MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodes
Electrical, Electronic and Information Engineering (DEI), University of Bologna, Italy.(博洛尼亚大学电气、电子与信息工程学院,意大利);Department of Electrical Engineering (ESAT), KU Leuven, Belgium.(卢旺达大学电气工程系,比利时);Dalle Molle Institute for Artificial Intelligence (IDSIA), USI--SUPSI, Switzerland.(人工智能研究所(IDSIA),瑞士USI--SUPSI)
Luca Bompani, Manuele Rusci, Luca Benini, Daniele Palossi, Francesco Conti
Modern smart vision sensors need on-device intelligence to process video streams, as cloud computing is often impractical due to bandwidth, latency, and privacy constraints. However, these sensory systems typically rely on ultra-low-power microcontrollers (MCUs) with limited memory and compute, making conventional video object detection methods, which require feature storage or multi-frame buffering, unfeasible. To address this challenge, we introduce Multi-Resolution Rescored ByteTrack (MR2-ByteTrack), a Video Object Detection (VOD) method tailored for MCU-based embedded vision nodes. MR2-ByteTrack reduces computational cost by alternating between full- and low-resolution inference, while linking detections across frames via ByteTrack and correcting misclassifications through the Rescore algorithm, which applies probability union rules to aggregate detection confidence scores across frames. We apply our approach to both a CNN-based detector and a Transformer-based model, demonstrating its generality across architectures with fundamentally different spatial processing. Experiments on ImageNetVID demonstrate that MR2-ByteTrack maintains accuracy, achieving mAP scores of up to 49.0 for the CNN-based models and 48.7 for the Transformer, while reducing multiply-accumulate operations by as much as 53\% for the CNNs and 32\% for the Transformer. When deployed on GAP9, an ultra-low-power RISC-V multicore MCU, our method yields up to 55\% energy savings compared to processing only full-resolution images, enabling the first real-time Transformer-based VOD on an MCU-class embedded vision node. Code available at https://github.com/Bomps4/Multi_Resolution_Rescored_ByteTrack/tree/IEEE_Access
Efficient 3D affinely equivariant CNNs with adaptive fusion of augmented spherical Fourier-Bessel bases
School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics(南京金融学院计算机与人工智能学院);Interdisciplinary Center for Scientific Computing, Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University(科学计算交叉中心、医学智能系统研究所、曼海姆医学院、海德堡大学);Computer Assisted Clinical Medicine, Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University(临床医学辅助计算机、医学智能系统研究所、曼海姆医学院、海德堡大学);Department of Diagnostic and Interventional Radiology, University Hospital Bonn(诊断与介入放射科、波恩大学医院);Interdisciplinary Center for Scientific Computing, Central Institute for Computer Engineering, CSZ Heidelberg Center for Model-Based AI, Data Analysis and Modeling in Medicine, Mannheim Institute for Intelligent Systems in Medicine, Medical Faculty Mannheim, Heidelberg University(科学计算交叉中心、计算机工程中央研究所、海德堡模型驱动AI中心、医学数据与建模中心、曼海姆医学智能系统研究所、曼海姆医学院、海德堡大学)
Stingray Detection of Aerial Images Using Augmented Training Images Generated by A Conditional Generative Model
Institute of Information Science, Academia Sinica(中央研究院资讯科学研究所);MOST Joint Research Center for AI Technology and All Vista Healthcare(科技部AI技术与全视医疗照护联合研究中心);National Sun Yat-sen University(国立中山大学)
SDCT-AuxNet$^θ$: DCT Augmented Stain Deconvolutional CNN with Auxiliary Classifier for Cancer Diagnosis
IIIT-Delhi(德里印度理工学院信息技术学院);AIIMS(全印医学科学学院)
急性淋巴细胞白血病(ALL)是一种全球普遍存在的儿科白细胞癌症。随着卷积神经网络(CNN)的普及,癌症的计算机辅助诊断引起了人们的广泛关注。这些工具易于部署,具有成本效益。因此,这些可以使癌症诊断设施的广泛覆盖成为可能。然而,到目前为止,由于没有大型训练数据集,开发这种用于ALL癌症的工具具有挑战性。恶性细胞和正常细胞之间的视觉相似性增加了问题的复杂性。本文讨论了最近发布的一个大型数据集,并提出了一种用于ALL癌症细胞图像分类的新型深度学习架构。所提出的架构,即SDCT-CNN Net $^θ$是一个2模块框架,它利用紧凑的CNN作为一个模块中的主分类器和核SVM作为辅助分类器在另一个。虽然CNN分类器通过双线性池化来使用特征,但是辅助分类器使用频谱平均特征。此外,该CNN是在光密度域中的染色剂去卷积量图像上而不是在传统的RGB图像上训练的。提出了一种新的测试策略,利用两个分类器的决策使用的置信度分数的预测类标签。在我们最近发布的15114张ALL癌症和健康细胞图像的公共数据集上进行了详细的实验,以确定所提出的方法的有效性,该方法对受试者水平的变异性也是鲁棒的。获得的加权F1评分为94.8 $\%$,这是迄今为止在这个具有挑战性的数据集上最好的。
Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
American International University-Bangladesh(美国国际大学-孟加拉国);Asian University of Bangladesh(孟加拉国亚洲大学);Information and Computer Science Department, King Fahd University of Petroleum and Minerals (KFUPM)(石油和矿物大学(KFUPM)信息与计算机科学系);SDAIA-KFUPM Joint Research Center for AI, King Fahd University of Petroleum and Minerals(人工智能联合研究中心(SDAIA-KFUPM), 石油和矿物大学);Interdisciplinary Research Center for Bio Systems and Machines, King Fahd University of Petroleum and Minerals(生物系统与机器交叉研究中心,石油和矿物大学);Independent University, Bangladesh(独立大学)
XMACNet: An Explainable Lightweight Attention based CNN with Multi Modal Fusion for Chili Disease Classification
Vellore Institute of Technology(韦洛尔理工学院);Angel College of Engineering and Technology(安吉尔工程技术学院);Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology(Vel Tech朗加拉詹·萨贡塔拉博士科技研究院);Bannari Amman Institute of Technology(班纳里·安曼理工学院)
Nondestructive chicken egg fertility detection using CNN-transfer learning algorithms
Institute of Computer Science, AGH University of Krakow(克拉科夫AGH科技大学计算机科学研究所);Universitas Pembangunan Nasional Veteran Yogyakarta(印度尼西亚国立日惹退伍大学);Universitas Negeri Malang(玛琅州立大学);Universitas Ahmad Dahlan(艾哈迈德·达兰大学);Hohai University(河海大学);Sylhet Agricultural University(锡尔赫特农业大学);King Abdulaziz University(阿卜杜勒阿齐兹国王大学);American University(美利坚大学)
Predicting 1p19q Chromosomal Deletion of Low-Grade Gliomas from MR Images using Deep Learning
Radiology Informatics Lab, Mayo Clinic(梅奥诊所放射信息实验室);Department of Pathology, Mayo Clinic(梅奥诊所病理科);Department of Neurologic Surgery, Mayo Clinic(梅奥诊所神经外科)
CT Scans As Video: Efficient Intracranial Hemorrhage Detection Using Multi-Object Tracking
Faculty of Computer Engineering, K. N. Toosi University of Technology(计算机工程学院,K.N. Toosi技术大学);Faculty of Electrical Engineering, K. N. Toosi University of Technology(电气工程学院,K.N. Toosi技术大学);Faculty of Mechanical Engineering, Tarbiat Modares University(机械工程学院,塔里亚特莫达雷斯大学)
Detection Of Concrete Cracks using Dual-channel Deep Convolutional Network
National Institute of Technology Durgapur(杜尔加普尔国家理工学院)
由于循环荷载和疲劳应力,会产生裂缝,影响任何民用基础设施的安全。如今,机器视觉正被用来帮助我们对混凝土结构进行适当的维护、监测和检查,部分取代人工进行的现场检查。提出了一种基于深度卷积神经网络(CNN)的裂缝检测方法,用于混凝土裂缝检测,无需显式计算缺陷特征。在研究过程中,创建了一个包含3200个混凝土裂缝标记图像的数据库,其中裂缝的对比度,照明条件,方向和严重程度变化非常大。在本文中,从使用这些256 x 256像素分辨率的图像训练的深度CNN开始,我们通过识别困难来逐步优化模型。使用增强的数据集,考虑到与无人机视频兼容的变化和退化,如随机缩放,旋转和强度缩放以及详尽的消融研究,我们设计了一个双通道深度CNN,它在现实情况下显示出高准确性(~ 92.25%)以及在寻找混凝土裂缝方面的鲁棒性。该模型已被测试的基础上的性能和分析的帮助下的特征图,建立了双通道结构的重要性。
AEGIS: A real-time multimodal augmented reality computer vision based system to assist facial expression recognition for individuals with autism spectrum disorder
University of Waterloo(滑铁卢大学);Vision and Image Processing Lab(视觉与图像处理实验室)
Enhancing Robustness of Human Detection Algorithms in Maritime SAR through Augmented Aerial Images to Simulate Weather Conditions
Jakarta Intercultural School(雅加达国际学校);Busan Foreign School(釜山外国语学校);SMPK 8 Penabur Tanjung Duren(丹戎杜伦佩纳布尔8号初中(基督教学校));Avon High School(雅芳高中);Algoverse AI Research(Algoverse人工智能研究院)