A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5

Deep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2021-08, Vol.13 (16), p.3095
Main Authors: Zhao, Jianqing, Zhang, Xiaohu, Yan, Jiawei, Qiu, Xiaolei, Yao, Xia, Tian, Yongchao, Zhu, Yan, Cao, Weixing
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Boxes
Data processing
Datasets
Deep learning
Error detection
Feature extraction
Laplace transforms
Machine learning
Methods
Neural networks
Object recognition
Occlusion
Phenotypes
Remote sensing
Semantics
Spikes
unmanned aerial vehicle
Unmanned aerial vehicles
Wheat
wheat spike detection
YOLOv5
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only Once)-based method to detect wheat spikes accurately in UAV images and solve spike error detection and miss detection caused by occlusion conditions. The proposed method introduces data cleaning and data augmentation to improve the generalization ability of the detection network. The network is rebuilt by adding a microscale detection layer, setting prior anchor boxes, and adapting the confidence loss function of the detection layer based on the IoU (Intersection over Union). These refinements improve the feature extraction for small-sized wheat spikes and lead to better detection accuracy. With the confidence weights, the detection boxes in multiresolution images are fused to increase the accuracy under occlusion conditions. The result shows that the proposed method is better than the existing object detection algorithms, such as Faster RCNN, Single Shot MultiBox Detector (SSD), RetinaNet, and standard YOLOv5. The average accuracy (AP) of wheat spike detection in UAV images is 94.1%, which is 10.8% higher than the standard YOLOv5. Thus, the proposed method is a practical way to handle the spike detection in complex field scenarios and provide technical references for field-level wheat phenotype monitoring.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs13163095