Fast-HBNet: Hybrid Branch Network for Fast Lane Detection

Article Engineering, Civil

Ripple-GAN: Lane Line Detection With Ripple Lane Line Detection Network and Wasserstein GAN

Youcheng Zhang et al.

Summary: This paper introduces two network models, RiLLD-Net and Ripple-GAN, for lane line detection in intelligent driving. RiLLD-Net utilizes quick connections and gradient maps for feature learning, while Ripple-GAN integrates various techniques to address challenging scenarios, improving the performance of lane line detection.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

添加到收藏夹

Article Engineering, Civil

SALMNet: A Structure-Aware Lane Marking Detection Network

Xuemiao Xu et al.

Summary: A new deep neural network architecture is proposed in this work to detect lane markings in a complex environment by analyzing their structure information, with two key contributions in network design: a semantic-guided channel attention module and a pyramid deformable convolution module. Experimental results demonstrate that this method outperforms others on three benchmark datasets.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A hierarchical sampling based triplet network for fine-grained image classification

Guiqing He et al.

Summary: The proposed method introduces a layered Triplet loss for fine-grained image classification, utilizing a "coarse to fine" scheme to construct the loss function and an ontology-based sampling method to mine more reasonable hard triplets. Semantic knowledge is employed to assign visually similar classes to the same learning task, improving classification accuracy.

PATTERN RECOGNITION (2021)

添加到收藏夹

Article Engineering, Civil