YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection

Hussain, Muhammad

doi:10.3390/machines11070677

Cited by 118 publications

(42 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YOLO (You Only Look Once) is a one-stage deep learning algorithm widely used for real-time object detection. Since it was first proposed, YOLO has gone through multiple iterations, with YOLOv8 being the newer generation [21] . Compared with the C3 module of YOLOv5, the newly proposed C2f module of YOLOv8 stacks more Bottleneck structures, which makes the features of different scales be better utilized and the overall performance is better.…”

Section: Proposed Methodsmentioning

confidence: 99%

A study on synthetic diamond quality evaluation using an enhanced YOLOv8n-based algorithm named YOLOv8n_adamas

Zhang,

Li,

ren

et al. 2024

Preprint

View full text Add to dashboard Cite

In response to the requirements for synthetic diamond quality evaluation in industrial applications, this study proposes an enhanced algorithm titled YOLOv8n_adamas, derived from an improved variant of the YOLOv8n neural network. To overcome the limitations in feature extraction and recognition of synthetic diamond images using the YOLOv8n model, the backbone architecture was redesigned by referring to ConvNextV2 structure, thereby enhancing the feature extraction capacity of the YOLOv8n backbone. An attention-based dynamic detection head was integrated into the original model, replacing the conventional detection head, leading to an improvement in the model's object detection sensitivity. Experimental results demonstrate that, compared to the baseline YOLOv8n network, the YOLOv8n_adamas algorithm achieves a 3.4% increase in precision, a 3.4% rise in recall, and respective improvements of 2.5% and 1.6% in mean precision at confidence levels of 0.5 and 0.95. Consequently, the accuracy of synthetic diamond quality evaluations has been significantly boosted.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

A study on synthetic diamond quality evaluation using an enhanced YOLOv8n-based algorithm named YOLOv8n_adamas

Zhang,

Li,

ren

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Compared with some of the latest YOLO series algorithms, such as YOLOv7 and YOLOv8, the model size of YOLOv5 is smaller, and it has the advantages of high efficiency and applicability. YOLOv5 is based on PyTorch and has an active GitHub library, further describing the implementation process to enable it to be used by a wider audience [49]. Therefore, we chose YOLOv5 as the basic algorithms to apply to multi object detection tasks in unstructured road scenes.…”

Section: Multitask Model and Network Structurementioning

confidence: 99%

Research on multitask model of object detection and road segmentation in unstructured road scenes

Gao,

Zhao,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

With the rapid development of artificial intelligence and computer vision technology, autonomous driving technology has become a hot area of concern. The driving scenarios of autonomous vehicles can be divided into structured scenarios and unstructured scenarios.Compared with structured scenes, unstructured road scenes lack the constraints of lane lines and traffic rules, and the safety awareness of traffic participants is weaker. Therefore, there are new and higher requirements for the environment perception tasks of autonomous vehicles in unstructured road scenes. The current research rarely integrates the target detection and road segmentation to achieve the simultaneous processing of target detection and road segmentation of autonomous vehicle in unstructured road scenes. Aiming at the above issues, a multitask model for object detection and road segmentation in unstructured road scenes is proposed. Through the sharing and fusion of the object detection model and road segmentation model, multitask model can complete the tasks of multi-object detection and road segmentation in unstructured road scenes while inputting a picture. Firstly, MobileNetV2 is used to replace the backbone network of YOLOv5, and multi-scale feature fusion is used to realize the information exchange layer between different features.Subsequently, a road segmentation model was designed based on the DeepLabV3+ algorithm.Its main feature is that it uses MobileNetV2 as the backbone network and combines the binary classification focus Loss function for network optimization. Then, we fused the object detection algorithm and road segmentation algorithm based on the shared MobileNetV2 network to obtain a multitask model and trained it on both the public dataset and the self-built dataset NJFU. The training results demonstrate that the multitask model significantly enhances the algorithm's execution speed by approximately 10 FPS while maintaining the accuracy of object detection and road segmentation. Finally, we conducted validation of the multitask model on an actual vehicle.

show abstract

“…In light of the preceding analysis, this study presents a straightforward and effective method, namely RSE, for detecting and extracting rail surface images from rail inspection images. Notably, the intricacy of the data in rail inspection images is considerably lower than that of the initial task data in detection models such as the YOLO series [42] or Faster-RCNN [43]. Upon analyzing the original rail inspection image, it becomes evident that the light reflection from the rail surface exhibits a propensity toward specular reflection, while the other areas leans toward diffuse reflection.…”

Section: Rsementioning

confidence: 99%

ISRM: introspective self-supervised reconstruction model for rail surface defect detection and segmentation

Li,

Min,

Yue

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The problems of intrinsic imbalance of the sample and interference from complex backgrounds limit the performance of existing deep learning methods when applied to the detection and segmentation of rail surface defects. To address these issues, an introspective self-supervised reconstruction model (ISRM) is proposed, which only requires normal samples in the training phase and incorporates the concept of self-supervised learning into an introspective autoencoder. The training framework of ISRM first extracts general features using a pretrained Feature Extractor. Subsequently, a Feature Transformer transfers the features to the target domain. Next, a Synthetic Defect Embedder embeds Bessel-Gaussian random defects into the feature space. Finally, the asymmetric autoencoder reconstructs the rail surface features back into image space. The transformation of pretrained features into target-oriented features helps mitigate domain bias. Since defects exhibit higher commonality in the feature space relative to the image space, embedding synthetic defects into the feature space effectively improves training efficiency. Moreover, the adversarial training architecture enhances the clarity of reconstructed images. The impact of core parameters on the model performance is analyzed through ablation experiments. The results from comparative experiments demonstrate that ISRM achieves 98.5% and 97.2% accuracy on defect detection and segmentation tasks, respectively, reducing the error rate by 11.8% and 3.4% compared to the current state-of-the-art model.

show abstract

YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection

Cited by 118 publications

References 69 publications

A study on synthetic diamond quality evaluation using an enhanced YOLOv8n-based algorithm named YOLOv8n_adamas

A study on synthetic diamond quality evaluation using an enhanced YOLOv8n-based algorithm named YOLOv8n_adamas

Research on multitask model of object detection and road segmentation in unstructured road scenes

ISRM: introspective self-supervised reconstruction model for rail surface defect detection and segmentation

Contact Info

Product

Resources

About