Small Object Augmentation of Urban Scenes for Real-Time Semantic Segmentation

Semantic segmentation is a key step in scene understanding for autonomous driving. Although deep learning has significantly improved the segmentation accuracy, current highquality models such as PSPNet and DeepLabV3 are inefficient given their complex architectures and reliance on multi-scale inputs...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - (2020) vom: 18. März
1. Verfasser: Yang, Zhengeng (VerfasserIn)
Weitere Verfasser: Yu, Hongshan, Feng, Mingtao, Sun, Wei, Lin, Xuefei, Sun, Mingui, Mao, Zhi-Hong, Mian, Ajmal
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2020
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:Semantic segmentation is a key step in scene understanding for autonomous driving. Although deep learning has significantly improved the segmentation accuracy, current highquality models such as PSPNet and DeepLabV3 are inefficient given their complex architectures and reliance on multi-scale inputs. Thus, it is difficult to apply them to real-time or practical applications. On the other hand, existing real-time methods cannot yet produce satisfactory results on small objects such as traffic lights, which are imperative to safe autonomous driving. In this paper, we improve the performance of real-time semantic segmentation from two perspectives, methodology and data. Specifically, we propose a real-time segmentation model coined Narrow Deep Network (NDNet) and build a synthetic dataset by inserting additional small objects into the training images. The proposed method achieves 65.7% mean intersection over union (mIoU) on the Cityscapes test set with only 8.4G floatingpoint operations (FLOPs) on 1024×2048 inputs. Furthermore, by re-training the existing PSPNet and DeepLabV3 models on our synthetic dataset, we obtained an average 2% mIoU improvement on small objects
Beschreibung:Date Revised 27.02.2024
published: Print-Electronic
Citation Status Publisher
ISSN:1941-0042
DOI:10.1109/TIP.2020.2976856