scholarly journals End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding

2018 ◽  
Author(s):  
Effrosyni Mavroudi ◽  
Divya Bhaskara ◽  
Shahin Sefati ◽  
Haider Ali ◽  
Rene Vidal
Keyword(s):  
Random Field ◽  
Sparse Coding ◽  
Conditional Random Field ◽  
Fine Grained ◽  
Action Segmentation ◽  
End To End

scholarly journals Remote Sensing Image Ship Detection under Complex Sea Conditions Based on Deep Semantic Segmentation

2020 ◽  
Vol 12 (4) ◽  
pp. 625 ◽  
Author(s):  
Yantong Chen ◽  
Yuyang Li ◽  
Junsheng Wang ◽  
Weinan Chen ◽  
Xianzhong Zhang
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Random Field ◽  
Conditional Random Field ◽  
Remote Sensing Image ◽  
Convolution Neural Network ◽  
Remote Sensing Images ◽  
Ship Detection ◽  
Deep Convolution Neural Network ◽  
End To End

Under complex sea conditions, ship detection from remote sensing images is easily affected by sea clutter, thin clouds, and islands, resulting in unreliable detection results. In this paper, an end-to-end convolution neural network method is introduced that combines a deep convolution neural network with a fully connected conditional random field. Based on the Resnet architecture, the remote sensing image is roughly segmented using a deep convolution neural network as the input. Using the Gaussian pairwise potential method and mean field approximation theorem, a conditional random field is established as the output of the recurrent neural network, thus achieving end-to-end connection. We compared the proposed method with other state-of-the-art methods on the dataset established by Google Earth and NWPU-RESISC45. Experiments show that the target detection accuracy of the proposed method and the ability of capturing fine details of images are improved. The mean intersection over union is 83.2% compared with other models, which indicates obvious advantages. The proposed method is fast enough to meet the needs for ship detection in remote sensing images.

scholarly journals An End-to-End Oil-Spill Monitoring Method for Multisensory Satellite Images Based on Deep Semantic Segmentation

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 725 ◽  
Author(s):  
Yantong Chen ◽  
Yuyang Li ◽  
Junsheng Wang
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Random Field ◽  
Oil Spill ◽  
Conditional Random Field ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Mean Field Approximation ◽  
Monitoring Method ◽  
End To End

In remote-sensing images, a detected oil-spill area is usually affected by spot noise and uneven intensity, which leads to poor segmentation of the oil-spill area. This paper introduced a deep semantic segmentation method that combined a deep-convolution neural network with the fully connected conditional random field to form an end-to-end connection. On the basis of Resnet, it first roughly segmented a multisource remote-sensing image as input by the deep convolutional neural network. Then, we used the Gaussian pairwise method and mean-field approximation. The conditional random field was established as the output of the recurrent neural network. The oil-spill area on the sea surface was monitored by the multisource remote-sensing image and was estimated by optical image. We experimentally compared the proposed method with other models on the dataset established by the multisensory satellite image. Results showed that the method improved classification accuracy and captured fine details of the oil-spill area. The mean intersection over the union was 82.1%, and the monitoring effect was obviously improved.

scholarly journals Deep-dense Conditional Random Fields for Object Co-segmentation

2017 ◽  
Author(s):  
Zehuan Yuan ◽  
Tong Lu ◽  
Yirui Wu
Keyword(s):  
Random Field ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Conditional Random Field ◽  
Competitive Performance ◽  
Image Region ◽  
Similarity Metric ◽  
Deep Network ◽  
Object Proposals ◽  
End To End

We address the problem of object co-segmentation in images. Object co-segmentation aims to segment common objects in images and has promising applications in AI agents. We solve it by proposing a co-occurrence map, which measures how likely an image region belongs to an object and also appears in other images. The co-occurrence map of an image is calculated by combining two parts: objectness scores of image regions and similarity evidences from object proposals across images. We introduce a deep-dense conditional random field framework to infer co-occurrence maps. Both similarity metric and objectness measure are learned end-to-end in a single deep network. We evaluate our method on two benchmarks and achieve competitive performance.

scholarly journals Neural Network based Continuous Conditional Random Field for Fine-grained Crime Prediction

2019 ◽  
Author(s):  
Fei Yi ◽  
Zhiwen Yu ◽  
Fuzhen Zhuang ◽  
Bin Guo
Keyword(s):  
Neural Network ◽  
Random Field ◽  
Short Term Memory ◽  
Conditional Random Field ◽  
Linear Mapping ◽  
Fine Grained ◽  
Crime Prediction ◽  
Model Training ◽  
Real World Datasets ◽  
Crime Modeling

Crime prediction has always been a crucial issue for public safety, and recent works have shown the effectiveness of taking spatial correlation, such as region similarity or interaction, for fine-grained crime modeling. In our work, we seek to reveal the relationship across regions for crime prediction using Continuous Conditional Random Field (CCRF). However, conventional CCRF would become impractical when facing a dense graph considering all relationship between regions. To deal with it, in this paper, we propose a Neural Network based CCRF (NN-CCRF) model that formulates CCRF into an end-to-end neural network framework, which could reduce the complexity in model training and improve the overall performance. We integrate CCRF with NN by introducing a Long Short-Term Memory (LSTM) component to learn the non-linear mapping from inputs to outputs of each region, and a modified Stacked Denoising AutoEncoder (SDAE) component for pairwise interactions modeling between regions. Experiments conducted on two different real-world datasets demonstrate the superiority of our proposed model over the state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document