Multilevel Thresholding for Image Segmentation Using Mean Gradient

Ashir, Abubakar M.

doi:10.1155/2022/1254852

Cited by 9 publications

(3 citation statements)

References 19 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These matrices include training and validation losses; Precisions, Recall and mean Average Precision (mAP). These parameters are indicative of how well the algorithm learns the task at hand (Anwar & Ashir, 2020;Ashir, 2022). All the losses initially started very high as expected and gradually approaches to zero as the number of epochs increases.…”

Section: Training and Validation Resultsmentioning

confidence: 56%

A Transfer-Learning-Based Approach for Emergency Vehicle Detection

2022

EAJSE

View full text Add to dashboard Cite

The paper presents a computer-vision based approach for real-time detection of different types of emergency vehicles under heavy traffic conditions. This enables preferential path clearance for emergency vehicles by the traffic controller which has the potential of saving lives, properties and increasing the ability to prevent crimes and drastically reducing the total time required by an emergency vehicle to reach its target destination. The main challenge emergency vehicles faced in and around the cities is heavy traffic jams, which significantly hampers their operations resulting in a disastrous outcome. In most of the cities, emergency vehicles are equipped with unique colors and sound system which enable the traffic police to identify them. As our cities become smarter and transition into an era of artificial intelligence, the old system may not be sustainable due to that fact that it needs humans to constantly monitor emergency vehicle arrival at the intersections and also the sound produces by such vehicles may be nuisance and discomforting to the general public. This paper proposed a method of automatic detection of four different categories of emergency vehicle irrespective of the vehicle's shapes, models or manufacturers' using modified version of YOLOv5 object detection algorithm. YOLO is an acronym for (You Only Look Once) and it is an object detection algorithm that divides images into a grid system. Each cell within the grid is responsible for detecting objects within itself. YOLO is one of the most famous object detection algorithms due to its speed and accuracy. YOLO models are used for object detection with high performance which consists of 84 classes to detect and differentiate between 84 different objects. The proposed model developed here is based on 4 classes which are (Firetrucks, Ambulance, Police Car, and Normal Cars) classes. The top layers (fully connected layers) of the YOLO algorithm were re-designed and retrained to get new learned weights while freezing the bottom layers (convolutional layers) and retaining the pre-trained YOLOv5 weights. After retraining with the proposed modified YOLOv5, the model has shown promising results and quite impressive metrics in detecting and classifying emergency vehicles and normal vehicles. Using Mean Average Precision (mAP) metric, for police cars we achieved 98%, 96% for fire trucks, 89% for ambulances and 97% for normal cars.

show abstract

Section: Training and Validation Resultsmentioning

confidence: 56%

A Transfer-Learning-Based Approach for Emergency Vehicle Detection

2022

EAJSE

View full text Add to dashboard Cite

show abstract

“…Over the past ten years, bi-level thresholding has attracted a lot of attention from researchers [1], [2]. The study of multilevel thresholding has also been ongoing [3]- [5]. The image in grayscale format is transformed into an image in binary format using the technique of bi-level thresholding [6].…”

Section: Introductionmentioning

confidence: 99%

An Otsu thresholding for images based on a nature-inspired optimization algorithm

Raheem¹,

Shabat²

2023

IJEECS

View full text Add to dashboard Cite

Thresholding is a type of image segmentation, where the pixels change to make the image easier to analyze. In bi-level thresholding, the image in grayscale format is transformed into a binary format. The traditional methods for image thresholding may be inefficient in finding the best threshold and take longer computation time. Recently, metaheuristic swarm-based algorithms were applied for optimization in different applications to find optimal solutions with minimum computational time. The proposed work aims to optimize the fitness function obtained by the Otsu algorithm using a metaheuristic swarm-based algorithm called the bat algorithm. As a result, the optimal threshold value for bi-level images in cloud detection was obtained. Also, one of the trajectory-based algorithms called hill climbing was applied to optimize the fitness function taken from the Otsu algorithm. The HYTA dataset was used to evaluate the work, which was later confirmed through testing. The findings of experiments indicated that the developed algorithm is promising and the performance of the metaheuristic population-based algorithm is better than the trajectory-based algorithm in terms of efficiency and computational time for image thresholding.

show abstract

“…If the feature vector of the pixel fits into the corresponding class localization in a hypercube, the pixel is classified to that class accordingly. In many tasks, segmentation can be simplified to binarization, which reduces the computational complexity and uncertainty of decisions 21,22 .…”

mentioning

confidence: 99%

Features extraction from multi-spectral remote sensing images based on multi-threshold binarization

Rusyn,

Lutsyk,

Kosarevych

et al. 2023

Sci Rep

View full text Add to dashboard Cite

In this paper, we propose a solution to resolve the limitation of deep CNN models in real-time applications. The proposed approach uses multi-threshold binarization over the whole multi-spectral remote sensing image to extract the vector of discriminative features for classification. We compare the classification accuracy and the training time of the proposed approach with ResNet and Ensemble CNN models. The proposed approach shows a significant advantage in accuracy for small datasets, while keeping very close recall score to both deep CNN models for larger datasets. On the other hand, regardless of the dataset size, the proposed multi-threshold binarization provides approximately 5 times lower training and inference time than both ResNet and Ensemble CNN models.

show abstract

Multilevel Thresholding for Image Segmentation Using Mean Gradient

Cited by 9 publications

References 19 publications

A Transfer-Learning-Based Approach for Emergency Vehicle Detection

A Transfer-Learning-Based Approach for Emergency Vehicle Detection

An Otsu thresholding for images based on a nature-inspired optimization algorithm

Features extraction from multi-spectral remote sensing images based on multi-threshold binarization

Contact Info

Product

Resources

About