As one of the most established biometric modalities, fingerprint recognition plays a crucial role in personal authentication and security systems, with fingerprints captured through contact-based or contactless acquisition. However, contactless fingerprint data remains relatively scarce compared to contact-based data, posing challenges for both intra-domain and cross-domain matching. To address these issues, we propose a contact-to-contactless fingerprint generation approach, which integrates a GAN-based fingerprint transfer module with a Unified Fingerprint Enhancement (UFE) module to maintain content consistency and preserve identity information. Extensive experiments on the NIST SD14 database, including both quantitative and qualitative evaluations, demonstrate the effectiveness of the proposed method.

Contactless fingerprint has gained lots of attention in recent fingerprint studies. However, most existing contactless fingerprint algorithms treat contactless fingerprints as 2D plain fingerprints, which lack consideration of the modality difference between contactless and contact fingerprints, especially the intrinsic 3D features in contactless fingerprints. This paper proposes a novel contactless fingerprint recognition algorithm that captures the revealed 3D feature of contactless fingerprints rather than the plain 2D feature. The proposed method first recovers 3D features from the monocular input contactless fingerprint, including the 3D shape model and 3D fingerprint feature (minutiae, orientation, etc.). Then, a novel pose estimation and matching method based on 3D graph network is proposed according to the extracted 3D feature. The proposed method is able to perform robust 3D feature extractions on various contactless fingerprints across multiple finger poses and correcting the pose of contactless fingerprints in 3D space. The results of the experiments on contactless fingerprint databases show that the proposed method successfully improves the matching accuracy of contactless fingerprints. Exceptionally, our method performs stably across multiple poses of contactless fingerprints due to 3D pose regression and embeddings, which is a great advantage compared to 2D-based previous contactless fingerprint recognition algorithms.

Researchers have conducted many pioneer researches on contactless fingerprints, yet the performance of contactless fingerprint recognition still lags behind contact-based methods primary due to the insufficient contactless fingerprint data with pose variations and lack of the usage of implicit 3D fingerprint representations. In this paper, we introduce a novel contactless fingerprint 3D registration, reconstruction and generation framework by integrating 3D Gaussian Splatting, with the goal of offering a new paradigm for contactless fingerprint recognition that integrates 3D fingerprint reconstruction and generation. To our knowledge, this is the first work to apply 3D Gaussian Splatting to the field of fingerprint recognition, and the first to achieve effective 3D registration and complete reconstruction of contactless fingerprints with sparse input images and without requiring camera parameters information. Experiments on 3D fingerprint registration, reconstruction, and generation prove that our method can accurately align and reconstruct 3D fingerprints from 2D images, and sequentially generates high-quality contactless fingerprints from 3D model, thus increasing the performances for contactless fingerprint recognition.

Fingerprint recognition is a crucial biometric authentication technology, known for its uniqueness and stability. Despite recent advancements in fingerprint matching, fingerprint distortions still pose significant challenges to fingerprint matching algorithms. To address this, fingerprint registration techniques have been developed. While supervised dense registration shows promise, it is hindered by speed, accuracy, and data annotation challenges. Unsupervised methods offer a solution to the lack of labeled data to deal with incorrect matches and weak regularization. Inspired by reinforcement learning (RL), this paper introduces an RL-based approach for fingerprint registration, decomposing the process into manageable steps and leveraging the Normalized Cross-Correlation (NCC) reward for unsupervised learning. By decomposing the registration process into incremental steps, our method effectively balances the trade-off between accuracy and the need for extensive data annotation. Experimental results on the FVC2004 dataset demonstrate improved performance, adaptability, and reduced reliance on labeled data. This study enhances the efficiency of fingerprint registration, presenting a robust approach for handling complex deformation fields.

Contactless fingerprint has gained lots of attention in recent fingerprint studies. However, most existing contactless fingerprint algorithms treat contactless fingerprints as 2D plain fingerprints, and still utilize traditional contact-based 2D fingerprints recognition methods. This recognition approach lacks consideration of the modality difference between contactless and contact fingerprints, especially the intrinsic 3D features in contactless fingerprints. This paper proposes a novel contactless fingerprint recognition algorithm that captures the revealed 3D feature of contactless fingerprints rather than the plain 2D feature. The proposed method first recovers 3D features from the input contactless fingerprint, including the 3D shape model and 3D fingerprint feature (minutiae, orientation, etc.). Then, a novel 3D graph matching method is proposed according to the extracted 3D feature. Additionally, the proposed method is able to perform robust 3D feature extractions on various contactless fingerprints across multiple finger poses. The results of the experiments on contactless fingerprint databases show that the proposed method successfully improves the matching accuracy of contactless fingerprints. Exceptionally, our method performs stably across multiple poses of contactless fingerprints due to 3D embeddings, which is a great advantage compared to 2D-based previous contactless fingerprint recognition algorithms.

Electrocardiogram (ECG) signals are crucial indicators of various human physiological states. A thorough analysis of these signals is indispensable for applications such as disease prediction, mental stress assessment, and other medical diagnostics. Despite the rapid progress in large language models (LLM) and their demonstrated prowess in natural language understanding, their application in ECG signal analysis remains underexplored. This paper introduces Tackle Electrocardiogram with Large Language Model Effectively (TELL ME), a novel approach that effectively transfers the robust comprehension capabilities of LLM to ECG signal processing. The method employs a front alignment strategy to align ECG modality with text modality via cross-attention mechanism and incorporates critical manual features into prompts to enhance the performances in specific tasks. The proposed solution has been validated across three downstream tasks, namely, quality assessment, ventricular premature beats detection, and denoising reconstruction, consistently achieving state-of-the-art (SOTA) results.

Distortion of the fingerprint images leads to a decline in fingerprint recognition performance, and fingerprint registration can mitigate this distortion issue by accurately aligning two fingerprint images. Currently, fingerprint registration methods often consist of two steps: an initial registration based on minutiae, and a dense registration based on matching points. However, when the quality of fingerprint image is low, the number of detected minutiae is reduced, leading to frequent failures in the initial registration, which ultimately causes the entire fingerprint registration process to fail. In this study, we propose an end-to-end single-step fingerprint registration algorithm that aligns two fingerprints by directly predicting the semi-dense matching points correspondences between two fingerprints. Thus, our method minimizes the risk of minutiae registration failure and also leverages global-local attentions to achieve end-to-end pixel-level alignment between the two fingerprints. Experiment results prove that our method can achieve the state-of-the-art matching performance with only single-step registration, and it can also be used in conjunction with dense registration algorithms for further performance improvements.

The detection and recognition of distracted driving behaviors has emerged as a new vision task with the rapid development of computer vision, which is considered as a challenging temporal action localization (TAL) problem in computer vision. The primary goal of temporal localization is to determine the start and end time of actions in untrimmed videos. Currently, most state-of-the-art temporal localization methods adopt complex architectures, which are cumbersome and time-consuming. In this paper, we propose a robust and efficient two-stage framework for distracted behavior classification-localization based on the sliding window approach, which is suitable for untrimmed naturalistic driving videos. To address the issues of high similarity among different behaviors and interference from background classes, we propose a multi-view fusion and adaptive thresholding algorithm, which effectively reduces missing detections. To address the problem of fuzzy behavior boundary localization, we design a post-processing procedure that achieves fine localization from coarse localization through post connection and candidate behavior merging criteria. In the AICITY2024 Task3 TestA, our method performs well, achieving Average Intersection over Union(AIOU) of 0.6080 and ranking eighth in AICITY2024 Task3. Our code will be released in the near future.

In the realm of intelligent traffic systems, fisheye cameras have emerged as a pivotal tool, distinguished by their expansive field of view which significantly enhances the surveillance of complex street networks and intersections. However, the inherent distortion characteristics of fisheye lenses, various illumination, tiny objects and confusion of vehicle classes pose significant challenges to conventional image processing and object detection techniques. To address these challenges, we propose an advanced object detection framework named FE-Det specifically designed for fisheye cameras in traffic monitoring systems. This framework integrates detection models optimized for day and night scene variability. Additionally, it incorporates innovative post-processing operations which brings detection enhancement, including a Vehicles Classifier Module for precise vehicle identification, a Static Objects Processing Module for more accurate detection of stationary objects and a Confidence Score Refinement Module to adjust confidence scores for improving the detection of peripheral objects. Experimental evidence substantiates that our framework exhibits a 1.4% improvement in distinguishing between day and night scenes compared to traditional models. Moreover, the application of the proposed post-processing method results in an additional enhancement of 4.1%.

At the current stage of autonomous driving, monitoring the behavior of safety stewards (drivers) is crucial to establishing liability in the event of an accident. However, there is currently no method for the quantitative assessment of safety steward behavior that is trusted by multiple stakeholders. In recent years, deep-learning-based methods can automatically detect abnormal behaviors with surveillance video, and blockchain as a decentralized and tamper-resistant distributed ledger technology is very suitable as a tool for providing evidence when determining liability. In this paper, a trusted supervision paradigm for autonomous driving (TSPAD) based on multimodal data authentication is proposed. Specifically, this paradigm consists of a deep learning model for driving abnormal behavior detection based on key frames adaptive selection and a blockchain system for multimodal data on-chaining and certificate storage. First, the deep-learning-based detection model enables the quantification of abnormal driving behavior and the selection of key frames. Second, the key frame selection and image compression coding balance the trade-off between the amount of information and efficiency in multiparty data sharing. Third, the blockchain-based data encryption sharing strategy ensures supervision and mutual trust among the regulatory authority, the logistic platform, and the enterprise in the driving process.

Contactless fingerprint has gained lots of attention in recent fingerprint studies. However, most existing contactless fingerprint algorithms treat contactless fingerprints as 2D plain fingerprints, and still utilize traditional contact-based 2D fingerprints recognition methods. This recognition approach lacks consideration of the modality difference between contactless and contact fingerprints, especially the intrinsic 3D features in contactless fingerprints. This paper proposes a novel contactless fingerprint recognition algorithm that captures the revealed 3D feature of contactless fingerprints rather than the plain 2D feature. The proposed method first recovers 3D features from the input contactless fingerprint, including the 3D shape model and 3D fingerprint feature (minutiae, orientation, etc.). Then, a novel 3D graph matching method is proposed according to the extracted 3D feature. Additionally, the proposed method is able to perform robust 3D feature extractions on various contactless fingerprints across multiple finger poses. The results of the experiments on contactless fingerprint databases show that the proposed method successfully improves the matching accuracy of contactless fingerprints. Exceptionally, our method performs stably across multiple poses of contactless fingerprints due to 3D embeddings, which is a great advantage compared to 2D-based previous contactless fingerprint recognition algorithms.

In recent years, motorcycle accidents have occurred frequently, with a important reason being that motorcyclists do not wear helmets properly. The visual method of detecting whether a motorcyclist is wearing helmet based on monitoring videos can provide technical support for traffic management. However, the appearance characteristics of motorcycle drivers and passengers are too similar to distinguish, which makes it difficult to detect helmet. In this task, we propose a Coarse-to-fine Two-stage Helmet Detection Method for Motorcyclists to improve the accuracy of helmet and motorcyclist detection. Our Coarse detector detect the rough location of people and motorcycle as the initial suggestion for the following Fine-grained detection. Then our Fine-grained detector employs a classification branch to accurately distinguish between the driver and passengers. Finally, we use some useful strategies such as Test Time Augmentation (TTA) and Weighted Boxes Fusion (WBF) to achieve further improvements to our proposed framework. Our proposed framework achieved mAP score of 39.4 % on the test dataset of AI City Challenge 2024 Track5.

Compared with contact-based fingerprint acquisition techniques, contactless acquisition has the advantages of less skin distortion, more complete fingerprint area, and hygienic acquisition. However, perspective distortion is a challenge in contactless fingerprint recognition, which changes the ridge frequency and relative minutiae location, and thus degrades the recognition accuracy. We propose a learning-based shape-from-texture algorithm to reconstruct a 3-D finger shape from a single image and unwarp the raw image to suppress the perspective distortion. Our experimental results for 3-D reconstruction on contactless fingerprint databases show that the proposed method has high 3-D reconstruction accuracy. Experimental results for contactless-to-contactless and contactless-to-contact-based fingerprint matching indicate that the proposed method can improve the matching accuracy.

Fingerprint registration is still a challenging task due to the large variation of fingerprint quality. Meanwhile, existing supervised fingerprint registration methods need sufficient amount of labeled fingerprint pairs which are difficult to obtain. In addition, the training data itself may not include enough variety of fingerprints thus limit such methods’ performance. In this work, we propose an unsupervised end-to-end framework for fingerprint registration which doesn’t require labeled fingerprint data. The proposed network is based on spatial transformer networks, and can be applied flexibly to achieve a better results by being used recursively. Experiment results show that our method gets the state-of-the-art matching scores while preserving the good ridge structure of fingerprints, and achieves competitive matching accuracy through score fusion when compared with supervised methods.