Recently, convolutional neural network (CNN) has led to significant improvement in the field of computer vision, especially accuracy and speed semantic segmentation tasks, which greatly improved robot scene perception. In this article, we propose a multilevel feature fusion dilated convolution (Refine-DeepLab). By improving space pyramid pooling structure, multiscale hybrid module, captures ric...

Semantic segmentation is a fundamental technology for autonomous driving. It has high demand inference speed and accuracy. However, good trade-off between accuracy latency yet not present in existing semantic approaches. Due to the limitation of speed, authors cannot increase number network layers without limit design modules like networks real-time. challenging problem how model with performan...

RGB-D semantic segmentation can be advanced with convolutional neural networks due to the availability of Depth data. Although objects cannot easily discriminated by just 2D appearance, local pixel difference and geometric patterns in Depth, they well separated some cases. Considering fixed grid kernel structure, CNNs are limited lack ability capture detailed, fine-grained information thus achi...