Patent
Image crack segmentation method based on deep convolutional neural network
Yao Jian,Liu Yahui,Zhao Jiao,Xie Renping +3 more
- 05 Sep 2017
19
TL;DR: In this paper, an image crack segmentation method based on a deep convolutional neural network is proposed, which consists of the steps that an original image is inputted to the deep CNN, and a characteristic graph is acquired through convolution, pooling and activation layer characteristic learning; sampling is performed on the characteristic graph so as to obtain the feature graph having the same size with that of the original image; and softmax prediction is performed to obtain a feature graph.
read more
Abstract: The invention discloses an image crack segmentation method based on a deep convolutional neural network. The image crack segmentation method comprises the steps that an original image is inputted to the deep convolutional neural network, and a characteristic graph is acquired through convolution, pooling and activation layer characteristic learning; sampling is performed on the characteristic graph so as to obtain the characteristic graph having the same size with that of the original image; and softmax prediction is performed on the characteristic graph having the same size with that of the original image so that the category of the corresponding position can be acquired, and crack area segmentation can be realized. Multilevel characteristic from the low level to the high level can be learned, high-precision crack area segmentation can be rapidly realized and the method is particularly suitable for bridge structure crack detection.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Rail surface defect detection method based on depth learning network
Hui Zhang,Song Yanan,Li Liu,Hang Zhong,Zhicong Liang +4 more
- 21 Dec 2018
TL;DR: Wang et al. as mentioned in this paper presented a rail surface defect detection method based on the depth learning network, aiming at solving various problems existing in the prior-rail detection methods. But the method is limited to the detection and identification of rail surface defects.
24
Patent
Human image segmentation method and mobile terminal
Xing Chen,Li Qidong,Zhang Wei,Gong Qiutang,Liu Ting +4 more
- 08 May 2018
TL;DR: In this article, a human image segmentation method is presented for human image processing in a mobile terminal. But the method is suitable for being executed in a single mobile terminal, and comprises the following steps of: segmenting a to-be-processed image by utilizing a predetermined segmentation network, wherein the predetermined network comprises an encoding stage and a decoding stage, the encoding stage comprises a first number of pairs of convolution layers and down-sampling layers, which are connected in sequence, and each pair of CNNs and DSSs forms a convolution-down
11
Patent
Method and system for monitoring water gauge water level video based on deep learning algorithm
Zhang Xin,Ding Xiaorong,Meng Kun,Li Gang,Lang Fenling +4 more
- 24 Jul 2018
TL;DR: In this paper, a method and system for monitoring a water gauge water level video based on a deep learning algorithm is presented, which belongs to the technical field of image identification and water level monitoring.
11
Patent
Bridge pavement crack detection and segmentation method based on semantic segmentation
Li Liangfu,Sun Ruiyun +1 more
- 11 Sep 2018
TL;DR: In this article, a bridge pavement crack detection and segmentation method based on semantic segmentation is proposed, and the method comprises the steps: firstly performing artificial segmentation of the samples in a data set, and making labels of training samples; secondly expanding the number of images in the data set by data enhancement; thirdly inputting a prepared training set into an FC-DenseNet 103 network model for training; and finally extracting cracks through a collected crack image of the test set.
6
Patent
Road surface defect detection method based on texture feature extraction
Chen Lili,Ren Junlan,Cao Hao,Si Jibing +3 more
- 20 Apr 2018
TL;DR: In this paper, a road surface defect detection method based on texture feature extraction is proposed, which consists of the following steps that an image having a road-surface defect is acquired and grayscale processing is performed so as to form a road -surface defect grayscales image, the feature values are extracted to form texture feature vectors and the road surface defects are represented by the texture feature vector of the same defect class are equally divided soas to form training set and a test set.
6
References
Patent
Vehicle exterior part image segmentation method based on deep learning
Shi Fang,Zou Jiayun,Wang Biao +2 more
- 12 Oct 2016
TL;DR: In this paper, a vehicle exterior part image segmentation method based on deep learning is proposed, where an original image is segmented and demarcated manually according to the segmentation target in the image, and the segmented labels are obtained; the original image and the segments are input into a deep learning neural network.
29
Patent
Convolutional neural network image super-resolution rebuilding method based on learning rate self adaption
Cao Xue,Yu Jing,Xiao Chuangbai +2 more
- 14 Dec 2016
TL;DR: In this article, a convolutional neural network image super-resolution reconstruction method based on learning rate self-adaptation is proposed. But the method is limited to low-resolution images.
27
Patent
Random convolutional neural network-based high-resolution image scene classification method
Bo Du,Fan Zhang,Liangpei Zhang +2 more
- 21 Dec 2016
TL;DR: In this article, a random convolutional neural network-based high-resolution image scene classification method is proposed, where features are hierarchically learned by using a deep convolution network, and model aggregation learning is carried out by utilizing a gradient upgrading method, so that the problem that a single model easily falls into a local optimal solution is solved and the network generalization capability is improved.
23