Deep convolutional neural networks for image-based Convolvulus sepium detection in sugar beet fields

Gao, Junfeng, French, Andrew, Pound, Michael , He, Yong, Pridmore, Tony and Pieters, Jan (2020) Deep convolutional neural networks for image-based Convolvulus sepium detection in sugar beet fields. Plant Methods, 16 . p. 19. ISSN 1746-4811

Full content URL: https://doi.org/10.1186/s13007-020-00570-z

Documents
Deep convolutional neural networks for image‑based Convolvulus sepium detection in sugar beet fields
Published Open Access Manuscript
[img]
[Download]
[img]
Preview
PDF
plant method publication.pdf - Whole Document
Available under License Creative Commons Attribution 4.0 International.

3MB
Item Type:Article
Item Status:Live Archive

Abstract

Background
Convolvulus sepium (hedge bindweed) detection in sugar beet fields remains a challenging problem due to variation in appearance of plants, illumination changes, foliage occlusions, and different growth stages under field conditions. Current approaches for weed and crop recognition, segmentation and detection rely predominantly on conventional machine-learning techniques that require a large set of hand-crafted features for modelling. These might fail to generalize over different fields and environments.

Results
Here, we present an approach that develops a deep convolutional neural network (CNN) based on the tiny YOLOv3 architecture for C. sepium and sugar beet detection. We generated 2271 synthetic images, before combining these images with 452 field images to train the developed model. YOLO anchor box sizes were calculated from the training dataset using a k-means clustering approach. The resulting model was tested on 100 field images, showing that the combination of synthetic and original field images to train the developed model could improve the mean average precision (mAP) metric from 0.751 to 0.829 compared to using collected field images alone. We also compared the performance of the developed model with the YOLOv3 and Tiny YOLO models. The developed model achieved a better trade-off between accuracy and speed. Specifically, the average precisions (APs@IoU0.5) of C. sepium and sugar beet were 0.761 and 0.897 respectively with 6.48 ms inference time per image (800 × 1200) on a NVIDIA Titan X GPU environment.

Keywords:Precision farming, Synthetic images, Transfer learning, weed detection
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
C Biological Sciences > C910 Applied Biological Sciences
Divisions:College of Science > Lincoln Institute for Agri-Food Technology
ID Code:41223
Deposited On:17 Jul 2020 11:29

Repository Staff Only: item control page