检索结果-内蒙古大学图书馆

Optimisation of a Siamese Neural Network for Real-Time Energy Efficient Object Tracking 1

学校读者我要写书评

暂无评论

International Conference on computer vision and Graphics, ICCVG 2020

作者： Przewlocka, Dominika Wasala, Mateusz Szolc, Hubert Blachut, Krzysztof Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (数字)9783030590062

ISBN: (纸本)9783030590055

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution video stream, with the lowest possible energy consumption. To meet these requirements, techniques such as the reduction of computational precision and pruning were considered. Brevitas, a tool dedicated for optimisation and quantisation of neural networks for FPGA implementation, was used. A number of training scenarios were tested with varying levels of optimisations – from integer uniform quantisation with 16 bits to ternary and binary networks. Next, the influence of these optimisations on the tracking performance was evaluated. It was possible to reduce the size of the convolutional filters up to 10 times in relation to the original network. The obtained results indicate that using quantisation can significantly reduce the memory and computational complexity of the proposed network while still enabling precise tracking, thus allow to use it in embedded vision systems. Moreover, quantisation of weights positively affects the network training by decreasing overfitting. © 2020, Springer Nature Switzerland AG.

关键词： Field programmable gate arrays (FPGA)

A vision Based Hardware-Software Real-Time Control System for the Autonomous Landing of an UAV 1

学校读者我要写书评

暂无评论

International Conference on computer vision and Graphics, ICCVG 2020

作者： Blachut, Krzysztof Szolc, Hubert Wasala, Mateusz Kryjak, Tomasz Gorgon, Marek Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (数字)9783030590062

ISBN: (纸本)9783030590055

In this paper we present a vision based hardware-software control system enabling the autonomous landing of a multirotor unmanned aerial vehicle (UAV). It allows for the detection of a marked landing pad in real-time for a 1280 720 @ 60 fps video stream. In addition, a LiDAR sensor is used to measure the altitude above ground. A heterogeneous Zynq SoC device is used as the computing platform. The solution was tested on a number of sequences and the landing pad was detected with 96% accuracy. This research shows that a reprogrammable heterogeneous computing system is a good solution for UAVs because it enables real-time data stream processing with relatively low energy consumption. © 2020, Springer Nature Switzerland AG.

关键词： System-on-chip

Rediscovering BCE Loss for Uniform Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Computer Vision Institute Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China

This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric to measure the model’s performance in uniform classification. Furthermore, begin with a naive loss, we mathematically derive a loss function suitable for the uniform classification, which is the BCE function integrated with a unified bias. We demonstrate the unified threshold could be learned via the bias. The extensive experiments on six classification datasets and three feature extraction models show that, compared to the SoftMax loss, the models trained with the BCE loss not only exhibit higher uniform classification accuracy but also higher sample-wise classification accuracy. In addition, the learned bias from BCE loss is very close to the unified threshold used in the uniform classification. The features extracted by the models trained with BCE loss not only possess uniformity but also demonstrate better intra-class compactness and inter-class distinctiveness, yielding superior performance on open-set tasks such as face recognition. © 2024, CC BY.

关键词： Classification (of information)

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models’ biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024, CC BY.

关键词： Contrastive Learning

Efficiently Approaching Groups of People in a Socially Acceptable Manner in Environments with Obstacles

学校读者我要写书评

暂无评论

Efficiently Approaching Groups of People in a Socially Accep...

IEEE International Conference on robotics and Automation (ICRA)

作者： Aline F. F. Silva Luciano E. Almeida Douglas G. Macharet Department of Computer Science Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais Brazil Laboratório de Inteligência Computacional e Robótica (LICRo) Instituto Federal do Triângulo Mineiro (IFTM) Brazil

Advancements in mobile robotics have allowed humans and robots to interact in different environments and ways. A problem of great interest in Human-Robot Interaction is how to approach individuals, e.g., to gather information, in a socially acceptable manner. We present a new method for planning sequential visits to various groups of people in cluttered environments. The problem is formulated as a Set Orienteering Problem, where each group denotes a cluster with a set of possible approaching points considering different F-formations. We use the concept of a social probabilistic roadmap to determine safe paths between groups. Simulations considering different cases show that methodology produces efficient tours that maximize the number of approached individuals while respecting social norms of distance and a limited budget.

关键词：

Traffic Sign Detection With Event Cameras and DCNN

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wzorek, Piotr Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Kraków Poland Department of Digital Systems Silesian University of Technology Gliwice Poland

In recent years, event cameras (DVS – Dynamic vision Sensors) have been used in vision systems as an alternative or supplement to traditional cameras. They are characterised by high dynamic range, high temporal resolution, low latency, and reliable performance in limited lighting conditions – parameters that are particularly important in the context of advanced driver assistance systems (ADAS) and self-driving cars. In this work, we test whether these rather novel sensors can be applied to the popular task of traffic sign detection. To this end, we analyse different representations of the event data: event frame, event frequency, and the exponentially decaying time surface, and apply video frame reconstruction using a deep neural network called FireNet. We use the deep convolutional neural network YOLOv4 as a detector. For particular representations, we obtain a detection accuracy in the range of 86.9-88.9% mAP@0.5. The use of a fusion of the considered representations allows us to obtain a detector with higher accuracy of 89.9% mAP@0.5. In comparison, the detector for the frames reconstructed with FireNet is characterised by an accuracy of 72.67% mAP@0.5. The results obtained illustrate the potential of event cameras in automotive applications, either as standalone sensors or in close cooperation with typical frame-based cameras. © 2022, CC BY.

关键词： Cameras

Pointsurface: Discriminative Point Cloud Surface Feature Extraction for 3d Face Recognition

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Yang, Junpeng Li, Qiufu Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Guangdong Shenzhen518172 China

3D face recognition performs better than 2D face recognition, in terms of robustness against lighting and digital attacks. Compared to 2D data, the rich geometric information in 3D data could be very useful to improve the performance of 3D face recognition. This paper introduces PointSurFace, a surface feature extraction integrated model tailored for point cloud based 3D face recognition. PointSurFace adopts a specially designed surface feature extraction module, which explores information about the position and normals of the 3D face surface to explicitly extract local discriminative features from 3D point cloud faces. Subsequently, it alternates between set abstraction (SA) layers and Inverted Residual MLP (InvResMLP) modules to effectively extract features from the point cloud data. To better handle the spatial relationships in the point cloud data, PointSurFace integrates coordinate and feature data within each SA layer and InvResMLP module. It also applies channel fusion operations to align these different types of data, thereby more effectively extracts point cloud features. Experimental results in 3D facial recognition and verification across multiple datasets demonstrate that PointSurFace achieves the best 3D face recognition performance to date. For example, on Lock3DFace, it achieves the state-of-the-art recognition and verification accuracy of 90.03% and 80.01%, respectively, surpassing previous methods by 2.02% and 3.19%. Results on cross-quality datasets also affirm PointSurFace’s strong generalization capabilities. Ablation experiments validate the effectiveness of each module within PointSurFace, which suggests that the proposed surface feature extraction module significantly enhances the point cloud based 3D facial recognition performance. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Luo, Cheng Lin, Qinliang Xie, Weicheng Wu, Bizhu Xie, Jinheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University2Shenzhen Institute of Artificial Intelligence & Robotics for Society3Guangdong Key Laboratory of Intelligent Information Processing

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they rely on a classification layer with a closed set of categories. Furthermore, the perturbations generated by these methods may appear in regions easily perceptible to the human visual system (HVS). To circumvent the former problem, we propose a novel algorithm that attacks semantic similarity on feature representations. In this way, we are able to fool classifiers without limiting attacks to a specific dataset. For imperceptibility, we introduce the low-frequency constraint to limit perturbations within high-frequency components, ensuring perceptual similarity between adversarial examples and originals. Extensive experiments on three datasets (CIFAR-10, CIFAR-100, and ImageNet-1K) and three public online platforms indicate that our attack can yield misleading and transferable adversarial examples across architectures and datasets. Additionally, visualization results and quantitative performance (in terms of four different metrics) show that the proposed algorithm generates more imperceptible perturbations than the state-of-the-art methods. Code is made available at https://***/LinQinLiang/SSAH-adversarial-attack. © 2022, CC BY.

关键词： Classification (of information)