Novel green-fruit detection algorithm based on D2D framework

Abstract

In the complex orchard environment, the efficient and accurate detection of object fruit is the basic requirement to realize the orchard yield measurement and automatic harvesting. Sometimes it is hard to differentiate between the object fruits and the background because of the similar color, and it is challenging due to the ambient light and camera angle by which the photos have been taken. These problems make it hard to detect green fruits in orchard environments. In this study, a two-stage dense to detection framework (D2D) was proposed to detect green fruits in orchard environments. The proposed model was based on multi-scale feature extraction of target fruit by using feature pyramid networks MobileNetV2 +FPN structure and generated region proposal of target fruit by using Region Proposal Network (RPN) structure. In the regression branch, the offset of each local feature was calculated, and the positive and negative samples of the region proposals were predicted by a binary mask prediction to reduce the interference of the background to the prediction box. In the classification branch, features were extracted from each sub-region of the region proposal, and features with distinguishing information were obtained through adaptive weighted pooling to achieve accurate classification. The new proposed model adopted an anchor-free frame design, which improves the generalization ability, makes the model more robust, and reduces the storage requirements. The experimental results of persimmon and green apple datasets show that the new model has the best detection performance, which can provide theoretical reference for other green object detection.

Immature Green Apple Detection and Sizing in Commercial Orchards Using YOLOv8 and Shape Fitting Techniques

“…Recently Wei et. al [22] developed a green fruit detection system in an orchard environment which was based on multi-scale feature extraction of target fruit by using Feature Pyramid Networks (FPN) MobileNetV2 and generated region proposal of the target fruit by using Region Proposal Network (RPN). Likewise, Gan et.…”

YOLOv5-LiNet: A lightweight network for fruits instance segmentation

“…Meanwhile, the actualization of lightweight network depends on the application of comparative simpler network structure such as MobileNet (MobileNetv1 [ 21 ]; MobileNetv2 [ 22 ]; MobileNetv3 [ 15 ]), SqueezeNet (SqueezeNet [ 23 ]; SqueezeNext [ 24 ]), ShuffleNet (ShuffleNetv1 [ 25 ]; ShuffleNetv2 [ 26 ]), and YOLO-tiny (YOLOv3-tiny [ 27 ]; YOLOv4-tiny [ 28 ]; YOLOv5n [ 20 ]) and so on. For the computer vision system aiming at accurate location and segmentation has a vital role for various agricultural applications [ 29 , 30 ].…”

TomatoDet: Anchor-free detector for tomato detection

“…Tested on three types of edge devices, the average detection precision reaches 93, 84.7, and 85% for oranges, tomatoes, and apples, respectively. Wei et al (2022) proposed a green fruit detection model based on D2Det. By incorporating MobileNetV2, feature pyramid networks and region proposal network structure into the original model, the detection accuracy of green fruits in orchard environments was greatly improved.…”