Search

Currently, small object detection in complex remote sensing environments faces significant challenges. The detectors designed for this scenario have limitations, such as insufficient extraction of spatial local information, inflexible feature fusion, and limited global feature acquisition capability. In addition, there is a need to balance performance and complexity when improving the model. To address these issues, this paper proposes an efficient and lightweight SCM-YOLO detector improved from YOLOv5 with spatial local information enhancement, multi-scale feature adaptive fusion, and global sensing capabilities. The SCM-YOLO detector consists of three innovative and lightweight modules: the Space Interleaving in Depth (SPID) module, the Cross Block and Channel Reweight Concat (CBCC) module, and the Mixed Local Channel Attention Global Integration (MAGI) module. These three modules effectively improve the performance of the detector from three aspects: feature extraction, feature fusion, and feature perception. The ability of SCM-YOLO to detect small objects in complex remote sensing environments has been significantly improved while maintaining its lightweight characteristics. The effectiveness and lightweight characteristics of SCM-YOLO are verified through comparison experiments with AI-TOD and SIMD public remote sensing small object detection datasets. In addition, we validate the effectiveness of the three modules, SPID, CBCC, and MAGI, through ablation experiments. The comparison experiments on the AI-TOD dataset show that the mAP50 and mAP50-95 metrics of SCM-YOLO reach 64.053% and 27.283%, respectively, which are significantly better than other models with the same parameter size. [ABSTRACT FROM AUTHOR]

Featured Application: The Raspberry Pi-based facial recognition system offers practical applications in access control for homes, businesses, and industrial sites, providing an affordable and reliable security solution. Its portability makes it ideal for surveillance in resource-limited settings. Additionally, it can enhance consumer electronics by enabling personalized smart home experiences. With further development, the system could also support demographic analysis in public spaces, contributing to informed decision making. Facial recognition technology has significantly advanced in recent years, with promising applications in fields ranging from security to consumer electronics. Its importance extends beyond convenience, offering enhanced security measures for sensitive areas and seamless user experiences in everyday devices. This study focuses on the development and validation of a facial recognition system utilizing a Haar cascade classifier and the AdaBoost machine learning algorithm. The system leverages characteristic facial features—distinct, measurable attributes used to identify and differentiate faces within images. A biometric facial recognition system was implemented on a Raspberry Pi microcomputer, capable of detecting and identifying faces using a self-contained reference image database. Verification involved selecting the similarity threshold, a critical factor influencing the balance between accuracy, security, and user experience in biometric systems. Testing under various environmental conditions, facial expressions, and user demographics confirmed the system's accuracy and efficiency, achieving an average recognition time of 10.5 s under different lighting conditions, such as daylight, artificial light, and low-light scenarios. It is shown that the system's accuracy and scalability can be enhanced through testing with larger databases, hardware upgrades like higher-resolution cameras, and advanced deep learning algorithms to address challenges such as extreme facial angles. Threshold optimization tests with six male participants revealed a value that effectively balances accuracy and efficiency. While the system performed effectively under controlled conditions, challenges such as biometric similarities and vulnerabilities to spoofing with printed photos underscore the need for additional security measures, such as thermal imaging. Potential applications include access control, surveillance, and statistical data collection, highlighting the system's versatility and relevance. [ABSTRACT FROM AUTHOR]

Online signature verification considers signatures as time sequences of different measurements of the signing instrument. These signals are captured on digital devices and therefore consist of a discrete number of samples. To enrich or simplify this information, several verifiers employ resampling and interpolation as a preprocessing step to improve their results; however, their design decisions may be difficult to generalize. This study investigates the direct effect of the sampling rate of the input signals on the accuracy of online signature verification systems without using interpolation techniques and proposes a novel online signature verification system based on a signer-dependent sampling frequency. Twenty verifier configurations were created for five different public signature databases and a variety of popular preprocessing approaches and evaluated for 20–40 different sampling rates. Our results show that there is an optimal range for the sampling frequency and the number of sample points that minimizes the error rate of a verifier. A sampling frequency range of 15–50 Hz and a signature point count of 60–240 provided the best accuracies in our experiments. As expected, lower ranges showed inaccurate results; interestingly, however, higher frequencies often decreased the verification accuracy. The results show that one can achieve better or at least the same verification accuracies faster by down-sampling the online signatures before further processing. The proposed system achieved competitive results to state-of-the-art systems for different databases by using the optimal sampling frequency. We also studied the effect of choosing individual sampling frequencies for each signer and proposed a signature verification system based on signer-dependent sampling frequency. The proposed system was tested using 500 different verification methods and improved the accuracy in 92% of the test cases compared to the usage of the original frequency. [ABSTRACT FROM AUTHOR]

The acquisition of chopstick skills is considered essential for child development and etiquette in many Asian cultures. However, a decline in chopstick education has been observed in Japan, and the underlying causes of this phenomenon remain elusive. This study aims to investigate children's chopstick skills and develop an objective method to evaluate them using a hand posture estimation model. In this study. A questionnaire survey was conducted among 165 first-grade elementary school students (aged 6–7) and their parents to investigate factors influencing chopstick proficiency. To complement this, video analyses were performed using a hand posture estimation model to assess the accuracy of chopstick grip classification. The findings showed that children's chopstick-holding styles could be classified into four categories: four-finger prehension (64 participants), three-finger prehension (49 participants), palm prehension (20 participants), and others (32 participants). Despite the fact that over 80% of parents reported teaching their children how to use chopsticks, a mere 9.7% of children exhibited correct chopstick-holding technique. Interestingly, factors such as intergenerational cohabitation with grandparents and child's age significantly influenced chopstick proficiency. These results indicate that a gap exists in the intergenerational transmission of chopstick skills, with parents potentially lacking sufficient knowledge to teach their children. The hand posture estimation model had a high accuracy rate of 85%, precision of 83%, and recall of 88% to identify whether children use chopsticks traditionally. While chopstick education is predominantly conducted within Japanese households, the increasing prevalence of nuclear families and dual-income households suggests a decline in intergenerational transmission of chopstick education. To address this issue, it is imperative to develop web applications that can integrate chopstick education into school curricula and promote chopstick skills among students. [ABSTRACT FROM AUTHOR]

Gesture recognition has a crucial role in Human–Computer Interaction (HCI) and in assisting the elderly to perform automatically their everyday activities. In this paper, three methods for gesture recognition and computer vision were implemented and tested in order to investigate the most suitable one. All methods, machine learning using IMU, machine learning on device, and were combined with certain activities that were determined during a needs analysis research. The same volunteers took part in the pilot testing of the proposed methods. The results highlight the strengths and weaknesses of each approach, revealing that while some methods excel in specific scenarios, the integrated solution of MoveNet and CNN provides a robust framework for real-time gesture recognition. [ABSTRACT FROM AUTHOR]

This paper proposes a method enhancing the accuracy of object detectors by utilizing background images for stationary camera systems. Object detection with stationary cameras is highly valuable across various applications, such as traffic control, crime prevention, and abnormal behavior detection. Deep learning-based object detectors, which are mainly used in such cases, are developed for general purposes and do not take advantage of stationary cameras at all. Previously, cascade-based object detection methods utilizing background have been studied for stationary camera systems. These methods typically consist of two stages: background subtraction followed by object classification. However, their object detection performance is highly dependent on the accuracy of the background subtraction results, and numerous parameters must be adjusted during background subtraction to adapt to varying conditions. This paper proposes an end-to-end object detection method named BGI-YOLO, which uses a background image simply by combining it with an input image before feeding it into the object detection network. In our experiments, the following five methods are compared: three candidate methods of combining input and background images, baseline YOLOv7, and a traditional cascade method. BGI-YOLO, which combines input and background images at image level, showed a detection performance (mAP) improvement compared to baseline YOLOv7, with an increase of 5.6%p on the WITHROBOT S1 dataset and 2.5%p on the LLVIP dataset. In terms of computational cost (GFLOPs), the proposed method showed a slight increase of 0.19% compared to baseline YOLOv7. The experimental results demonstrated that the proposed method is highly effective for improving detection accuracy without increasing computational cost. [ABSTRACT FROM AUTHOR]

Currently, gait recognition research is gradually expanding from ideal indoor environments to real-world outdoor scenarios. However, recognition scenarios in practical applications are often more complex than those considered in existing studies. For instance, real-world scenarios present multiple influencing factors, such as viewpoint variations and diverse carried items. Notably, many gait recognition tasks occur under low-light conditions at night. At present, research on gait recognition in nocturnal environments is relatively limited, and effective methods for nighttime gait recognition are lacking. To address this gap, this study extends gait recognition research to outdoor nighttime environments and introduces the first wild gait dataset encompassing both daytime and nighttime data, named Gait Recognition of Day and Night (GaitDN). Furthermore, to tackle the challenges posed by low-light conditions and other influencing factors in outdoor nighttime gait recognition, we propose a novel pose-based gait recognition framework called GaitSAT. This framework models the intrinsic correlations of human joints by integrating self-attention and graph convolution modules. We conduct a comprehensive evaluation of the proposed method and existing approaches using both the GaitDN dataset and other available datasets. The proposed GaitSAT achieves state-of-the-art performance on the OUMVLP, GREW, Gait3D, and GaitDN datasets, with Rank-1 accuracies of 60.77%, 57.37%, 22.90%, and 86.24%, respectively. Experimental results demonstrate that GaitSAT achieves higher accuracy and superior generalization capabilities compared to state-of-the-art pose-based methods. [ABSTRACT FROM AUTHOR]

In response to image degradation caused by rain during image acquisition, this paper proposes a rain removal method for single image of dual-branch joint network based on a sparse Transformer (DBSTNet). The developed model comprises a rain removal subnet and a background recovery subnet. The former extracts rain trace information utilizing a rain removal strategy, while the latter employs this information to restore background details. Furthermore, a U-shaped encoder-decoder branch (UEDB) focuses on local features to mitigate the impact of rainwater on background detail textures. UEDB incorporates a feature refinement unit to maximize the contribution of the channel attention mechanism in recovering local detail features. Additionally, since tokens with low relevance in the Transformer may influence image recovery, this study introduces a residual sparse Transformer branch (RSTB) to overcome the limitations of the Convolutional Neural Network’s (CNN’s) receptive field. Indeed, RSTB preserves the most valuable self-attention values for the aggregation of features, facilitating high-quality image reconstruction from a global perspective. Finally, the parallel dual-branch joint module, composed of RSTB and UEDB branches, effectively captures the local context and global structure, culminating in a clear background image. Experimental validation on synthetic and real datasets demonstrates that rain removal images exhibit richer detail information, significantly improving the overall visual effect. [ABSTRACT FROM AUTHOR]

Code review is a critical process in software development, contributing to the overall quality of the product by identifying errors early. A key aspect of this process is the selection of appropriate reviewers to scrutinize changes made to source code. However, in large-scale open-source projects, selecting the most suitable reviewers for a specific change can be a challenging task. To address this, we introduce the Code Context Based Reviewer Recommendation (CCB-RR), a model that leverages information from changesets to recommend the most suitable reviewers. The model takes into consideration the paths of modified files and the context derived from the changesets, including their titles and descriptions. Additionally, CCB-RR employs KeyBERT to extract the most relevant keywords and compare the semantic similarity across changesets. The model integrates the paths of modified files, keyword information, and the context of code changes to form a comprehensive picture of the changeset. We conducted extensive experiments on four open-source projects, demonstrating the effectiveness of CCB-RR. The model achieved a Top-1 accuracy of 60%, 55%, 51%, and 45% on the Android, OpenStack, QT, and LibreOffice projects respectively. For Mean Reciprocal Rank (MRR), CCB achieved 71%, 62%, 52%, and 68% on the same projects respectively, thereby highlighting its potential for practical application in code reviewer recommendation. [ABSTRACT FROM AUTHOR]

Exercise-based rehabilitation programs have proven to be effective in enhancing the quality of life and reducing mortality and rehospitalization rates. AI-driven virtual rehabilitation, which allows patients to independently complete exercises at home, utilizes AI algorithms to analyze exercise data, providing feedback to patients and updating clinicians on their progress. These programs commonly prescribe a variety of exercise types, leading to a distinct challenge in rehabilitation exercise assessment datasets: while abundant in overall training samples, these datasets often have a limited number of samples for each individual exercise type. This disparity hampers the ability of existing approaches to train generalizable models with such a small sample size per exercise type. Addressing this issue, this paper introduces a novel supervised contrastive learning framework with hard and soft negative samples that effectively utilizes the entire dataset to train a single model applicable to all exercise types. This model, with a Spatial-Temporal Graph Convolutional Network (ST-GCN) architecture, demonstrated enhanced generalizability across exercises and a decrease in overall complexity. Through extensive experiments on three publicly available rehabilitation exercise assessment datasets, UI-PRMD, IRDS, and KIMORE, our method has proven to surpass existing methods, setting a new benchmark in rehabilitation exercise quality assessment., Competing Interests: Declarations. Conflict of interest: The authors declare no competing interests., (© 2024. International Federation for Medical and Biological Engineering.)

What makes animal gaits so audibly rhythmic? To answer this question, we recorded the footfall sound of 19 horses and quantified the rhythmic differences in the temporal structure of three natural gaits: walk, trot, and canter. Our analyses show that each gait displays a strikingly specific rhythmic pattern and that all gaits are organized according to small-integer ratios, those found when adjacent temporal intervals are related by a mathematically simple relationship of integer numbers. Walk and trot exhibit an isochronous structure (1:1)-similar to a ticking clock-while canter is characterized by three small-integer ratios (1:1, 1:2, 2:1). While walk and trot both show isochrony, trot has a slower tempo and is more precise and accurate, like a metronome. Our results quantitatively discriminate horse gaits based on rhythm, revealing striking commonalities with human music and some animal communicative signals. Gait and vocal rhythmicity share key features, and the former likely predates the latter; we suggest this supports gait-based hypotheses for the evolution of rhythm. Specifically, the perception of locomotor rhythmicity may have evolved in different species under pressure for predator recognition and mate selection; it may have been later exapted for rhythmic vocal communication., (© 2024 The Author(s). Annals of the New York Academy of Sciences published by Wiley Periodicals LLC on behalf of The New York Academy of Sciences.)