PDNet: Improved YOLOv5 Nondeformable Disease Detection Network for Asphalt Pavement

Yang, Zhen; Li, Lin; Luo, Wenting

doi:10.1155/2022/5133543

Cited by 12 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous BM detection studies have used a confidence threshold of 50% [ 9 , 31 , 32 ] or confidence thresholds ranging from 0.1 to 0.9 [ 11 ]; however, these approach may not lead to optimal results for BM detection. Other object detection research has utilized the F1-score, which represents the harmonic mean of precision and recall, to determine the optimal confidence threshold [ 33 , 34 , 35 ]. As the recall is more important than the precision in BM detection, we introduced the F2-score, which emphasizes the importance of recall by assigning it twice the weight of precision, to determine the optimal confidence threshold.…”

Section: Methodsmentioning

confidence: 99%

Automatic Detection of Brain Metastases in T1-Weighted Construct-Enhanced MRI Using Deep Learning Model

Zhou,

Qiu,

Liu

et al. 2023

Cancers

View full text Add to dashboard Cite

As a complication of malignant tumors, brain metastasis (BM) seriously threatens patients’ survival and quality of life. Accurate detection of BM before determining radiation therapy plans is a paramount task. Due to the small size and heterogeneous number of BMs, their manual diagnosis faces enormous challenges. Thus, MRI-based artificial intelligence-assisted BM diagnosis is significant. Most of the existing deep learning (DL) methods for automatic BM detection try to ensure a good trade-off between precision and recall. However, due to the objective factors of the models, higher recall is often accompanied by higher number of false positive results. In real clinical auxiliary diagnosis, radiation oncologists are required to spend much effort to review these false positive results. In order to reduce false positive results while retaining high accuracy, a modified YOLOv5 algorithm is proposed in this paper. First, in order to focus on the important channels of the feature map, we add a convolutional block attention model to the neck structure. Furthermore, an additional prediction head is introduced for detecting small-size BMs. Finally, to distinguish between cerebral vessels and small-size BMs, a Swin transformer block is embedded into the smallest prediction head. With the introduction of the F2-score index to determine the most appropriate confidence threshold, the proposed method achieves a precision of 0.612 and recall of 0.904. Compared with existing methods, our proposed method shows superior performance with fewer false positive results. It is anticipated that the proposed method could reduce the workload of radiation oncologists in real clinical auxiliary diagnosis.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Detection of Brain Metastases in T1-Weighted Construct-Enhanced MRI Using Deep Learning Model

Zhou,

Qiu,

Liu

et al. 2023

Cancers

View full text Add to dashboard Cite

show abstract

“…YOLOv5 is a compound-scale object detection algorithm and provides models trained on the Common Object in Context dataset. It implements object detection by regression calculation directly on the image, and its effect on pavement crack detection has been proven in recent research [28,30,42]. YOLOv5 uses the mature structure of the YOLO algorithm and integrates some strategies of other machine vision algorithms which achieved great success in the object detection field.…”

Section: Methodsmentioning

confidence: 99%

“…The newer and more powerful deep learning algorithms are also used for pavement crack segmentation and detection, such as R-CNN (Region-CNN) [22], Fast R-CNN [23], Faster R-CNN [24,25] and Mask R-CNN [26,27]. The YOLO algorithm, the faster and more widely used object detection, is applied to locate cracks in the image which shows a huge potential in pavement inspection [28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Pavement crack detection based on point cloud data and data fusion

Dong

Wang

Chen

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

The three-dimensional detection in point cloud data for pavement cracks has drawn the attention of many researchers recently. In the field of pavement surface point cloud detection, the key tasks include the identification of pavement cracks and the extraction of the location and size information of pavement cracks. Based on the point cloud data of pavement surface, we developed two methods to directly extract and detect cracks, respectively. The first method is based on the improved sliding window algorithm by combining the random sample consensus (RANSAC) technique to directly extract the crack information from point clouds. The second method is developed based on YOLOv5 to process the two-dimensional images transformed from point cloud data for automatic pavement crack detection. We also attempted to fuse the point cloud images with greyscale images as input for the YOLOv5. Analysis results show that the improved sliding window algorithm efficiently extracts pavement cracks with less noise, and the YOLOv5-based method obtains a good detection of pavement cracks. This article is part of the theme issue ‘Artificial intelligence in failure analysis of transportation infrastructure and materials’.

show abstract

“…However, due to its high model complexity, its reasoning speed increases. In order to realize model compression, accelerated detection, and accurate recognition under multi-scale conditions, Yang et al [23] proposed a lightweight algorithm PDNet based on improved YOLOv5.Although it can achieve high detection speed, it fails to pay attention to the low resolution and small object problems in road disease detection.…”

Section: Introductionmentioning

confidence: 99%

Road Disease Detection Algorithm Based on YOLOv5s-DSG

Xiang

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Automatic detection and classification of road conditions are critical for the timely maintenance and repair of road surfaces. Aiming at the problems of single detection type, low detection efficiency, the low resolution of detection objects, and difficult detection of small object features in the road disease detection scene, this paper proposes an improved YOLOv5s road disease detection algorithm, YOLOv5s-DSG. First, optimize the depth and width of the network structure to reduce the impact on road damage image detection performance. Secondly, the Ghost module replaces the traditional convolution to reduce the number of model parameters, making the model lightweight and improving the detection rate. Finally, the Space-to-depth-Conv module is introduced to adapt to low-resolution and small object detection tasks. A large number of experiments on datasets such as Road Damage Dataset 2022 show that the average accuracy of the improved model at low resolution 640×640 is 1.1% higher than that of the original model, and the FPS is increased from 85 to 90; when the resolution is reduced to 480×480, the average accuracy remains the same and the FPS increases to 93. Compared with existing algorithms, it has apparent advantages in road comprehensive disease detection and classification.

show abstract

PDNet: Improved YOLOv5 Nondeformable Disease Detection Network for Asphalt Pavement

Cited by 12 publications

References 41 publications

Automatic Detection of Brain Metastases in T1-Weighted Construct-Enhanced MRI Using Deep Learning Model

Automatic Detection of Brain Metastases in T1-Weighted Construct-Enhanced MRI Using Deep Learning Model

Pavement crack detection based on point cloud data and data fusion

Road Disease Detection Algorithm Based on YOLOv5s-DSG

Contact Info

Product

Resources

About