Real-Time Pattern-Recognition of GPR Images with YOLO v3 Implemented by Tensorflow

Li, Yuanhong; Zhen, Zhao; Luo, Yangfan; Zhi, Qiu

doi:10.3390/s20226476

Cited by 55 publications

(31 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All images are in JPG format and were annotated using two formats PascalVoc (XML) and YOLO (TXT). These formats were chosen since they are commonly used in object recognition tasks or to evaluate and compare the performance of different techniques [4] , [5] .…”

Section: Data Descriptionmentioning

confidence: 99%

Dataset for localization and classification of Medjool dates in digital images

Pérez-Pérez

Salomón-Torres²,

García-Vázquez

2021

Data in Brief

View full text Add to dashboard Cite

Nowadays, harvesting, sorting, and packaging fruit and vegetables are still done manually, despite the hard work this represents. The features that experts commonly use to sorting the date palm fruit are size, color, shape, and texture. Recently, it has started to design and develop artificial vision systems that consider the criteria of size, color, shape, and texture to automate these processes. However, the development of these systems is complex due to the lack of labeled datasets that facilitate the creation of models to locate, recognize and classify palm date fruit. This dataset is entitled Medjool, an image dataset of different sizes and maturity levels of Medjool dates. Researchers may use this data to develop a model for automatic location, recognition, classification, and visual counting of the Medjool dates on trays taking into account their visual features such as shape, color, size, and texture. This dataset was collected from the first-round harvest at Palmeras RQ Ranch in Mexicali, Mexico. Images acquisition was performed in natural light. The dataset comprises 2,576 annotated images in two formats, YOLO and PascalVOC format.

show abstract

Section: Data Descriptionmentioning

confidence: 99%

Dataset for localization and classification of Medjool dates in digital images

Pérez-Pérez

Salomón-Torres²,

García-Vázquez

2021

Data in Brief

View full text Add to dashboard Cite

show abstract

“…After establishing the dataset, an experiment was conducted to compare and verify the object recognition accuracy in terms of rebar diameter using the YOLO-v3 algorithm. To execute the YOLO-v3 algorithm, a computer equipped with an Intel i5-6300 CPU, NVIDIA GeForce GTX 960M GPU, and 8 GB of memory was used, and Figure 8 network architecture was selected as the backbone network [23]. In terms of the acquired data, 80% was used as learning data and 20% was used as verification data.…”

Section: Experimental Planning and Configurationmentioning

confidence: 99%

Improvement of GPR-Based Rebar Diameter Estimation Using YOLO-v3

Park¹,

Kim

Jeon

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

As the frequency of earthquakes has increased in Korea in recent years, designing earthquake-resistant facilities has been increasingly emphasized. Structures constructed with rebars are vulnerable to shaking, which reduces their seismic performance and may result in damage to human life and property. Because the construction of facilities requires the maintenance of sub-constructions, such as by cutting rebars or compensating for missing rebars, information on rebar diameter is required. In this study, the YOLO-v3 algorithm, which has the fastest object recognition performance, was applied to the structural correction data, and a basic experiment was conducted in the air to predict the diameter of rebars in a facility, in real time based on ground-penetrating radar data. The reason for using the YOLO-v3 algorithm is that in the case of GPR data that change slightly according to the diameter of the reinforcing bar, it is difficult to discriminate with the naked eye, and the result may change depending on the inspector. The model achieved a higher accuracy than conventional rebar detection and diameter prediction methods. In addition, the possibility of real-time rebar diameter prediction during construction, using the proposed method, was verified.

show abstract

“…In comparison to recognition algorithms, a detection algorithm does not only predict class labels but detects locations of objects as well. So, it not only classifies the image into a category, but it can also detect multiple Objects within an Image [11]. It is extremely fast and accurate.…”

Section: A Comparison Of Yolo With Other Detection Algorithmmentioning

confidence: 99%

“…This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities [11] (Fig. 6).…”

Section: A Comparison Of Yolo With Other Detection Algorithmmentioning

confidence: 99%

Real Time Vehicle Detection, Tracking, and Inter-vehicle Distance Estimation based on Stereovision and Deep Learning using YOLOv3

Bourja¹,

Derrouz²,

Abdelali³

et al. 2021

IJACSA

View full text Add to dashboard Cite

In this paper, we propose a robust real-time vehicle tracking and inter-vehicle distance estimation algorithm based on stereovision. Traffic images are captured by a stereoscopic system installed on the road, and then we detect moving vehicles with the YOLO V3 Deep Neural Network algorithm. Thus, the real-time video goes through an algorithm for stereoscopy-based measurement in order to estimate distance between detected vehicles. However, detecting the real-time objects have always been a challenging task because of occlusion, scale, illumination etc. Thus, many convolutional neural network models based on object detection were developed in recent years. But they cannot be used for real-time object analysis because of slow speed of recognition. The model which is performing excellent currently is the unified object detection model which is You Only Look Once (YOLO). But in our experiment, we have found that despite of having a very good detection precision, YOLO still has some limitations. YOLO processes every image separately even in a continuous video or frames. Because of this much important identification can be lost. So, after the vehicle detection and tracking, inter-vehicle distance estimation is done.

show abstract

Real-Time Pattern-Recognition of GPR Images with YOLO v3 Implemented by Tensorflow

Cited by 55 publications

References 37 publications

Dataset for localization and classification of Medjool dates in digital images

Dataset for localization and classification of Medjool dates in digital images

Improvement of GPR-Based Rebar Diameter Estimation Using YOLO-v3

Real Time Vehicle Detection, Tracking, and Inter-vehicle Distance Estimation based on Stereovision and Deep Learning using YOLOv3

Contact Info

Product

Resources

About