Detecting Citrus in Orchard Environment by Using Improved YOLOv4
Open Access
- 25 November 2020
- journal article
- research article
- Published by Wiley in Scientific Programming
- Vol. 2020, 1-13
Abstract
Real-time detection of fruits in orchard environments is one of crucial techniques for many precision agriculture applications, including yield estimation and automatic harvesting. Due to the complex conditions, such as different growth periods and occlusion among leaves and fruits, detecting fruits in natural environments is a considerable challenge. A rapid citrus recognition method by improving the state-of-the-art You Only Look Once version 4 (YOLOv4) detector is proposed in this paper. Kinect V2 camera was used to collect RGB images of citrus trees. The Canopy algorithm and the K-Means++ algorithm were then used to automatically select the number and size of the prior frames from these RGB images. An improved YOLOv4 network structure was proposed to better detect smaller citrus under complex backgrounds. Finally, the trained network model was used for sparse training, pruning unimportant channels or network layers in the network, and fine-tuning the parameters of the pruned model to restore some of the recognition accuracy. The experimental results show that the improved YOLOv4 detector works well for detecting different growth periods of citrus in a natural environment, with an average increase in accuracy of 3.15% (from 92.89% to 96.04%). This result is superior to the original YOLOv4, YOLOv3, and Faster R-CNN. The average detection time of this model is 0.06 s per frame at 1920 × 1080 resolution. The proposed method is suitable for the rapid detection of the type and location of citrus in natural environments and can be applied to the application of citrus picking and yield evaluation in actual orchards.Keywords
Funding Information
- Shanghai Agriculture Applied Technology Development Program (G2015060402, 61762013, 2018AD19339, 20-A-02-02)
- National Natural Science Foundation of China (G2015060402, 61762013, 2018AD19339, 20-A-02-02)
- Science and Technology Foundation of Guangxi Province (G2015060402, 61762013, 2018AD19339, 20-A-02-02)
- Research Fund of Guangxi Key Lab of Multi-source Information Mining & Security (G2015060402, 61762013, 2018AD19339, 20-A-02-02)
- Guangxi Scholarship Fund of the Guangxi Education Department (G2015060402, 61762013, 2018AD19339, 20-A-02-02)
This publication has 19 references indexed in Scilit:
- Fruit detection in natural environment using partial shape matching and probabilistic Hough transformPrecision Agriculture, 2019
- Deep learning for real-time fruit detection and orchard fruit load estimation: benchmarking of ‘MangoYOLO’Precision Agriculture, 2019
- Apple detection during different growth stages in orchards using the improved YOLO-V3 modelComputers and Electronics in Agriculture, 2019
- Detection of orchard citrus fruits using a monocular machine vision-based method for automatic fruit picking applicationsComputers and Electronics in Agriculture, 2018
- Face detection using deep learning: An improved faster RCNN approachNeurocomputing, 2018
- Multiple camera fruit localization using a particle filterComputers and Electronics in Agriculture, 2017
- Deep Count: Fruit Counting Based on Deep Simulated LearningSensors, 2017
- Sensors and systems for fruit detection and localization: A reviewComputers and Electronics in Agriculture, 2015
- Deep learningNature, 2015
- A Proposal for Automatic Fruit Harvesting by Combining a Low Cost Stereovision Camera and a Robotic ArmSensors, 2014