Improvement of Road Instance Segmentation Algorithm Based on the Modified Mask R-CNN

Abstract

Although the Mask region-based convolutional neural network (R-CNN) model possessed a dominant position for complex and variable road scene segmentation, some problems still existed, including insufficient feature expressive ability and low segmentation accuracy. To address these problems, a novel road scene segmentation algorithm based on the modified Mask R-CNN was proposed. The multi-scale backbone network, Res2Net, was utilized to replace the ResNet network, and aimed to improve the feature extraction capability. The soft non-maximum suppression algorithm with attenuation function (soft-NMS) was adopted to improve detection efficiency in the case of a higher overlap rate. The comparison analyses of partition accuracy for various models were performed on the adopted Cityscapes dataset. The results demonstrated that the modified Mask R-CNN effectively increased the segmentation accuracy, especially for small and highly overlapping objects. The adopted Res2Net and soft-NMS can effectively enhance the feature extraction and improve segmentation performance. The average accuracy of the modified Mask R-CNN model reached up to 0.321, and was 0.054 higher than Mask R-CNN. This work provides important guidance to design a more efficient road scene instance segmentation algorithm for further promoting the actual application in automatic driving systems.

Color Face Image Generation with Improved Generative Adversarial Networks

“…The convolutional layers in CNNs employ filters that scan the input image to detect local patterns. Motivated by the advent of CNN networks, there are some variants, including R-CNN, Fast R-CNN, Faster R-CNN [13][14][15][16], and Mask R-CNN [17][18][19]. In addition, recognition performance can be further improved using the Residual Network (ResNet) with deep learning.…”