Abstract Global soft biometrics-based identification refers to the recognition of subjects using human traits such as gender, age, and ethnicity. Unlike traditional biometric methods that rely on unique physical markers such as fingerprints or iris scans, soft biometrics represents a non-intrusive, viable, and versatile approach, thus making them particularly valuable for surveillance and security applications. Despite significant advances, several issues have been associated with traditional biometrics, like maintaining accuracy, addressing algorithmic bias, and limited computational efficiency. To address those issues, this paper presents a comprehensive coverage of the current advances in Global soft biometric-based recognition as a solution, where four key contributions are made; i.e., (i) advocacy on the relevance and impact of soft biometrics in surveillance and security, (ii) development of a new and unique CeleBImg dataset to overcome algorithmic biases and improve diversity in soft biometric-based recognition, (iii) rigorous performance comparison of current methods in-practice for Global soft biometrics-based recognition and, (iv) identification of open challenges with potential solutions in the field within the context of surveillance and security. This paper sets a solid foundation for using Global soft biometrics in the CCTV-based surveillance and security domain, with their significance, relevance and effectiveness.

Advancements in digital education have revolutionized traditional learning environments, driving the widespread adoption of virtual and hybrid classrooms. Engagement, a vital factor for effective learning, necessitates continuous monitoring and assessment to optimize outcomes. This study introduces EngageSense, a hybrid real-time engagement detection system leveraging facial biometrics, computer vision, and deep learning. First, a new dataset is created via user eye images taken from webcam of laptop. Then, Dlib's HOG + Linear SVM for face detection, a CNN model trained on 4,453 eye images dataset(classified into left, right, and center gaze directions), and OpenPose MobileNetV1 for body pose estimation are used. By fusing gaze direction (99.50% accuracy) and pose features, EngageSense classifies engagement into three levels: fully engaged, partially engaged, and not engaged with an accuracy of 90%. By providing actionable real-time insights, EngageSense empowers educators to foster meaningful interactions and enhance learning experiences in virtual environments.

While online education and virtual meetings increasingly form part of the modern learning environment, it is uniquely difficult to gauge participant engagement in virtual class sessions. Traditional approaches are usually based on either attendance counts or observation by a moderator and can seldom offer real-time, precise feedback as to the degree of individual contribution. This kind of approach is surely unsuitable for a large learning setting or even for remote learning, where active participation may be more difficult to gauge. The existing limitations, therefore, raise the need to introduce VEMeter, a tool designed to measure and quantify the level of participation in virtual class sessions. VEMeter analyzes transcripts and chat logs from virtual meetings using state-of-the-art text-processing techniques, including TF-IDF and Cosine Similarity. These techniques help in measuring the participant engagement against those of the presenter or facilitator. This enables a more objective and correct analysis of how participants in the session interact and contribute. To enhance its analysis, VEMeter cleans text by applying several advanced techniques: stopword removal, lemmatization, contraction expansion, and tokenization. Through the application of these pre-processing techniques, it will be easier to eliminate irrelevant content and noise inside the text for the generated engagement metrics to reflect meaningful participations and not trivial ones. Data privacy and security are at the very core of VEMeter. The tool anonymizes participant data through name encryption; thus, it guarantees protection of participants' personal information in an ethical analytics ecosystem. This already allows VEMeter to provide insights into engagement without compromising participant confidentiality. VEMeter enables rich analytics and visualizations through bar charts, scatter plots, and correlation heatmaps that explain the level of engagement and variation of participation based on the word count. Educators can track participation in virtual sessions in real time through these insights and make timely interventions to enhance engagement. This study contributes to engagement level assessment by introducing an NLP-driven participation analysis tool. Practically, it effectively provides educators with a data-driven methodology to measure student engagement in virtual classrooms. The following paper designs, implements, and evaluates a proof-of-concept VEMeter to enrich virtual education by supplying real-time insights into participant engagement.

Automated nonfunctional requirements (NFRs) classification enhances consistency and traceability by systematically labeling requirements, saving effort, supporting early architectural and testing decisions, improving stakeholder communication, and enabling quality across diverse software domains. While prior work has applied natural language processing (NLP) and machine learning (ML) to NFR classification, existing datasets are often limited in size, domain diversity, and contextual richness. This study presents a novel dataset comprising over 2400 NFRs spanning 269 software projects across 26 software application domains, including nine blockchain projects. The raw requirements are standardized using Rupp’s boilerplate to reduce vagueness and ambiguity, and the classification of NFRs types follows ISO/IEC 25,010 definitions. We employ a range of traditional ML, deep learning (DL), and a transformer‐based model (i.e., BERT‐base) for automated classification of NFRs, evaluating performance across cross‐domain and blockchain‐specific NFRs. Results highlight that domain‐aware adaptation significantly enhances classification accuracy, with traditional ML and DL models showing strong performance on blockchain requirements. This work contributes a publicly available, context‐rich dataset and provides empirical insights into the effectiveness of NLP‐based NFR classification in both general and blockchain‐specific settings.

This paper addresses key limitations in recent 3D tracking-by-detection methods, focusing on the challenges of identifying legitimate trajectories and mitigating state estimation drift in the Kalman filter. Current methods rely heavily on threshold-based detection score filtering approaches to reduce false positives and prevent ghost trajectories. However, these approaches fail for distant and partially occluded objects, where detection scores drop, and false positives surpass that threshold. Additionally, many existing methods assume that detections provide precise localization, overlooking the inherent noise that affects localization accuracy and causes state drift for occluded objects, as demonstrated in this work. To this end, a novel track validity mechanism, combined with a multi-stage observational gating process, is proposed that significantly reduces ghost tracks and improves tracking performance. Our method achieves 29.47% enhancement in Multi-Object tracking accuracy (MOTA) on the KITTI validation dataset with the Second detector. Furthermore, a refined Kalman filter term mitigates localization noise, ensuring robust state estimation for objects that are occluded and superior recovery during prolonged occlusions. This results in higher-order tracking accuracy (HOTA) improving by 4.8% on the KITTI validation dataset with the PV-RCNN detector. The proposed online framework, RobMOT, outperforms state-of-the-art methods, including deep learning approaches, across multiple detectors, with HOTA improvements of up to 3.92% on the KITTI testing dataset and 8.7% on the KITTI validation dataset while achieving the lowest identity switch (IDSW) scores of 7 and 0, respectively. RobMOT excels under challenging scenarios, such as tracking distant objects and handling prolonged occlusions, surpassing state-of-the-art methods on the Waymo Open testing dataset with a 1.77% improvement in MOTA for objects at distances exceeding 50 meters. RobMOT achieves a groundbreaking runtime of 3221 FPS using a single CPU, establishing itself as a highly efficient and scalable solution for real-time multi-object tracking.

Navigating autonomous vehicles efficiently across unstructured and off-road terrains remains a formidable challenge, often requiring intricate mapping or multi-step pipelines. However, these conventional approaches struggle to adapt to dynamic environments. This paper presents TerrainSense, an end-to-end framework that overcomes these limitations. By utilizing a transformers, TerrainSense detects lane semantics and topology from camera images, enabling mapless path planning without the reliance on highly detailed maps. The efficacy of TerrainSense was rigorously assessed on six diverse datasets, evaluating its efficacy in detection, segmentation, and path prediction using various metrics. Notably, it outperforms the other state-of-the-art methods by 9.32% in precisely predicting the path with 18.28% faster inference time.

The efficient navigation of autonomous vehicles across rugged and unstructured terrains remains a significant challenge. Most existing research in this area emphasizes the need for complex mappings or intricate multi-step methodologies. However, these traditional approaches often struggle to adapt to dynamic changes in environmental conditions. In this paper, we introduce PathFormer, an end-to-end framework designed specifically to address these challenges. PathFormer utilizes transformers to decode free-space semantics and configurations directly from camera images, enabling efficient path planning without the reliance on detailed, pre-existing maps. The performance of PathFormer was rigorously evaluated across diverse datasets, where it demonstrated superior capabilities, outperforming other state-of-the-art methods by 3.68% in precisely segmenting free-space regions and showing a 13.65% improvement in correctly predicting traversable paths.

Before the world-wide deployment of autonomous vehicles, it is essential to implement intermediate solutions with partial autonomy. One such solution is the use of vehicle teleoperation, the act of controlling a vehicle from a distance. In real time applications of teleoperation, it is often pertinent to use augmented reality components within the teleoperator view, which are referred to as a predictive display. In this work, we evaluate our predictive display method, which is a guiding path based on the free space in the environment. The path is generated based on our Dual Transformer Network (DTNet), which uses both object detection and lane semantic segmentation to define the free space in the environment. While the model has previously performed well on image data, it is necessary to observe its accuracy in the presence of time delay and packet loss, to assess its performance in a real-time setting. Thus, in this work, we use CARLA simulator to compare the detected free space on the teleoperator side to the true free space on the vehicle side across different values of time delay and packet loss. Under optimal network conditions, our model yielded a remarkable 87.9% DSC score and 81.3% IoU score. Defining our minimum performance threshold as 80% DSC and 70% IoU, we conclude that our model can effectively mitigate the challenges of time delay below 100ms and packet loss below 1%, both of which represent substantial tolerances.

Abstract The field of biometrics research encompasses the need to associate an identity to an individual based on the persons physiological or behaviour traits. While the use of intrusive techniques such as retina scans and finger print identification has resulted in highly accurate systems, the scalability of such systems in real-world applications such as surveillance and border security has been limited. As a branch of biometrics research, the origin of soft biometrics could be traced back to need for non-intrusive solutions for extracting physiological traits of a person. Following high number of research outcomes reported in the literature on soft biometrics, this paper aims to consolidate the scope of soft biometrics research across four thematic schemes (i) a detailed review of soft biometrics research data sets, their annotation strategies and building a largest novel collection of soft traits; (ii) the assessment of metrics that affect the performance of soft biometrics system; (iii) a comparative analysis on feature and modality level fusion reported in the literature for enhancing the system performance; and (iv) a performance analysis of hybrid soft biometrics recognition system using multi-scale criterion. The paper also presents a detailed analysis on the global traits associated to person identity such as gender, age and ethnicity. The contribution of the paper is to provide a comprehensive review of scientific literature, identify open challenges and offer insights on new research directions in the filed.

Following the spread of COVID-19, a sharp rise was found in virtual classrooms worldwide, where ensuring the continuous engagement of participants is a big challenge. Continuous engagement relies on continuous authentication, where technologies like biometrics are helpful to determine the engagement level of the participants. In our work, we developed an application called Face Monitor, which uses facial soft bio-metrics to authenticate the participants arbitrarily, and later to determine the engagement level using this arbitrary authentication information. Our developed application Face Monitor is a critical component of our proposed multi-faceted engagement monitoring platform known as ENGAGE. In our work, several existing online teaching and learning platforms are also compared for existing engagement monitoring support and we defined our own criterion for relative engagement. This paper presents a complete architecture of our developed application called Face Monitor, its functioning, and an output demo. In our opinion, Face Monitor is a genuinely useful application for the higher education sector throughout the world. Face Monitor can be useful to determine the relative level of engagement for different participants during a series of teaching sessions and to calculate overall grades for a module or training session.

Unlicensed cognitive-radio (CR)-assisted Internet of Vehicles (IoV) users can access licensed providers’ radio spectrum and concurrently utilize the dedicated channel for data transmission in vehicular communication. Optimizing channel access in cognitive IoV networks can help maximize available spectrum resources. This article proposes a novel sensing and communication integrated framework, dubbed as the CR-assisted IoV network (CRAV-Net), using a cluster-based hybrid optimization approach with adaptive congestion-aware modeling for dynamic high-mobility vehicular networks in an urban city context. In CRAV-Net, intelligent hybrid learning spectrum agents are introduced, which perform spectrum sensing (SS) using a deep learning (DL) model. It dynamically learns the multilevel spatial and temporal graphical features from input spectrograms through layer-by-layer propagation. It efficiently predicts the spectrum occupancy in the primary spectrum, without a priori knowledge of the radio environment. Then, to assign the vacant channels to the secondary vehicles, a support vector machine classifier is trained based on several learning features, including the vehicle stay time, vehicle density, and network capacity, to select the optimal resource route. The proposed framework achieves an overall accuracy of 99.74% in SS using the custom data set, outperforming state of the art by 12.60% at −25-dB signal-to-noise ratio. In addition, it brings a performance gain of 0.81% in SS accuracy when evaluated on real-world signals. Furthermore, in optimal network node allocation, the proposed framework achieves a mean accuracy of 98.45%, outperforming the existing methods by 0.63% and 18.32% in terms of accuracy and allocation time, respectively.

Auxiliary attachments change is more frequent than essential clothing in human beings. Usually, auxiliary attachments include coat, jumper, hat and bag etc. It is one of the hardest recognition task in machine vision. It becomes more difficult if a specific person is reappearing after a longer time period while the other influential factors are angle variation and walking speed etc. One of the key application areas for person verification is border control where auxiliary attachments variation is more common. It is usually reflection of ethnicity or fashion. In machine vision, availability of such datasets is very limited, in particular, having reappearance after longer time period i.e., more than weeks or months. To overcome limited dataset problem, transfer learning is a leading solution for improved verification. In this paper, we proposed an aggregated deep learning model called, ApparelNet, more specifically for person verification in border control environment. We used Front-View Gait (FVG) to evaluate the performance of our aggregated model. The FVG is a pedestrian dataset of people encompassing auxiliary attachments variation, having three different angles from the camera and three different walking speeds. Our ApparelNet acquires single image based detection confidence using OpenPose and later additional layers of pre-trained EfficientNetB0 are trained on custom FVG dataset, including fine tuning of the overall EfficientNetB0. The EfficientNetB0 is highly efficient and scalable transfer learning model from the family of Deep-CNN. Overall, our ApparelNet reported training and validation accuracy of 98%, while looking at border control scenario, model verification is performed by selecting random images of 12 different individuals and prediction probability is computed which accumulates to 96%. In our opinion, the model has strong candidature for person reidentification where goal is one-to-many recognition. It may become an ancillary component of any biometrics system too.