A Semantic Segmentation Method for Road Environment Images Based on Hybrid Convolutional Auto-Encoder

Keyphrases

• Abstract Features 9%
• Autoencoder 36%
• Autonomous Vehicles 9%
• CamVid 9%
• Cityscape 9%
• Convolutional Autoencoder 100%
• Convolutional Layer 18%
• Convolutional Neural Network 9%
• Data Learning 9%
• Deconvolution Layer 9%
• Deep Convolutional Neural Network (deep CNN) 9%
• Deep Learning 9%
• Feature Enhancement 9%
• Feature Extracting 9%
• Image-based 100%
• Network Architecture 9%
• Network Layer 9%
• Network Model 9%
• Network Parameters 9%
• Network Training 9%
• Pooling Layer 27%
• Real-time Performance 18%
• Road Environment 100%
• Segmentation Accuracy 9%
• Segmentation Effect 18%
• Segmentation Feature 9%
• Segmentation-based 9%
• Semantic Features 9%
• Semantic Segmentation 100%
• Simple Network 9%
• Supervised Learning 18%
• Training Time 9%

Computer Science

• Autoencoder 9%
• Autonomous Vehicles 9%
• Convolution Layer 18%
• Convolutional Auto-Encoder 100%
• Convolutional Neural Network 9%
• Deep Convolutional Neural Networks 9%
• Deep Learning Method 9%
• Image Segmentation 100%
• Network Architecture 9%
• Network Layer 9%
• Network Parameter 9%
• Real Time Performance 18%
• segmentation accuracy 9%
• Segmentation Method 100%
• Segmentation Model 9%
• Semantic Feature 9%
• Supervised Learning 18%