Figure 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Improved bubble defect detection algorithm. It includes four parts: Backbone, Tyre-Feature Pyramid Network, Region proposal, and Region prediction.
Source publication
With the development of neural networks, object detection based on deep learning is developing rapidly, and its applications are gradually increasing. In the tire industry, detecting speckle interference bubble defects of tire crown has difficulties such as low image contrast, small object scale, and large internal differences of defects, which aff...
Context in source publication
Similar publications
A simple and interpretable way to learn a dynamical system from data is to interpolate its vector-field with a kernel. In particular, this strategy is highly efficient (both in terms of accuracy and complexity) when the kernel is data-adapted using Kernel Flows (KF) [34] (which uses gradient-based optimization to learn a kernel based on the premise...
Citations
... The authors of [17] proposed a Faster RCNN network based on the feature pyramid network to detect tire bubble defects. Their model contains four parts: the backbone, Tire Feature Pyramid Network, region proposal, and region prediction. ...
Automatic detection of tire defects has become an important issue for tire production companies since these defects cause road accidents and loss of human lives. Defects in the inner structure of the tire cannot be detected with the naked eye; thus, a radiographic image of the tire is gathered using X-ray cameras. This image is then examined by a quality control operator, and a decision is made on whether it is a defective tire or not. Among all defect types, the foreign object type is the most common and may occur anywhere in the tire. This study proposes an explainable deep learning model based on Xception and Grad-CAM approaches. This model was fine-tuned and trained on a novel real tire dataset consisting of 2303 defective tires and 49,198 non-defective. The defective tire class was augmented using a custom augmentation technique to solve the imbalance problem of the dataset. Experimental results show that the proposed model detects foreign objects with an accuracy of 99.19%, recall of 98.75%, precision of 99.34%, and f-score of 99.05%. This study provided a clear advantage over similar literature studies.
... The authors of [17] proposed a Faster RCNN network based on the feature pyramid network to detect tire bubble defects. Their model contains four parts: the backbone, Tire Feature Pyramid Network, region proposal, and region prediction. ...
Automatic detection of tire defects has become an important issue for tire production companies since these defects cause road accidents and loss of human lives. Defects in the inner structure of the tire cannot be detected with the naked eye; thus, a radiographic image of the tire is gathered using X-ray cameras. This image is then examined by a quality control operator, and a decision is made on whether it is a defective tire or not. Among all defect types, the foreign object type is the most common and may occur anywhere in the tire. This study proposes an explainable deep learning model based on Xception and Grad-CAM approaches. This model was fine-tuned and trained on a novel real tire dataset consisting of 2303 defective tires and 49,198 non-defective. The defective tire class was augmented using a custom augmentation technique to solve the imbalance problem of the dataset. Experimental results show that the proposed model detects foreign objects with an accuracy of 99.19%, recall of 98.75%, precision of 99.34%, and f-score of 99.05%. This study provided a clear advantage over similar literature studies.
... Owing to their smaller receptive fields, shallow feature maps within a network tend to gather more detailed and specific information. Consequently, shallower layers of the network contain finer details and intricate information [21]. Utilizing the shallow-layer information of a neural network is a popular method for recognizing small targets. ...
Birds pose a serious threat to the safe operation of aircrafts. Existing object detection methods have achieved good results for big and medium instances; however, for small flying bird instances, drawbacks such as slow speed, low accuracy, and large model size are still present. Therefore, to overcome these shortcomings, we propose the SMB-YOLOv5 model to detect birds near airports. First, we introduce a self-supervised predictive convolution attention block to enable YOLOv5s6 to focus on critical information, thereby enhancing detection performance. Second, we introduce a multi-branch block (MBB) that enhances the expressive capability of the network by incorporating branches with different receptive fields. Third, to enhance the feature fusion capability of the model and detection mAP@50 for small-bird instances, drawing inspiration from the bidirectional feature pyramid network, we reutilize the shallow-level features of the feature extraction network. We also remove some modules to ensure an increased accuracy without excessively inflating the model size. Finally, to increase the convergence speed of the network, we modify its loss function by replacing complete IoU (CIoU) with efficient IoU (EIoU), which improves the detection mAP@50 of the network. Compared to the YOLOv5s6 model, the proposed SMB-YOLOv5 model achieves a 2.6% increase in mAP@50 on the test dataset. The detection speed has reached 24 fps. We find that the SMB-YOLOv5 has a higher mAP@50 than the other algorithms in the test dataset and the lowest number of parameters, and it can be applied in airport bird detection systems to provide more precise bird orientation information for airport bird detection tasks.
... Visual inspection is a common method for detecting defects using either the raw human eye or inspection equipment or both these methods. With the development of computers and highly sensitive cameras, visual inspection uses digital images and deep learning to quickly and consistently identify defects in the manufacturing line such as in rubber tire, which is a flexible composite structure composed of rubber and was inspected by [1][2][3][4]. These papers have proposed tire defect classification based on different convolutional networks, which prove the robustness and effectiveness of the improved networks with reduced tire defect detection time. ...
This paper proposes a machine vision system for the surface inspection of black rubber rollers in manufacturing processes. The system aims to enhance the surface quality of the rollers by detecting and classifying defects. A lighting system is installed to highlight surface defects. Two algorithms are proposed for defect detection: a traditional-based method and a deep learning-based method. The former is fast but limited to surface defect detection, while the latter is slower but capable of detecting and classifying defects. The accuracy of the algorithms is verified through experiments, with the traditional-based method achieving near-perfect accuracy of approximately 98% for defect detection, and the deep learning-based method achieving an accuracy of approximately 95.2% for defect detection and 96% for defect classification. The proposed machine vision system can significantly improve the surface inspection of black rubber rollers, thereby ensuring high-quality production.
... Rajeswari et al. 34 developed a weighted mass-based convolutional neural network to detect tire defects, and the results of this study showed that tire deformation and durability can be predicted from track design through a weighted mass-based convolutional neural network. Yang et al. 35 developed an improved Faster RCNN-FPN for tire speckle interference bubble defect detection. Their research can fuse features across levels and directions to improve small object detection and localization and improve object detection accuracy. ...
Driving can understand the importance of tire tread depth and air pressure, but most people are unaware of the safety risks of tire oxidation. Drivers must maintain vehicle tire quality to ensure performance, efficiency, and safety. In this study, a deep learning tire defect detection method was designed. This paper improves the traditional ShuffleNet and proposes an improved ShuffleNet method for tire image detection. The research results are compared with the five methods of GoogLeNet, traditional ShuffleNet, VGGNet, ResNet and improved ShuffleNet through tire database verification. The experiment found that the detection rate of tire debris defects was 94.7%. Tire defects can be effectively detected, which proves the robustness and effectiveness of the improved ShuffleNet, enabling drivers and tire manufacturers to save labor costs and greatly reduce tire defect detection time.
... Small objects (less than 32 2 pixels) usually struggle to show sufficient appearance information, which increases the difficulty of feature recognition and extraction, leading to poor performance when detecting small objects. However, small objects extensively exist in the real world and play a crucial role in many fields, such as automatic driving [1][2][3], defect detection [4][5][6], remote sensing [7][8][9] and pest detection [10][11][12]. In particular, agricultural production is greatly restricted by the erosion of crop pests, which has brought infinite losses to the global agricultural economy. ...
As deep learning has been successfully applied in various domains, it has recently received considerable research attention for decades, making it possible to efficiently and intelligently detect crop pests. Nevertheless, the detection of pest objects is still challenging due to the lack of discriminative features and pests’ aggregation behavior. Recently, intersection over union (IoU)-based object detection has attracted much attention and become the most widely used metric. However, it is sensitive to small-object localization bias; furthermore, IoU-based loss only works when ground truths and predicted bounding boxes are intersected, and it lacks an awareness of different geometrical structures. Therefore, we propose a simple and effective metric and a loss function based on this new metric, truncated structurally aware distance (TSD). Firstly, the distance between two bounding boxes is defined as the standardized Chebyshev distance. We also propose a new regression loss function, truncated structurally aware distance loss, which consider the different geometrical structure relationships between two bounding boxes and whose truncated function is designed to impose different penalties. To further test the effectiveness of our method, we apply it on the Pest24 small-object pest dataset, and the results show that the mAP is 5.0% higher than other detection methods.
When using advanced detection algorithms to monitor alligator gar in real-time in wild waters, the efficiency of existing detection algorithms is subject to certain limitations due to turbid water quality, poor underwater lighting conditions, and obstruction by other objects. In order to solve this problem, we developed a lightweight real-time detection network model called ARD-Net, from the perspective of reducing the amount of calculation and obtaining more feature map patterns. We introduced a cross-domain grid matching strategy to accelerate network convergence, and combined the involution operator and dual-channel attention mechanism to build a more lightweight feature extractor and multi-scale detection reasoning network module to enhance the network’s response to different semantics. Compared with the yoloV5 baseline model, our method performs equivalently in terms of detection accuracy, but the model is smaller, the detection speed is increased by 1.48 times, When compared with the latest State-of-the-Art (SOTA) method, YOLOv8, our method demonstrates clear advantages in both detection efficiency and model size,and has good real-time performance. Additionally, we created a dataset of alligator gar images for training.
When using advanced detection algorithms to monitor alligator gar in real-time in wild waters, the efficiency of existing detection algorithms is subject to certain limitations due to turbid water quality, poor underwater lighting conditions, and obstruction by other objects. In order to solve this problem, we developed a lightweight real-time detection network model called ARD-Net, from the perspective of reducing the amount of calculation and obtaining more feature map patterns. We introduced a cross-domain grid matching strategy to accelerate network convergence, and combined the involution operator and dual-channel attention mechanism to build a more lightweight feature extractor and multi-scale detection reasoning network module to enhance the network’s response to different semantics. Compared with the yoloV5 baseline model, our method performs equivalently in terms of detection accuracy, but the model is smaller, the detection speed is increased by 1.48 times, and has good real-time performance. Additionally, we created a dataset of alligator gar images for training.
