共查询到16条相似文献,搜索用时 62 毫秒
1.
目的 达到纸病检测中能够充分提取纸病特征、提高检测精度、降低小目标漏检率的目标。方法 基于Faster R-CNN的检测算法进行改进,主要改进的做法是利用深度残差网络ResNet-50替换原模型的骨干特征提取网络VGG16,以保留更多的纸病特征信息,增强特征网络对纸张缺陷的提取能力;在算法中添加空间和通道的双重注意力机制CBAM,用来提高纸病检测精度;将ROI-Pooling替换为ROI-Align,增强网络的泛化能力。结果 实验结果表明,改进后的算法平均精度达到98%,较原算法平均精度提升了9%。结论 改进后的算法能够充分提取纸病特征信息,有效提高了纸病的检测精度,以及提高了小目标纸病的检测率,降低了错漏检率。 相似文献
2.
3.
4.
基于Faster R-CNN改进的数粒机系统 总被引:1,自引:1,他引:0
目的解决目前数粒机只能计数不能同时分拣残损药粒的问题。方法设计以Faster R-CNN深度神经网络为核心的药粒数粒机系统。在原有的数粒机基础之上,更换CCD线阵相机为面阵相机,以满足图像采集的需求,进一步使用图像分割和多线程技术加快图像处理速度。最终通过训练好的Faster R-CNN网络检测出目标并分拣。结果经过测试集的验证,正常药粒识别率达到了95.47%,残损药粒识别率达到了97.94%,单幅图像处理达到了65 ms的实时速度。结论该方法在传统的计数基础上很好地融合了先进的深度学习技术,实现了目标的自动分拣。 相似文献
5.
6.
根据目标检测算法中出现的目标漏检和重复检测问题,本文提出了一种基于双阈值-非极大值抑制的Faster R-CNN改进算法。算法首先利用深层卷积网络架构提取目标的多层卷积特征,然后通过提出的双阈值-非极大值抑制(DT-NMS)算法在RPN阶段提取目标候选区域的深层信息,最后使用了双线性插值方法来改进原RoI pooling层中的最近邻插值法,使算法在检测数据集上对目标的定位更加准确。实验结果表明,DT-NMS算法既有效地平衡了单阈值算法对目标漏检问题和目标误检问题的关系,又针对性地减小了同一目标被多次检测的概率。与soft-NMS算法相比,本文算法在PASCAL VOC2007上的重复检测率降低了2.4%,多次检测的目标错分率降低了2%。与Faster R-CNN算法相比,本文算法在PASCAL VOC2007上检测精度达到74.7%,性能提升了1.5%。在MSCOCO数据集上性能提升了1.4%。同时本文算法具有较快的检测速度,达到16 FPS。 相似文献
7.
《中国计量学院学报》2020,(2):240-246
目的:为了解决传统目标检测方法在应对极端长宽比和小目标检测时存在的准确率低的问题,设计了一种改进Faster RCNN的铝型材表面缺陷检测方法。方法:在Faster RCNN的基础上,以残差网络替换原始VGG16网络提取图像特征,采用特征金字塔网络提取并融合多尺度的特征图,合成低级和高级语义信息。结果:在4 000张图片测试集的基础上,检测准确率达到78.9%,召回率为85.6%,均衡平均数为82.1%,相比于原始Faster RCNN模型,分别提高了16.2%、17%、16.6%。结论:相对于原始Faster RCNN模型,本文采用的改进算法在缺陷检测上有更好的效果,从而为计算机辅助小目标缺陷检测做了可行性论证。 相似文献
8.
9.
10.
针对人工进行轮毂分拣存在的误识别问题,采用一种基于ResNet50与迁移学习的神经网络模型来识别汽车轮毂。把预训练模型参数迁移到ResNet50卷积神经网络中,修改原网络的输出层,构建基于ResNet50的迁移学习模型,通过进一步训练轮毂数据集来微调模型参数,提取轮毂的细粒度特征。通过对比AlexNet、VGG11、VGG16与ResNet50模型在未使用微调、使用微调和冻结不同数量卷积层参数时的训练效率、准确率,证明ResNet50迁移学模型在冻结前7个Bottleneck残差块参数时不仅能缩短训练时间,并能在相同迭代周期下取得更高的准确率。在该冻结策略下训练生成TL-ResNet50迁移学习模型,分别对8种轮毂进行预测,得出每种轮毂的平均准确率达到99%以上。 相似文献
11.
The aim of information hiding is to embed the secret message in a normal cover media such as image, video, voice or text, and then the secret message is transmitted through the transmission of the cover media. The secret message should not be damaged on the process of the cover media. In order to ensure the invisibility of secret message, complex texture objects should be chosen for embedding information. In this paper, an approach which corresponds multiple steganographic algorithms to complex texture objects was presented for hiding secret message. Firstly, complex texture regions are selected based on a kind of objects detection algorithm. Secondly, three different steganographic methods were used to hide secret message into the selected block region. Experimental results show that the approach enhances the security and robustness. 相似文献
12.
13.
目的 针对施工环境中工程机械目标大小不一、相互遮挡、工作形态各异等问题,提出一种基于注意力与特征融合的目标检测方法(AT–FFRCNN)。方法 在主干网络中采用ResNet50和特征路径聚合网络PFPN,融合不同尺度的特征信息,在区域建议网络(RPN)和全连接层引入注意力机制,提高目标识别的能力,在损失函数中使用广义交并比(GIoU),提高目标框的准确性。结果 实验表明,文中提出方法检测准确率比其他方法有较大提高,检测平均准确率(mAP)达到90%以上。结论 能够较好地完成工程机械目标的检测任务。 相似文献
14.
Edge detection is one of the core steps of image processing and computer vision. Accurate and fine image edge will make further target detection and semantic segmentation more effective. Holistically-Nested edge detection (HED) edge detection network has been proved to be a deep-learning network with better performance for edge detection. However, it is found that when the HED network is used in overlapping complex multi-edge scenarios for automatic object identification. There will be detected edge incomplete, not smooth and other problems. To solve these problems, an image edge detection algorithm based on improved HED and feature fusion is proposed. On the one hand, features are extracted using the improved HED network: the HED convolution layer is improved. The residual variable convolution block is used to replace the normal convolution enhancement model to extract features from edges of different sizes and shapes. Meanwhile, the empty convolution is used to replace the original pooling layer to expand the receptive field and retain more global information to obtain comprehensive feature information. On the other hand, edges are extracted using Otsu algorithm: Otsu-Canny algorithm is used to adaptively adjust the threshold value in the global scene to achieve the edge detection under the optimal threshold value. Finally, the edge extracted by improved HED network and Otsu-Canny algorithm is fused to obtain the final edge. Experimental results show that on the Berkeley University Data Set (BSDS500) the optimal data set size (ODS) F-measure of the proposed algorithm is 0.793; the average precision (AP) of the algorithm is 0.849; detection speed can reach more than 25 frames per second (FPS), which confirms the effectiveness of the proposed method. 相似文献
15.
Automatic road damage detection using image processing is an important aspect
of road maintenance. It is also a challenging problem due to the inhomogeneity of road
damage and complicated background in the road images. In recent years, deep
convolutional neural network based methods have been used to address the challenges of
road damage detection and classification. In this paper, we propose a new approach to
address those challenges. This approach uses densely connected convolution networks as
the backbone of the Mask R-CNN to effectively extract image feature, a feature pyramid
network for combining multiple scales features, a region proposal network to generate the
road damage region, and a fully convolutional neural network to classify the road damage
region and refine the region bounding box. This method can not only detect and classify the
road damage, but also create a mask of the road damage. Experimental results show that the
proposed approach can achieve better results compared with other existing methods. 相似文献
16.
干滩长度是整个尾矿坝安全稳定性的一个重要参数。为了实时准确地测得干滩长度值,提出了一种高效、智能、准确的在线监测新方法--基于Mask R-CNN实例分割算法的干滩长度测量方法。此方法共分为4部分:(1) 在尾矿坝两岸安装监控摄像头;(2) 基于Mask R-CNN算法,训练出识别水线并输出水线坐标的网络模型;(3) 将水线轮廓坐标与实际干滩长度进行回归分析,拟合出测量算法关系式;(4)将水线坐标输入上述关系式,即可通过视频画面实时测得干滩长度。研究结果表明,此模型能够准确地进行干滩长度的测量,且适用于光照不足、图像模糊、雨雪天气等情况。 相似文献