed to understand the underlying reasons for these improvements. The proposed technique can be used in VR UI applications to enhance the selection of distant objects, especially for cases with frequent view shifts.

CDANet: a small object detection model for unmanned aerial vehicle images based on cross-layer guidance and skip dilated fusion

CDANet: a small object detection model for unmanned aerial vehicle images based on cross-layer guidance and skip dilated fusion

Vision-guided crack identification and size quantification framework for dam underwater concrete structures

Remotely operated vehicles with cameras provide a non-contact inspection solution for dam underwater structural defect detection. However, manual information extraction methods suffer from problems like labor costs and high misjudgment. This study proposes an integrated dam underwater crack identification and size quantification framework using machine vision and deep learning. First, a real-time automatic detection framework for dam underwater cracks is built via You Only Look Once v5 (YOLOv5), and four different backbone detectors are introduced to balance detection accuracy and speed. Then, the Swin-Transformer module is inserted into the YOLOv5 model to enhance its feature extraction capability and small object detection capability. Next, a method for measuring the true size of cracks was constructed based on deep learning and infrared laser rangefinders. In this study, physical model experiments and actual engineering projects are combined to validate the generalization capability of the proposed crack identification and size quantification method. Experimental results show that the Swin-Transformer-based YOLOv5 model effectively balances detection accuracy and speed with a precision of 0.986, a recall of 0.979, a mean average precision of 0.985, and a frame rate of 68 frames per second in detecting underwater crack images with 768 × 576 pixels. In addition, the proposed method can accurately identify and detect cracks in complex underwater scenes, including obstacle interference, tilt shooting angle, uneven illumination, and turbid water scenarios. Moreover, the method proposed in this paper can quantify the overall size and geometric parameters of underwater cracks with relatively small errors.

Multi-Scale Feature Fusion Enhancement for Underwater Object Detection

Underwater object detection (UOD) presents substantial challenges due to the complex visual conditions and the physical properties of light in underwater environments. Small aquatic creatures often congregate in large groups, further complicating the task. To address these challenges, we develop Aqua-DETR, a tailored end-to-end framework for UOD. Our method includes an align-split network to enhance multi-scale feature interaction and fusion for small object identification and a distinction enhancement module using various attention mechanisms to improve ambiguous object identification. Experimental results on four challenging datasets demonstrate that Aqua-DETR outperforms most existing state-of-the-art methods in the UOD task, validating its effectiveness and robustness.

Object Detection and Tracking in Maritime Environments in Case of Person-Overboard Scenarios: An Overview

We examine the current state of the art and the related research on the automated detection and tracking of small objects—or persons—in the context of a person-overboard (POB) scenario and present the associated governing relationship between different technologies, platforms, and approaches as a system of systems. A novel phase model, structuring a POB scenario, comprises three phases: (1) detection, (2) search and track, and (3) rescue. Within these phases, we identify the central areas of responsibility and describe in detail the phases (1) and (2). We emphasize the importance of a high-level representation of different systems and their interactions to comprehensively represent the complexity and dynamics of POB scenarios. Our systematic classification and detailed description of the technologies and methods used provide valuable insights to support future regulatory and research activities. Our primary aim is to advance the development of corresponding technologies and standards.

Shufflenetv2UNet: An improved neural network model for grassland sample coverage extraction

AbstractAccurate extraction of grassland sample coverage is crucial for regional ecological environment monitoring. Due to the strong feature learning capability, high flexibility, and scalability of deep learning methods, they have great potential in grassland sample extraction modelling. However, we still lack a model that can achieve both lightweight structure and effective performance for small object segmentation to considering the small target characteristics of grassland vegetation and the requirements for model deployment in later stages. Here, we combined the UNet model, which performs well in small target segmentation, with the lightweight network Shufflenetv2 model, proposing an improved UNet neural network, Shufflenetv2UNet, for grassland sample coverage extraction. The core of Shufflenetv2UNet is the removal of maximum pooling and double‐layer convolution modules from downsampling in the UNet neural network. In addition, the Inverted Residual Block structure module from Shufflenetv2 was added to achieve a lightweight model and improved extraction accuracy. The Shufflenetv2UNet achieves an accuracy of 98.23%, with a parameter size of 50.74 M, and a model inference speed of 0.004 s. Compared to existing extraction methods, this model has advantages in prediction accuracy, parameter size, and model inference speed. Moreover, Shufflenetv2UNet achieved different types of grassland sample coverage extractions, with good robustness, generalization, and universality, enabling investigators to quickly and accurately obtain grassland sample coverage. This allows more dynamic and accurate ground measurement data for regional grassland environmental monitoring.

A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection

Remote sensing object detection (RSOD) plays a crucial role in resource utilization, geological disaster risk assessment and urban planning. Deep learning-based object-detection algorithms have proven effective in remote sensing image studies. However, accurate detection of objects with small size, dense distribution and complex object arrangement remains a significant challenge in the remote sensing field. To address this, a refined and efficient object-detection algorithm (RE-YOLO) has been proposed in this paper for remote sensing images. Initially, a refined and efficient module (REM) was designed to balance computational complexity and feature-extraction capabilities, which serves as a key component of the RE_CSP block. RE_CSP block efficiently extracts multi-scale information, overcoming challenges posed by complex backgrounds. Moreover, the spatial extracted attention module (SEAM) has been proposed in the bottleneck of backbone to promote representative feature learning and enhance the semantic information capture. In addition, a three-branch path aggregation network (TBPAN) has been constructed as the neck network, which facilitates comprehensive fusion of shallow positional information and deep semantic information across different channels, enabling the network with a robust ability to capture contextual information. Extensive experiments conducted on two large-scale remote sensing datasets, DOTA-v1.0 and SCERL, demonstrate that the proposed RE-YOLO outperforms state-of-the-art other object-detection approaches and exhibits a significant improvement in generalization ability.

Research on image recognition and processing application technology of unmanned vehicle based on deep learning

Abstract. Image recognition technology is critically important in various fields, including the rapidly advancing sector of autonomous vehicles. As one of the core components enabling driverless cars to perceive their environment and make informed decisions, image recognition has seen significant advancements due to deep learning. This paper focuses on the application of deep learning in image recognition for self-driving cars and explores its implications for the future of autonomous driving technology. To begin with, this paper examines the empirical evaluation of deep learning models in highway driving scenarios. By employing Convolutional Neural Networks (CNN), these models achieve high detection rates and superior accuracy in recognizing vehicles and lanes. The robustness of these models is tested under varying weather conditions and times, demonstrating their effectiveness compared to classical computer vision techniques. Next, the paper discusses radar-camera fusion technology, highlighting different fusion strategies such as data-level, feature-level, object-level, and hybrid-level. The findings suggest that while feature-level fusion excels in detecting small objects in complex scenes, hybrid-level fusion is optimal for diverse driving situations. This section provides valuable insights into the integration of multimodal data for improved object recognition and semantic segmentation. After discussing fusion technologies, the paper finally reviews the security challenges posed by adversarial attacks on deep learning-based unmanned systems.

The agency of object: the doppa as a narrator for a dynamic Uyghur identity

ABSTRACT This article explores the Uyghur doppa from the late nineteenth and early twentieth centuries to understand Uyghur cultural life and identity. It links the doppa to Uyghur history and the evolving sense of ‘Uyghurness’, reflecting its cultural significance today, both in Xinjiang and through the diaspora. The limited scholarly work on the doppa, spanning 150 years, suggests a gender bias in documenting female-associated crafts. Ironically, at a time when the doppa holds increasing importance, especially with the creation of Doppa Day (5 May), this lack of resources opens up space for creative discourse on Uyghur identity. The study also reveals a tendency to adapt through cultural experiences while maintaining a deep connection to the homeland. Ultimately, this research demonstrates how a small cultural object can provide profound insights into community sensibilities and material culture.