RecepNet: Network with Large Receptive Field for Real-Time Semantic Segmentation and Application for Blue-Green Algae



Yang, Kaiyuan, Wang, Zhonghao, Yang, Zheng, Zheng, Peiyang, Yao, Shanliang, Zhu, Xiaohui ORCID: 0000-0003-1024-5442, Yue, Yong, Wang, Wei, Zhang, Jie and Ma, Jieming
(2022) RecepNet: Network with Large Receptive Field for Real-Time Semantic Segmentation and Application for Blue-Green Algae. REMOTE SENSING, 14 (21). p. 5315.

Access the full-text of this item by clicking on the Open Access link.

Abstract

<jats:p>Most high-performance semantic segmentation networks are based on complicated deep convolutional neural networks, leading to severe latency in real-time detection. However, the state-of-the-art semantic segmentation networks with low complexity are still far from detecting objects accurately. In this paper, we propose a real-time semantic segmentation network, RecepNet, which balances accuracy and inference speed well. Our network adopts a bilateral architecture (including a detail path, a semantic path and a bilateral aggregation module). We devise a lightweight baseline network for the semantic path to gather rich semantic and spatial information. We also propose a detail stage pattern to store optimized high-resolution information after removing redundancy. Meanwhile, the effective feature-extraction structures are designed to reduce computational complexity. RecepNet achieves an accuracy of 78.65% mIoU (mean intersection over union) on the Cityscapes dataset in the multi-scale crop and flip evaluation. Its algorithm complexity is 52.12 GMACs (giga multiply–accumulate operations) and its inference speed on an RTX 3090 GPU is 50.12 fps. Moreover, we successfully applied RecepNet for blue-green algae real-time detection. We made and published a dataset consisting of aerial images of water surface with blue-green algae, on which RecepNet achieved 82.12% mIoU. To the best of our knowledge, our dataset is the world’s first public dataset of blue-green algae for semantic segmentation.</jats:p>

Item Type: Article
Uncontrolled Keywords: blue-green algae detection, deep learning, real time, semantic segmentation
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 03 Mar 2023 09:33
Last Modified: 14 Mar 2024 17:50
DOI: 10.3390/rs14215315
Open Access URL: https://doi.org/10.3390/rs14215315
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3168718