Open Access

ARTICLE

Improved Convolutional Neural Network for Traffic Scene Segmentation

Fuliang Xu, Yong Luo, Chuanlong Sun, Hong Zhao^*

College of Mechanical and Electrical Engineering, Qingdao University, Qingdao, 266071, China

* Corresponding Author: Hong Zhao. Email:

(This article belongs to the Special Issue: Machine Learning Empowered Distributed Computing: Advance in Architecture, Theory and Practice)

Computer Modeling in Engineering & Sciences 2024, 138(3), 2691-2708. https://doi.org/10.32604/cmes.2023.030940

Received 04 May 2023; Accepted 01 August 2023; Issue published 15 December 2023

Abstract

In actual traffic scenarios, precise recognition of traffic participants, such as vehicles and pedestrians, is crucial for intelligent transportation. This study proposes an improved algorithm built on Mask-RCNN to enhance the ability of autonomous driving systems to recognize traffic participants. The algorithm incorporates long and short-term memory networks and the fused attention module (GSAM, GCT, and Spatial Attention Module) to enhance the algorithm’s capability to process both global and local information. Additionally, to increase the network’s initial operation stability, the original network activation function was replaced with Gaussian error linear unit. Experiments were conducted using the publicly available Cityscapes dataset. Comparing the test results, it was observed that the revised algorithm outperformed the original algorithm in terms of AP₅₀, AP₇₅, and other metrics by 8.7% and 9.6% for target detection and 12.5% and 13.3% for segmentation.

---

Keywords

---