BFP Net: Balanced Feature Pyramid Network for Small Apple Detection in Complex Orchard Environment

Abstract

Despite of significant achievements made in the detection of target fruits, small fruit detection remains a great challenge, especially for immature small green fruits with a few pixels. The closeness of color between the fruit skin and the background greatly increases the difficulty of locating small target fruits in the natural orchard environment. In this paper, we propose a balanced feature pyramid network (BFP Net) for small apple detection. This network can balance information mapped to small apples from two perspectives: multiple-scale fruits on the different layers of FPN and a characteristic of a new extended feature from the output of ResNet50 conv1. Specifically, we design a weight-like feature fusion architecture on the lateral connection and top-down structure to alleviate the small-scale information imbalance on the different layers of FPN. Moreover, a new extended layer from ResNet50 conv1 is embedded into the lowest layer of standard FPN, and a decoupled-aggregated module is devised on this new extended layer of FPN to complement spatial location information and relieve the problem of locating small apple. In addition, a feature Kullback-Leibler distillation loss is introduced to transfer favorable knowledge from the teacher model to the student model. Experimental results show that APS of our method reaches 47.0%, 42.2%, and 35.6% on the benchmark of the GreenApple, MinneApple, and Pascal VOC, respectively. Overall, our method is not only slightly better than some state-of-the-art methods but also has a good generalization performance.

FCOS-LSC: A Novel Model for Green Fruit Detection in a Complex Orchard Environment

“…In previous studies, a combination of deep learning techniques and image processing has made significant progress in target fruit recognition tasks [ 42 ]. The 2-stage detection model has high detection accuracy relative to the 1-stage model but involves the design of the anchor frame, and the complexity and computational volume of its model increase along with it.…”

Global Navigation Satellite Systems as State-of-the-Art Solutions in Precision Agriculture: A Review of Studies Indexed in the Web of Science

“…The use of computer vision with RGB cameras in harvesting robots provides several benefits and opens up new opportunities in the field of PA [70]. RGB cameras image the crops, which are subsequently analyzed with computer vision algorithms to extract the color, shape, texture, and other visual characteristics of crops to differentiate between ripe and immature fruits and vegetables [71]. The force/torque sensor allows the robot to detect how much force is needed to harvest the crops without harming them.…”

Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique

“…Fan et al [19] refined the YOLOv4 detection algorithm for apple defect identification, employing channel and layer pruning strategies and an L1paradigm non-extreme value suppression method to prune redundant detection frames, achieving a 93.9% average detection accuracy. Sun et al [20] integrated the Res2Net module into the RetinaNet algorithm, coupling a weighted bi-directional feature pyramid network with a focus-based loss and efficient intersection and concatenation ratio in the joint loss function for apple target detection. Zhang et al [21] implemented GhostNet in the improved YOLOv4 apple target detection task, reconstructing the feature extraction network with a depth-separable convolutional lightweight necking network and detection head, integrating coordinate attention into the feature pyramid, and reconfiguring the feature extraction network.…”