Drone or unmanned aerial vehicle(UAV)technology has undergone significant changes.The technology allows UAV to carry out a wide range of tasks with an increasing level of sophistication,since drones can cover a large ...Drone or unmanned aerial vehicle(UAV)technology has undergone significant changes.The technology allows UAV to carry out a wide range of tasks with an increasing level of sophistication,since drones can cover a large area with cameras.Meanwhile,the increasing number of computer vision applications utilizing deep learning provides a unique insight into such applications.The primary target in UAV-based detection applications is humans,yet aerial recordings are not included in the massive datasets used to train object detectors,which makes it necessary to gather the model data from such platforms.You only look once(YOLO)version 4,RetinaNet,faster region-based convolutional neural network(R-CNN),and cascade R-CNN are several well-known detectors that have been studied in the past using a variety of datasets to replicate rescue scenes.Here,we used the search and rescue(SAR)dataset to train the you only look once version 5(YOLOv5)algorithm to validate its speed,accuracy,and low false detection rate.In comparison to YOLOv4 and R-CNN,the highest mean average accuracy of 96.9%is obtained by YOLOv5.For comparison,experimental findings utilizing the SAR and the human rescue imaging database on land(HERIDAL)datasets are presented.The results show that the YOLOv5-based approach is the most successful human detection model for SAR missions.展开更多
针对Yolov3-Tiny算法在加油站监控场景检测时由于数据特征提取不充分而导致检测精度低、漏检率高等问题,提出一种基于加油站场景的Misp-YOLO(You Only Look Once)目标检测算法。首先引入Mosaic数据增强算法,使图片包含更多特征信息;其...针对Yolov3-Tiny算法在加油站监控场景检测时由于数据特征提取不充分而导致检测精度低、漏检率高等问题,提出一种基于加油站场景的Misp-YOLO(You Only Look Once)目标检测算法。首先引入Mosaic数据增强算法,使图片包含更多特征信息;其次使用InceptionV2和PSConv(Poly-Scale Convolution)多尺度特征提取方法提升网络多尺度预测能力;最后结合scSE(Concurrent Spatial and Channel ‘Squeeze&Excitation’)注意力机制,重构主干网络输出特征。实验结果证明该算法具有较高检测准确度,并且检测速度满足实际需求。优化后的算法性能得到极大提升,可推广应用于其他目标检测中。展开更多
为提高传统目标检测的识别效果和准确率,并加快运算速度,提出了一种具有更强大特征学习和特征表达能力的卷积神经网络(CNN:Convolutional Neural Network)模型和相关的深度学习训练算法,并将其应用于计算机视觉领域的大规模识别任务。...为提高传统目标检测的识别效果和准确率,并加快运算速度,提出了一种具有更强大特征学习和特征表达能力的卷积神经网络(CNN:Convolutional Neural Network)模型和相关的深度学习训练算法,并将其应用于计算机视觉领域的大规模识别任务。首先详细分析了传统目标检测算法,如V-J(Viola-Jones)检测器、 HOG(Histogram of Oriented Gradients)特征结合SVM(Support Vector Machine)分类器和DPM(Deformable Parts Model)检测器的特点。然后提出了深度学习算法,如RCNN(Region-based Convolutional Neural Networks)算法和YOLO(You Only Look Once)算法,并分析了其在目标检测任务中的应用现状。针对倒地检测任务,使用YOLOv5(You Only Look Once version 5)模型对不同身高体型目标人群的行为进行训练。通过使用不同的交并比(IOU:Intersection over Union)、准确率(Precision,P)、召回率(Recall,R)和PR曲线等评估指标,对YOLOv5模型进行了分析,评估了其在检测站立和倒地两种活动方式的实际效果。同时通过预训练和增强处理,增加了训练样本数量并提高了网络的识别准确率。实验结果表明,倒地识别率达到了86%。可将其应用于灾区探测救援类机器人的设计中,以辅助识别和分类受伤倒地人员,提高灾区救援效率。展开更多
自动驾驶场景下的目标检测是计算机视觉中重要研究方向之一,确保自动驾驶汽车对物体进行实时准确的目标检测是研究重点。近年来,深度学习技术迅速发展并被广泛应用于自动驾驶领域中,极大促进了自动驾驶领域的进步。为此,针对YOLO(You On...自动驾驶场景下的目标检测是计算机视觉中重要研究方向之一,确保自动驾驶汽车对物体进行实时准确的目标检测是研究重点。近年来,深度学习技术迅速发展并被广泛应用于自动驾驶领域中,极大促进了自动驾驶领域的进步。为此,针对YOLO(You Only Look Once)算法在自动驾驶领域中的目标检测研究现状,从以下4个方面分析。首先,总结单阶段YOLO系列检测算法思想及其改进方法,分析YOLO系列算法的优缺点;其次,论述YOLO算法在自动驾驶场景下目标检测中的应用,从交通车辆、行人和交通信号识别这3个方面分别阐述和总结研究现状及应用情况;此外,总结目标检测中常用的评价指标、目标检测数据集和自动驾驶场景数据集;最后,展望目标检测存在的问题和未来发展方向。展开更多
For the detection of marine ship objects in radar images, large-scale networks based on deep learning are difficult to be deployed on existing radar-equipped devices. This paper proposes a lightweight convolutional ne...For the detection of marine ship objects in radar images, large-scale networks based on deep learning are difficult to be deployed on existing radar-equipped devices. This paper proposes a lightweight convolutional neural network, LiraNet, which combines the idea of dense connections, residual connections and group convolution, including stem blocks and extractor modules.The designed stem block uses a series of small convolutions to extract the input image features, and the extractor network adopts the designed two-way dense connection module, which further reduces the network operation complexity. Mounting LiraNet on the object detection framework Darknet, this paper proposes Lira-you only look once(Lira-YOLO), a lightweight model for ship detection in radar images, which can easily be deployed on the mobile devices. Lira-YOLO's prediction module uses a two-layer YOLO prediction layer and adds a residual module for better feature delivery. At the same time, in order to fully verify the performance of the model, mini-RD, a lightweight distance Doppler domain radar images dataset, is constructed. Experiments show that the network complexity of Lira-YOLO is low, being only 2.980 Bflops, and the parameter quantity is smaller, which is only 4.3 MB. The mean average precision(mAP) indicators on the mini-RD and SAR ship detection dataset(SSDD) reach 83.21% and 85.46%, respectively,which is comparable to the tiny-YOLOv3. Lira-YOLO has achieved a good detection accuracy with less memory and computational cost.展开更多
针对YOLO(you only look once)v5算法在应用于光学遥感图像舰船目标检测任务时所面临的小目标误检率、漏检率较高的情况,提出一种基于YOLOv5改进的光学遥感图像舰船目标检测方法。首先对路径聚合网络结构进行改进,设计语义信息增强模块...针对YOLO(you only look once)v5算法在应用于光学遥感图像舰船目标检测任务时所面临的小目标误检率、漏检率较高的情况,提出一种基于YOLOv5改进的光学遥感图像舰船目标检测方法。首先对路径聚合网络结构进行改进,设计语义信息增强模块提取更富语义信息的浅层特征,增强对小目标特征的表达能力;然后使用Swish函数作为激活函数,提高网络对数据非线性特征的表征能力,加快模型的收敛速度;最后针对舰船目标的尺寸特点优化检测端结构,移除大目标检测头以减少推理计算量。测试集上的实验表明,该方法相较改进前将检测精度提高了5.2%且推理时间有所减少,在保证检测实时性的同时增强了模型的小目标辨别能力。展开更多
目前乳腺癌已取代肺癌成为年发病率最高的癌症,基于深度学习的目标检测技术可对乳腺X线、乳腺超声和乳腺核磁共振等非侵入式成像进行自动病变检测,已成为乳腺癌辅助诊断的首选途径.YOLO(you only look once)系列算法是基于深度学习的目...目前乳腺癌已取代肺癌成为年发病率最高的癌症,基于深度学习的目标检测技术可对乳腺X线、乳腺超声和乳腺核磁共振等非侵入式成像进行自动病变检测,已成为乳腺癌辅助诊断的首选途径.YOLO(you only look once)系列算法是基于深度学习的目标检测算法,经典YOLO算法在速度和精准度具有优势,被广泛应用于计算机视觉各领域,最新YOLO算法是计算机视觉领域的SOTA(state of the art)模型,如何利用YOLO系列算法提高乳腺癌检测速度和准确率,已经成为研究者关注的焦点之一.基于此,本文介绍经典YOLO系列算法的原理,梳理经典YOLO系列算法在乳腺癌图像检测中的应用现状,并归纳总结现存问题,同时对YOLO系列算法在乳腺癌检测的进一步应用进行展望.展开更多
文摘Drone or unmanned aerial vehicle(UAV)technology has undergone significant changes.The technology allows UAV to carry out a wide range of tasks with an increasing level of sophistication,since drones can cover a large area with cameras.Meanwhile,the increasing number of computer vision applications utilizing deep learning provides a unique insight into such applications.The primary target in UAV-based detection applications is humans,yet aerial recordings are not included in the massive datasets used to train object detectors,which makes it necessary to gather the model data from such platforms.You only look once(YOLO)version 4,RetinaNet,faster region-based convolutional neural network(R-CNN),and cascade R-CNN are several well-known detectors that have been studied in the past using a variety of datasets to replicate rescue scenes.Here,we used the search and rescue(SAR)dataset to train the you only look once version 5(YOLOv5)algorithm to validate its speed,accuracy,and low false detection rate.In comparison to YOLOv4 and R-CNN,the highest mean average accuracy of 96.9%is obtained by YOLOv5.For comparison,experimental findings utilizing the SAR and the human rescue imaging database on land(HERIDAL)datasets are presented.The results show that the YOLOv5-based approach is the most successful human detection model for SAR missions.
文摘针对Yolov3-Tiny算法在加油站监控场景检测时由于数据特征提取不充分而导致检测精度低、漏检率高等问题,提出一种基于加油站场景的Misp-YOLO(You Only Look Once)目标检测算法。首先引入Mosaic数据增强算法,使图片包含更多特征信息;其次使用InceptionV2和PSConv(Poly-Scale Convolution)多尺度特征提取方法提升网络多尺度预测能力;最后结合scSE(Concurrent Spatial and Channel ‘Squeeze&Excitation’)注意力机制,重构主干网络输出特征。实验结果证明该算法具有较高检测准确度,并且检测速度满足实际需求。优化后的算法性能得到极大提升,可推广应用于其他目标检测中。
基金The Natural Science Foundation of Jiangsu Province(No.BK20230956)the Jiangsu Funding Program for Excellent Postdoctoral Talents(No.2022ZB188)the Transportation Technology Plan Project of Jiangsu Province(No.2020QD28).
文摘为提高传统目标检测的识别效果和准确率,并加快运算速度,提出了一种具有更强大特征学习和特征表达能力的卷积神经网络(CNN:Convolutional Neural Network)模型和相关的深度学习训练算法,并将其应用于计算机视觉领域的大规模识别任务。首先详细分析了传统目标检测算法,如V-J(Viola-Jones)检测器、 HOG(Histogram of Oriented Gradients)特征结合SVM(Support Vector Machine)分类器和DPM(Deformable Parts Model)检测器的特点。然后提出了深度学习算法,如RCNN(Region-based Convolutional Neural Networks)算法和YOLO(You Only Look Once)算法,并分析了其在目标检测任务中的应用现状。针对倒地检测任务,使用YOLOv5(You Only Look Once version 5)模型对不同身高体型目标人群的行为进行训练。通过使用不同的交并比(IOU:Intersection over Union)、准确率(Precision,P)、召回率(Recall,R)和PR曲线等评估指标,对YOLOv5模型进行了分析,评估了其在检测站立和倒地两种活动方式的实际效果。同时通过预训练和增强处理,增加了训练样本数量并提高了网络的识别准确率。实验结果表明,倒地识别率达到了86%。可将其应用于灾区探测救援类机器人的设计中,以辅助识别和分类受伤倒地人员,提高灾区救援效率。
文摘自动驾驶场景下的目标检测是计算机视觉中重要研究方向之一,确保自动驾驶汽车对物体进行实时准确的目标检测是研究重点。近年来,深度学习技术迅速发展并被广泛应用于自动驾驶领域中,极大促进了自动驾驶领域的进步。为此,针对YOLO(You Only Look Once)算法在自动驾驶领域中的目标检测研究现状,从以下4个方面分析。首先,总结单阶段YOLO系列检测算法思想及其改进方法,分析YOLO系列算法的优缺点;其次,论述YOLO算法在自动驾驶场景下目标检测中的应用,从交通车辆、行人和交通信号识别这3个方面分别阐述和总结研究现状及应用情况;此外,总结目标检测中常用的评价指标、目标检测数据集和自动驾驶场景数据集;最后,展望目标检测存在的问题和未来发展方向。
基金supported by the Joint Fund of Equipment Pre-Research and Aerospace Science and Industry (6141B07090102)。
文摘For the detection of marine ship objects in radar images, large-scale networks based on deep learning are difficult to be deployed on existing radar-equipped devices. This paper proposes a lightweight convolutional neural network, LiraNet, which combines the idea of dense connections, residual connections and group convolution, including stem blocks and extractor modules.The designed stem block uses a series of small convolutions to extract the input image features, and the extractor network adopts the designed two-way dense connection module, which further reduces the network operation complexity. Mounting LiraNet on the object detection framework Darknet, this paper proposes Lira-you only look once(Lira-YOLO), a lightweight model for ship detection in radar images, which can easily be deployed on the mobile devices. Lira-YOLO's prediction module uses a two-layer YOLO prediction layer and adds a residual module for better feature delivery. At the same time, in order to fully verify the performance of the model, mini-RD, a lightweight distance Doppler domain radar images dataset, is constructed. Experiments show that the network complexity of Lira-YOLO is low, being only 2.980 Bflops, and the parameter quantity is smaller, which is only 4.3 MB. The mean average precision(mAP) indicators on the mini-RD and SAR ship detection dataset(SSDD) reach 83.21% and 85.46%, respectively,which is comparable to the tiny-YOLOv3. Lira-YOLO has achieved a good detection accuracy with less memory and computational cost.
文摘针对YOLO(you only look once)v5算法在应用于光学遥感图像舰船目标检测任务时所面临的小目标误检率、漏检率较高的情况,提出一种基于YOLOv5改进的光学遥感图像舰船目标检测方法。首先对路径聚合网络结构进行改进,设计语义信息增强模块提取更富语义信息的浅层特征,增强对小目标特征的表达能力;然后使用Swish函数作为激活函数,提高网络对数据非线性特征的表征能力,加快模型的收敛速度;最后针对舰船目标的尺寸特点优化检测端结构,移除大目标检测头以减少推理计算量。测试集上的实验表明,该方法相较改进前将检测精度提高了5.2%且推理时间有所减少,在保证检测实时性的同时增强了模型的小目标辨别能力。
文摘目前乳腺癌已取代肺癌成为年发病率最高的癌症,基于深度学习的目标检测技术可对乳腺X线、乳腺超声和乳腺核磁共振等非侵入式成像进行自动病变检测,已成为乳腺癌辅助诊断的首选途径.YOLO(you only look once)系列算法是基于深度学习的目标检测算法,经典YOLO算法在速度和精准度具有优势,被广泛应用于计算机视觉各领域,最新YOLO算法是计算机视觉领域的SOTA(state of the art)模型,如何利用YOLO系列算法提高乳腺癌检测速度和准确率,已经成为研究者关注的焦点之一.基于此,本文介绍经典YOLO系列算法的原理,梳理经典YOLO系列算法在乳腺癌图像检测中的应用现状,并归纳总结现存问题,同时对YOLO系列算法在乳腺癌检测的进一步应用进行展望.