One-Shot Summary Prototypical Network Toward Accurate Unpaved Road Semantic Segmentation

Wang, Yooseung; Lee, Dong hyuk; Heo, Jiseong; Park, Jihun

doi:10.1109/lsp.2021.3087457

Cited by 6 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the safety and reliability of intelligent vehicles, instance segmentation technology [5] for field-of-vision object detection has been introduced to obtain more accurate determination of shapes and attributes of traffic participants in the driving environment. Instance segmentation is a very challenging task that combines object detection [6][7][8] and semantic segmentation [9,10]. However, some problems currently exist in the segmentation task [11], including feature mapping inconsistencies with the actual read, insufficient feature expression, and poor segmentation performance, especially for small or occluded objects in the actual driving environment [12].…”

Section: Introductionmentioning

confidence: 99%

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

Wan,

Chang,

Zhang

2023

Electronics

View full text Add to dashboard Cite

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.

show abstract