Lightweight and efficient neural network with SPSA attention for wheat ear detection

Author:

Dong Yan1,Liu Yundong1,Kang Haonan2,Li Chunlei1,Liu Pengcheng3ORCID,Liu Zhoufeng1

Affiliation:

1. School of Electronic and Information Engineering, Zhongyuan University of Technology, ZhengZhou, China

2. Department of Statistics and Data Science, National University of Singapore, Singapore

3. Department of Computer Science, University of York, York, United Kingdom

Abstract

Advancements in deep neural networks have made remarkable leap-forwards in crop detection. However, the detection of wheat ears is an important yet challenging task due to the complex background, dense targets, and overlaps between wheat ears. Currently, many detectors have made significant progress in improving detection accuracy. However, some of them are not able to make a good balance between computational cost and precision to meet the needs of deployment in real world. To address these issues, a lightweight and efficient wheat ear detector with Shuffle Polarized Self-Attention (SPSA) is proposed in this paper. Specifically, we first utilize a lightweight backbone network with asymmetric convolution for effective feature extraction. Next, SPSA attention is given to adaptively select focused positions and produce a more discriminative representation of the features. This strategy introduces polarized self-attention to spatial dimension and channel dimension and adopts Shuffle Units to combine those two types of attention mechanisms effectively. Finally, the TanhExp activation function is adopted to accelerate the inference speed and reduce the training time, and CIOU loss is used as the border regression loss function to enhance the detection ability of occlusion and overlaps between targets. Experimental results on the Global Wheat Head Detection dataset show that our method achieves superior detection performance compared with other state-of-the-art approaches.

Funder

NSFC

Henan Science and Technology Innovation Team

IRTSTHN

ZhongYuan Science and Technology Innovation Leading Talent Program

Interdisciplinary Direction Team in the Zhongyuan University of Technology

Publisher

PeerJ

Subject

General Computer Science

Reference56 articles.

1. Automatic counting of wheat spikes from wheat growth images;Alharbi,2018

2. Yolov4: optimal speed and accuracy of object detection;Bochkovskiy;ArXiv preprint,2020

3. The field wheat count based on the efficientdet algorithm;Cao,2020

4. Xception: deep learning with depthwise separable convolutions;Chollet,2017

5. Statistical methods for texture analysis applied to agronomical images;Cointault,2008

Cited by 17 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3