Lightweight Algorithm for Apple Detection Based on an Improved YOLOv5 Model

Sun, Yu; Zhang, Dongwei; Guo, Xindong; Yang, Hua

doi:10.3390/plants12173032

Cited by 6 publications

(7 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ascertain the superior efficiency of the enhanced VEW-YOLOv8n algorithm, derived from YOLOv8n, it was compared with prevailing two-stage and single-stage target detection algorithms. The two-stage category included FasterRCNN, while the singlestage category included lightweight algorithms like YOLOv3-tiny [34], YOLOv5n [35], YOLOv6n [36], and YOLOv8n, along with high-precision, medium-large algorithms such as YOLOv8 m [37], and YOLOv3. Algorithms with larger convolutional kernels, namely YOLOv8n-InceptionNext and SSD target detection algorithms, were also compared.…”

Section: Discussionmentioning

confidence: 99%

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

Han,

Lu,

Dong

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This study addresses the challenges in the non-destructive detection of diseased apples, specifically the high complexity and poor real-time performance of the classification model for detecting diseased fruits in apple grading. Research is conducted on a lightweight model for apple defect recognition, and an improved VEW-YOLOv8n method is proposed. The backbone network incorporates a lightweight, re-parameterization VanillaC2f module, reducing both complexity and the number of parameters, and it employs an extended activation function to enhance the model’s nonlinear expression capability. In the neck network, an Efficient-Neck lightweight structure, developed using the lightweight modules and augmented with a channel shuffling strategy, decreases the computational load while ensuring comprehensive feature information fusion. The model’s robustness and generalization ability are further enhanced by employing the WIoU bounding box loss function, evaluating the quality of anchor frames using outlier metrics, and incorporating a dynamically updated gradient gain assignment strategy. Experimental results indicate that the improved model surpasses the YOLOv8n model, achieving a 2.7% increase in average accuracy, a 24.3% reduction in parameters, a 28.0% decrease in computational volume, and an 8.5% improvement in inference speed. This technology offers a novel, effective method for the non-destructive detection of diseased fruits in apple grading working procedures.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Han,

Lu,

Dong

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Conversely, our study aligns with the trajectory of employing DL techniques for fruit detection and extends it by integrating real-time video stream synchronization and tackling the challenges of environmental adaptability. Lastly, the study by Sun et al [ 37 ] presents a lightweight algorithm for apple detection based on an improved YOLOv5 model that achieves an impressive detection speed of 0.013 s/pic. However, our approach complements this by offering a system that focuses not only on lightweight model architecture that detects fruits relatively rapidly in real-time processing but also achieves a higher detection accuracy (a mAP rate of 86.8% by YOLOv5-v1, compared to 81.7% by Sun et al).…”

Section: Discussionmentioning

confidence: 99%

“…Finally, to evaluate and validate the performance of YOLOv5-v1, it was tested on 200 images from the test set and compared with recent related detection algorithms: (i) Mai et al [ 34 ] employed Faster R-CNN; (ii) Chu et al [ 35 ] adopted Mask R-CNN; (iii) Biffi et al [ 36 ] used ATSS, ResNet50, and FPN; (iv) Sun et al [ 37 ] utilized the modified YOLOv5-CS ( Table 8 ). The evaluation was performed based on the values of mAP and the average recognition speed.…”

Section: Case Studymentioning

confidence: 99%

“…Biffi et al [ 36 ] employed an adaptive training sample selection technique with ResNet50 and FPN, which excelled in dense orchards but showed vulnerability in adverse weather conditions and with varied apple types. Lastly, Sun et al [ 37 ] proposed a lightweight YOLOv5-CS that reduced detection speed by 15.56% (in floating-point operations) and increased average precision to 99.1% for real-time applications. However, the real-world applicability of YOLOv5-CS in diverse orchard conditions and its performance with small or overlapping fruits warrant further exploration.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Integrated System for Fruit Detection Using Multi-UAV Imaging and Deep Learning

Melnychenko,

Scislo,

Savenko

et al. 2024

Sensors

View full text Add to dashboard Cite

In the context of Industry 4.0, one of the most significant challenges is enhancing efficiency in sectors like agriculture by using intelligent sensors and advanced computing. Specifically, the task of fruit detection and counting in orchards represents a complex issue that is crucial for efficient orchard management and harvest preparation. Traditional techniques often fail to provide the timely and precise data necessary for these tasks. With the agricultural sector increasingly relying on technological advancements, the integration of innovative solutions is essential. This study presents a novel approach that combines artificial intelligence (AI), deep learning (DL), and unmanned aerial vehicles (UAVs). The proposed approach demonstrates superior real-time capabilities in fruit detection and counting, utilizing a combination of AI techniques and multi-UAV systems. The core innovation of this approach is its ability to simultaneously capture and synchronize video frames from multiple UAV cameras, converting them into a cohesive data structure and, ultimately, a continuous image. This integration is further enhanced by image quality optimization techniques, ensuring the high-resolution and accurate detection of targeted objects during UAV operations. Its effectiveness is proven by experiments, achieving a high mean average precision rate of 86.8% in fruit detection and counting, which surpasses existing technologies. Additionally, it maintains low average error rates, with a false positive rate at 14.7% and a false negative rate at 18.3%, even under challenging weather conditions like cloudiness. Overall, the practical implications of this multi-UAV imaging and DL-based approach are vast, particularly for real-time fruit recognition in orchards, marking a significant stride forward in the realm of digital agriculture that aligns with the objectives of Industry 4.0.

show abstract

“…Furthermore, because Detectron2 incorporates several widely employed deep learning models for object detection and instance segmentation, it possesses the potential for future compatibility with a broader range of agricultural and industrial production scenarios. These scenarios may include tasks like recognizing plant fructifications and identifying crop pests, extending its applicability beyond the sole measurement of rapeseed pod phenotype omics data [ 62 , 63 , 64 , 65 , 66 ]. By combining machine vision, we also determined the length, width, and two-dimensional image area of the rapeseed pods in the image using a single coin as a reference.…”

Section: Discussionmentioning

confidence: 99%

Segmentation and Phenotype Calculation of Rapeseed Pods Based on YOLO v8 and Mask R-Convolution Neural Networks

Wang,

Liu,

et al. 2023

Plants

View full text Add to dashboard Cite

Rapeseed is a significant oil crop, and the size and length of its pods affect its productivity. However, manually counting the number of rapeseed pods and measuring the length, width, and area of the pod takes time and effort, especially when there are hundreds of rapeseed resources to be assessed. This work created two state-of-the-art deep learning-based methods to identify rapeseed pods and related pod attributes, which are then implemented in rapeseed pots to improve the accuracy of the rapeseed yield estimate. One of these methods is YOLO v8, and the other is the two-stage model Mask R-CNN based on the framework Detectron2. The YOLO v8n model and the Mask R-CNN model with a Resnet101 backbone in Detectron2 both achieve precision rates exceeding 90%. The recognition results demonstrated that both models perform well when graphic images of rapeseed pods are segmented. In light of this, we developed a coin-based approach for estimating the size of rapeseed pods and tested it on a test dataset made up of nine different species of Brassica napus and one of Brassica campestris L. The correlation coefficients between manual measurement and machine vision measurement of length and width were calculated using statistical methods. The length regression coefficient of both methods was 0.991, and the width regression coefficient was 0.989. In conclusion, for the first time, we utilized deep learning techniques to identify the characteristics of rapeseed pods while concurrently establishing a dataset for rapeseed pods. Our suggested approaches were successful in segmenting and counting rapeseed pods precisely. Our approach offers breeders an effective strategy for digitally analyzing phenotypes and automating the identification and screening process, not only in rapeseed germplasm resources but also in leguminous plants, like soybeans that possess pods.

show abstract

Lightweight Algorithm for Apple Detection Based on an Improved YOLOv5 Model

Cited by 6 publications

References 39 publications

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

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

Intelligent Integrated System for Fruit Detection Using Multi-UAV Imaging and Deep Learning

Segmentation and Phenotype Calculation of Rapeseed Pods Based on YOLO v8 and Mask R-Convolution Neural Networks

Contact Info

Product

Resources

About