Apple Detection in Complex Scene Using the Improved YOLOv4 Model

Abstract

To enable the apple picking robot to quickly and accurately detect apples under the complex background in orchards, we propose an improved You Only Look Once version 4 (YOLOv4) model and data augmentation methods. Firstly, the crawler technology is utilized to collect pertinent apple images from the Internet for labeling. For the problem of insufficient image data caused by the random occlusion between leaves, in addition to traditional data augmentation techniques, a leaf illustration data augmentation method is proposed in this paper to accomplish data augmentation. Secondly, due to the large size and calculation of the YOLOv4 model, the backbone network Cross Stage Partial Darknet53 (CSPDarknet53) of the YOLOv4 model is replaced by EfficientNet, and convolution layer (Conv2D) is added to the three outputs to further adjust and extract the features, which make the model lighter and reduce the computational complexity. Finally, the apple detection experiment is performed on 2670 expanded samples. The test results show that the EfficientNet-B0-YOLOv4 model proposed in this paper has better detection performance than YOLOv3, YOLOv4, and Faster R-CNN with ResNet, which are state-of-the-art apple detection model. The average values of Recall, Precision, and F1 reach 97.43%, 95.52%, and 96.54% respectively, the average detection time per frame of the model is 0.338 s, which proves that the proposed method can be well applied in the vision system of picking robots in the apple industry.

An improved Yolov3 based on dual path network for cherry tomatoes detection

“…The latest yolo series algorithm is Yolov5. Wu, Ma, Zhao, and Liu (2021) applied yolov4 to apple detection in complex environment. In this article, first, the data set is expanded by using data expansion algorithm.…”

Real Time Pear Fruit Detection and Counting Using YOLOv4 Models and Deep SORT

“…Their system had an AP of 96.28 % and a detection speed of 106 FPS on the high-powered Tesla V100 GPU. Other studies also evaluated the performance of YOLO-based models on detecting other fruits such as apple, lemon, banana and cherry [ 8 , 11 , 12 , 13 , 15 , 16 , 32 ].…”

“…Several studies have utilized YOLO-based models for fruit detection and have demonstrated that YOLO models have a huge potential in accurate real time detection of fruits in an orchard [ 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. However, there were some concerns found among these studies.…”

A Real-Time Vehicle Counting, Speed Estimation, and Classification System Based on Virtual Detection Zone and YOLO

“…e loss function remains the same as the YOLOv4 model, which consists of three parts: classification loss, regression loss, and confidence loss [28]. Classification loss and confidence loss remain the same as the YOLOv3 model, but complete intersection over union (CIoU) is used to replace mean-squared error (MSE) to optimize the regression loss [29].…”