A pavement distresses identification method optimized for YOLOv5s

Guo, Kun; He, Chengbo; Yang, Min; Wang, Sudong

doi:10.1038/s41598-022-07527-3

Cited by 26 publications

(14 citation statements)

References 20 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the current algorithm has the problem of excessive amounts of floating-point operations and parameters, which is not conducive to the embedding and deployment of the model [12]. Another example is the single source of images and data, which is not conducive to the testing of model effects [25]. Nevertheless, it can be seen that the technology has a very good prospect, perhaps in some areas, especially in medical images, the development speed will be slow, but with the continuous development of computer technology and the crossfertilization of multidisciplinary theories, deep learning applications will certainly play a greater role in various fields.…”

Section: Discussionmentioning

confidence: 99%

Investigation of the theory and applications of deep learning-based image recognition

Cai

2023

International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023)

View full text Add to dashboard Cite

Image recognition technology, as an important branch in the field of artificial intelligence, aims to process and analyze images to recognize objects in images. The aim of this paper is to summarize the general approach to implementing image recognition and the application of this technology in some fields by analyzing relevant articles in the field of image recognition in recent years and to suggest possible conjectures on the future direction of this technology. This paper points out that the image recognition process is divided into two main parts: image processing and image recognition. For the implementation of the corresponding algorithms, this paper introduces two commonly used software libraries: OpenCV and YOLOv5. In addition, the paper also focuses on the applications and contributions of image recognition techniques to face recognition, lane detection, and medical image analysis. It is also pointed out that image recognition technology has a very promising future, and that there is still a lot of further improvement in the field of medical image analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Investigation of the theory and applications of deep learning-based image recognition

Cai

2023

International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023)

View full text Add to dashboard Cite

show abstract

“…YOLOv5 is currently the more popular deep learning network algorithm and there are four types: YOLOv5x, YOLOv5l, YOLOv5m and YOLOv5s, the difference lies in the size and performance of their models. Considering the speed of infrared insulator image recognition, the YOLOv5s model with the smallest input feature map size, higher accuracy and faster speed is used in this paper [11] . Its network framework is shown in Figure 1, and there exist four parts, which are Input at the input, Backbone at the backbone network, Neck at the neck network, and Head at the output.Mosaic data enhancement is used on the input side.…”

Section: Yolov5 Modelmentioning

confidence: 99%

Research on infrared insulator image recognition based on improved YOLOv5

Lang,

Ji,

Xie

et al. 2023

Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023)

View full text Add to dashboard Cite

As the scale of transmission lines is expanding, the safety of transmission line operation is getting more and more attention; insulators as an important component of transmission lines, the use of insulators greatly affects the safe operation of transmission lines. The traditional depth recognition algorithm can not achieve effective recognition of infrared images, in order to achieve rapid recognition of insulators in complex environments, this paper proposes the recognition of infrared insulator images based on the improved YOLOv5 depth neural network detection algorithm. Firstly, Ghost convolution was introduced into the backbone network to speed up detection and network lightweighting; secondly, to enhance the multi-scale convergence of networks, improved GAM attention module added behind the neck network; in addition, the network introduces an EIOU loss function for convergence; finally, validation of this improved algorithm with the collected infrared insulator dataset. The results show that the improved algorithm in this paper achieves 91.2% accuracy and 92.1% mAP on the infrared insulator dataset, which improves 2.3% and 4.1% compared with the test results of YOLOv5 model, simultaneous detection speed up to 91 FPS, which meets the real-time requirement.

show abstract

“…(5) Model evaluation index: in Eqs. ( 3) and (4), P represents the number of actual positive samples while the model predicts the number of positive samples, FP represents the number of actual negative samples while the model predicts positive samples, FN represents the number of actual positive samples while the model predicts negative samples, TN represents the number of actual negative samples and predicted negative samples [10].…”

Section: Target Detection Model: Yolo V5mentioning

confidence: 99%

Research on Two-Way Detection of YOLO V5s+Deep Sort Road Vehicles Based on Attention Mechanism

Gao

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

YOLO v5 was born when Joseph Redmon, the father of YOLO, announced his retirement from the field of computer vision, and its structure was further optimized on the basis of YOLO v4. After the sort target tracking algorithm was proposed, the deep sort algorithm added the optimization of apparent features on the basis of the sort algorithm, which enables the model to be more suitable for practical situations and more mature for vehicle detection on traffic roads. Focusing on the new direction of road traffic detection, a single camera is used to detect and track dual-channel vehicles. In the process of experimental exploration, a “double vertical line” algorithm is proposed by introducing the attention mechanism into the YOLO v5 structure and combining with the deep sort target tracking algorithm, which provides a new thinking angle and flow chart for vehicle repeat counting. Finally, the detection results of vehicle identity and traffic flow are obtained through experiments, enabling vehicles to be detected and tracked in real time even on roads with a certain speed. In addition, the calculation law avoids the miscalculation of roads with forks, obtains excellent results on vehicle types and traffic flow, and uses id identity to give car information, which significantly improves the possibility that the model can be applied to practical problems.

show abstract

A pavement distresses identification method optimized for YOLOv5s

Cited by 26 publications

References 20 publications

Investigation of the theory and applications of deep learning-based image recognition

Investigation of the theory and applications of deep learning-based image recognition

Research on infrared insulator image recognition based on improved YOLOv5

Research on Two-Way Detection of YOLO V5s+Deep Sort Road Vehicles Based on Attention Mechanism

Contact Info

Product

Resources

About