Comparison of object detection and patch-based classification deep learning models on mid-to late-season weed detection in UAV imagery

Arun Narenthiran Veeranampalayam Sivakumar, Jiating Li, Stephen Scott, Eric Psota, Amit J. Jhala, Joe D. Luck, Yeyin Shi

Research output: Contribution to journalArticlepeer-review

59 Scopus citations

Abstract

Mid-to late-season weeds that escape from the routine early-season weed management threaten agricultural production by creating a large number of seeds for several future growing seasons. Rapid and accurate detection of weed patches in field is the first step of site-specific weed management. In this study, object detection-based convolutional neural network models were trained and evaluated over low-altitude unmanned aerial vehicle (UAV) imagery for mid-to lateseason weed detection in soybean fields. The performance of two object detection models, Faster RCNN and the Single Shot Detector (SSD), were evaluated and compared in terms of weed detection performance using mean Intersection over Union (IoU) and inference speed. It was found that the Faster RCNN model with 200 box proposals had similar good weed detection performance to the SSD model in terms of precision, recall, f1 score, and IoU, as well as a similar inference time. The precision, recall, f1 score and IoU were 0.65, 0.68, 0.66 and 0.85 for Faster RCNN with 200 proposals, and 0.66, 0.68, 0.67 and 0.84 for SSD, respectively. However, the optimal confidence threshold of the SSD model was found to be much lower than that of the Faster RCNN model, which indicated that SSD might have lower generalization performance than Faster RCNN for mid-to late-season weed detection in soybean fields using UAV imagery. The performance of the object detection model was also compared with patch-based CNN model. The Faster RCNN model yielded a better weed detection performance than the patch-based CNN with and without overlap. The inference time of Faster RCNN was similar to patch-based CNN without overlap, but significantly less than patchbased CNN with overlap. Hence, Faster RCNN was found to be the best model in terms of weed detection performance and inference time among the different models compared in this study. This work is important in understanding the potential and identifying the algorithms for an on-farm, near real-time weed detection and management.

Original languageEnglish (US)
Article number2136
JournalRemote Sensing
Volume12
Issue number13
DOIs
StatePublished - Jul 1 2020

Keywords

  • CNN
  • Detection performance
  • Faster RCNN
  • Inception v2
  • Inference time
  • MobileNet v2
  • Patch-based CNN
  • SSD

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)

Fingerprint

Dive into the research topics of 'Comparison of object detection and patch-based classification deep learning models on mid-to late-season weed detection in UAV imagery'. Together they form a unique fingerprint.

Cite this