A DETR-like detector-based semi-supervised object detection method for Brassica Chinensis growth monitoring

芸苔属 探测器 计算机科学 人工智能 对象(语法) 目标检测 计算机视觉 模式识别(心理学) 遥感 数据挖掘 生物 地理 农学 电信
作者
Haoyan Li,Fanhuai Shi
出处
期刊:Computers and Electronics in Agriculture [Elsevier]
卷期号:219: 108788-108788
标识
DOI:10.1016/j.compag.2024.108788
摘要

Object detection technology plays a crucial role in crop growth monitoring within smart agriculture. However, data labeling is a costly process necessary for constructing a large-scale dataset, which is essential to prevent overfitting in deep learning-based object detection models. Semi-Supervised Object Detection (SSOD) presents a cost-effective solution to reduce labeling and model training expenses; nevertheless, existing SSOD algorithms fall short in addressing the specific challenges posed by detection tasks in Brassica Chinensis growth monitoring. Specifically, the two-stage object detector cannot be well-suited for scenes characterized by severe occlusion and complex backgrounds. The Non-Maximum Suppression (NMS) may filter out numerous true positives in scenarios with severe occlusion. Moreover, the label assignment enlarges the negative effects of the noise introduced by teacher model's prediction, resulting in potential divergence. To tackle these challenges, we propose an end-to-end SSOD method based on Detection Transformer (DETR), which streamlines the post-processing without NMS and adopts a more advanced bipartite matching assignment strategy. These modifications tailor the semi-supervised training method to better align with the unique characteristics of detection tasks in Brassica Chinensis growth monitoring. Furthermore, two key techniques: low threshold filtering and decoupled optimization, are introduced to address class-imbalance and multi-task optimization conflict in the tasks, respectively. In the end, we conduct experiments using two self-constructed Brassica Chinensis image datasets to validate the effectiveness of the proposed method, which demonstrates state-of-the-art (SOTA) performance in both tasks. For plant detection, the proposed method achieves an mAP of 74.1 using only 5 % of the total data volume (18 images). In the wormhole detection task, the method achieves an AP50 of 73.7 using 5 % of the total data volume (73 images). These impressive results meet the requirements for practical applications in Brassica Chinensis growth monitoring.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
今后应助帮我消消黑眼圈采纳,获得30
刚刚
高山仰止发布了新的文献求助10
1秒前
1秒前
小宋同学不能怂完成签到 ,获得积分10
1秒前
AM应助朴实老虎采纳,获得10
1秒前
1秒前
WWW完成签到,获得积分10
3秒前
子车茗应助amg采纳,获得20
4秒前
守心完成签到,获得积分10
4秒前
博士加油发布了新的文献求助10
4秒前
4秒前
Yee完成签到 ,获得积分10
4秒前
梓歆完成签到 ,获得积分10
4秒前
Tim完成签到,获得积分10
5秒前
FOR完成签到,获得积分10
5秒前
ll完成签到,获得积分10
6秒前
rrjl发布了新的文献求助10
6秒前
小小果妈完成签到 ,获得积分10
6秒前
huahua完成签到 ,获得积分10
7秒前
真的不会完成签到,获得积分10
8秒前
发光诱饵完成签到,获得积分10
8秒前
圆圆完成签到,获得积分10
9秒前
陈预立完成签到,获得积分10
9秒前
单薄含巧完成签到,获得积分10
9秒前
deniroming完成签到,获得积分10
10秒前
奋斗初南完成签到,获得积分10
10秒前
鲤鱼寄容完成签到 ,获得积分10
11秒前
11秒前
yesdanny发布了新的文献求助30
11秒前
cassiel完成签到,获得积分10
11秒前
Anx1ous完成签到,获得积分10
12秒前
坚定的雁完成签到 ,获得积分10
12秒前
14秒前
大个应助学术菜鸟采纳,获得10
14秒前
奈何桥尾完成签到,获得积分10
14秒前
14秒前
博士加油完成签到,获得积分10
14秒前
DMMM完成签到,获得积分10
15秒前
可爱的函函应助20230321采纳,获得30
16秒前
今后应助20230321采纳,获得30
16秒前
高分求助中
The late Devonian Standard Conodont Zonation 2000
Nickel superalloy market size, share, growth, trends, and forecast 2023-2030 2000
The Lali Section: An Excellent Reference Section for Upper - Devonian in South China 1500
Very-high-order BVD Schemes Using β-variable THINC Method 870
Mantiden: Faszinierende Lauerjäger Faszinierende Lauerjäger 800
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 800
Fundamentals of Dispersed Multiphase Flows 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3253464
求助须知:如何正确求助?哪些是违规求助? 2896017
关于积分的说明 8289700
捐赠科研通 2564792
什么是DOI,文献DOI怎么找? 1392561
科研通“疑难数据库(出版商)”最低求助积分说明 652230
邀请新用户注册赠送积分活动 629544