Deep Context Convolutional Neural Networks for Semantic Segmentation

Yang, Wenbin; Zhou, Quan; Yi, Fan; Gao, Guangwei; Wu, Songsong; Ou, Weihua; Lu, Huimin; Cheng, Jie; Latecki, Longin Jan

doi:10.1007/978-981-10-7299-4_58

Cited by 15 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternative solutions to improve the performance of segmentation models are based on fusing feature maps at different levels of abstraction [27,28] and fusing global context information [29,30]. However, these methods need to add complexity to the semantic segmentation model.…”

Section: Semantic Segmentationmentioning

confidence: 99%

A novel vSLAM framework with unsupervised semantic segmentation based on adversarial transfer learning

Jin

Chen

Sun

et al. 2020

Applied Soft Computing

View full text Add to dashboard Cite

Significant progress has been made in the field of visual Simultaneous Localization and Mapping (vSLAM) systems. However, the localization accuracy of vSLAM can be significantly reduced in dynamic applications with mobile robots or passengers. In this paper, a novel semantic SLAM framework in dynamic environments is proposed to improve the localization accuracy. We incorporate a semantic segmentation model into the Oriented FAST and Rotated BRIEF-SLAM2 (ORB-SLAM2) system to filter out dynamic feature points, but we encounter one main challenge, i.e. the performance of a segmentation network well-trained with labeled datasets may decrease seriously in a real application without any labeled data due to the inconsistency between the source domain and the target domain. Therefore, we proposed an unsupervised semantic segmentation model with a Residual Neural Network (ResNet) structure, which is trained by the adversarial transfer learning method in the multi-level feature spaces. This work may be the first to perform multi-level feature space adversarial transfer learning for the semantic SLAM task in dynamic environments. In order to evaluate our method, images of indoor scenes from three datasets are used as the source domain, and the dynamic sequences of the TUM dataset are used as the target domain. The extensive experimental results show favorable performance against the state-of-the-art methods in terms of the absolute trajectory accuracy and image semantic segmentation quality.

show abstract

Section: Semantic Segmentationmentioning

confidence: 99%

A novel vSLAM framework with unsupervised semantic segmentation based on adversarial transfer learning

Jin

Chen

Sun

et al. 2020

Applied Soft Computing

View full text Add to dashboard Cite

show abstract

“…The goal of image segmentation is to find meaningful objects from an image. Among all the image segmentation algorithms, a thresholding segmentation algorithm is one of the efficiency algorithms 21–30 …”

Section: Algorithm Performance Analysismentioning

confidence: 99%

An improved artificial bee colony algorithm based on elite search strategy with segmentation application on robot vision system

Rong

Yang

Gao

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Summary Aiming at accelerating the convergence speed and enhancing relative poor local search ability of the traditional artificial bee colony algorithm (ABC), this article introduces an ABC with a new elite search strategy. First, we propose a strategy of recording individuals with high performance. Then bees have more chances to learn from a real elite. In the onlooked bee phase, its updating equation is changed for having more opportunities to search in a valuable area. Furthermore, for saving the value of function evaluations, a new learning equation for the best onlooked bee is proposed. The image segmentation of a robot binocular stereo vision system is a key problem in mechanical robot vision system, but the computation time limits its application. The experimental results show that the proposed algorithm achieves better performance on 10 benchmark functions and the image segmentation problem of mechanical robot in comparison with several other state of the art algorithms.

show abstract

“…erefore, we reference the advantage of residual properties to build a new block, which is based on the depth separable convolution layer. Furthermore, Zhou et al [36] and Yang et al [37] connected multilayer feature information by skip connections that are of great help for the final results. erefore, we use skip connections in our neural network architecture.…”

Section: Related Workmentioning

confidence: 99%

Traffic Scene Depth Analysis Based on Depthwise Separable Convolutional Neural Network

Yuan

Zhou

et al. 2019

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

In order to obtain the distances between the surrounding objects and the vehicle in the traffic scene in front of the vehicle, a monocular visual depth estimation method based on the depthwise separable convolutional neural network is proposed in this study. First, features containing shallow depth information were extracted from the RGB images using the convolution layers and maximum pooling layers. Subsampling operations were also performed on these images. Subsequently, features containing advanced depth information were extracted using a block based on an ensemble of convolution layers and a block based on depth separable convolution layers. e output from all different blocks is combined afterwards. Finally, transposed convolution layers were used for upsampling the feature maps to the same size with the original RGB image. During the upsampling process, skip connections were used to merge the features containing shallow depth information that was obtained from the convolution operation through the depthwise separable convolution layers. e depthwise separable convolution layers can provide more accurate depth information features for estimating the monocular visual depth. At the same time, they require reduced computational cost and fewer parameter numbers while providing a similar level (or slightly better) computing performance. Integrating multiple simple convolutions into a block not only increases the overall depth of the neural network but also enables a more accurate extraction of the advanced features in the neural network. Combining the output from multiple blocks can prevent the loss of features containing important depth information. e testing results show that the depthwise separable convolutional neural network provides a superior performance than the other monocular visual depth estimation methods. erefore, applying depthwise separable convolution layers in the neural network is a more effective and accurate approach for estimating the visual depth.

show abstract

Deep Context Convolutional Neural Networks for Semantic Segmentation

Cited by 15 publications

References 22 publications

A novel vSLAM framework with unsupervised semantic segmentation based on adversarial transfer learning

A novel vSLAM framework with unsupervised semantic segmentation based on adversarial transfer learning

An improved artificial bee colony algorithm based on elite search strategy with segmentation application on robot vision system

Traffic Scene Depth Analysis Based on Depthwise Separable Convolutional Neural Network

Contact Info

Product

Resources

About