Search results
1 – 10 of 100This work aims to present a deep learning model for face mask detection in surveillance environments such as automatic teller machines (ATMs), banks, etc. to identify persons…
Abstract
Purpose
This work aims to present a deep learning model for face mask detection in surveillance environments such as automatic teller machines (ATMs), banks, etc. to identify persons wearing face masks. In surveillance environments, complete visibility of the face area is a guideline, and criminals and law offenders commit crimes by hiding their faces behind a face mask. The face mask detector model proposed in this work can be used as a tool and integrated with surveillance cameras in autonomous surveillance environments to identify and catch law offenders and criminals.
Design/methodology/approach
The proposed face mask detector is developed by integrating the residual network (ResNet)34 feature extractor on top of three You Only Look Once (YOLO) detection layers along with the usage of the spatial pyramid pooling (SPP) layer to extract a rich and dense feature map. Furthermore, at the training time, data augmentation operations such as Mosaic and MixUp have been applied to the feature extraction network so that it can get trained with images of varying complexities. The proposed detector is trained and tested over a custom face mask detection dataset consisting of 52,635 images. For validation, comparisons have been provided with the performance of YOLO v1, v2, tiny YOLO v1, v2, v3 and v4 and other benchmark work present in the literature by evaluating performance metrics such as precision, recall, F1 score, mean average precision (mAP) for the overall dataset and average precision (AP) for each class of the dataset.
Findings
The proposed face mask detector achieved 4.75–9.75 per cent higher detection accuracy in terms of mAP, 5–31 per cent higher AP for detection of faces with masks and, specifically, 2–30 per cent higher AP for detection of face masks on the face region as compared to the tested baseline variants of YOLO. Furthermore, the usage of the ResNet34 feature extractor and SPP layer in the proposed detection model reduced the training time and the detection time. The proposed face mask detection model can perform detection over an image in 0.45 s, which is 0.2–0.15 s lesser than that for other tested YOLO variants, thus making the proposed detection model perform detections at a higher speed.
Research limitations/implications
The proposed face mask detector model can be utilized as a tool to detect persons with face masks who are a potential threat to the automatic surveillance environments such as ATMs, banks, airport security checks, etc. The other research implication of the proposed work is that it can be trained and tested for other object detection problems such as cancer detection in images, fish species detection, vehicle detection, etc.
Practical implications
The proposed face mask detector can be integrated with automatic surveillance systems and used as a tool to detect persons with face masks who are potential threats to ATMs, banks, etc. and in the present times of COVID-19 to detect if the people are following a COVID-appropriate behavior of wearing a face mask or not in the public areas.
Originality/value
The novelty of this work lies in the usage of the ResNet34 feature extractor with YOLO detection layers, which makes the proposed model a compact and powerful convolutional neural-network-based face mask detector model. Furthermore, the SPP layer has been applied to the ResNet34 feature extractor to make it able to extract a rich and dense feature map. The other novelty of the present work is the implementation of Mosaic and MixUp data augmentation in the training network that provided the feature extractor with 3× images of varying complexities and orientations and further aided in achieving higher detection accuracy. The proposed model is novel in terms of extracting rich features, performing augmentation at the training time and achieving high detection accuracy while maintaining the detection speed.
Details
Keywords
Xinfa Shi, Ce Cui, Shizhong He, Xiaopeng Xie, Yuhang Sun and Chudong Qin
The purpose of this paper is to identify smaller wear particles and improve the calculation speed, identify more abrasive particles and promote industrial applications.
Abstract
Purpose
The purpose of this paper is to identify smaller wear particles and improve the calculation speed, identify more abrasive particles and promote industrial applications.
Design/methodology/approach
This paper studies a new intelligent recognition method for equipment wear debris based on the YOLO V5S model released in June 2020. Nearly 800 ferrography pictures, 23 types of wear debris, about 5,000 wear debris were used to train and test the model. The new lightweight approach of wear debris recognition can be implemented in rapidly and automatically and also provide for the recognition of wear debris in the field of online wear monitoring.
Findings
An intelligent recognition method of wear debris in ferrography image based on the YOLO V5S model was designed. After the training, the GIoU values of the model converged steadily at about 0.02. The overall precision rate and recall rate reached 0.4 and 0.5, respectively. The overall MAP value of each type of wear debris was 40.5, which was close to the official recognition level of YOLO V5S in the MS COCO competition. The practicality of the model was approved. The intelligent recognition method of wear debris based on the YOLO V5S model can effectively reduce the sensitivity of wear debris size. It also has a good recognition effect on wear debris in different sizes and different scales. Compared with YOLOV. YOLOV, Mask R-CNN and other algorithms%2C, the intelligent recognition method based on the YOLO V5S model, have shown their own advantages in terms of the recognition effect of wear debris%2C the operation speed and the size of weight files. It also provides a new function for implementing accurate recognition of wear debris images collected by online and independent ferrography analysis devices.
Originality/value
To the best of the authors’ knowledge, the intelligent identification of wear debris based on the YOLO V5S network is proposed for the first time, and a large number of wear debris images are verified and applied.
Details
Keywords
Vishva Payghode, Ayush Goyal, Anupama Bhan, Sailesh Suryanarayan Iyer and Ashwani Kumar Dubey
This paper aims to implement and extend the You Only Live Once (YOLO) algorithm for detection of objects and activities. The advantage of YOLO is that it only runs a neural…
Abstract
Purpose
This paper aims to implement and extend the You Only Live Once (YOLO) algorithm for detection of objects and activities. The advantage of YOLO is that it only runs a neural network once to detect the objects in an image, which is why it is powerful and fast. Cameras are found at many different crossroads and locations, but video processing of the feed through an object detection algorithm allows determining and tracking what is captured. Video Surveillance has many applications such as Car Tracking and tracking of people related to crime prevention. This paper provides exhaustive comparison between the existing methods and proposed method. Proposed method is found to have highest object detection accuracy.
Design/methodology/approach
The goal of this research is to develop a deep learning framework to automate the task of analyzing video footage through object detection in images. This framework processes video feed or image frames from CCTV, webcam or a DroidCam, which allows the camera in a mobile phone to be used as a webcam for a laptop. The object detection algorithm, with its model trained on a large data set of images, is able to load in each image given as an input, process the image and determine the categories of the matching objects that it finds. As a proof of concept, this research demonstrates the algorithm on images of several different objects. This research implements and extends the YOLO algorithm for detection of objects and activities. The advantage of YOLO is that it only runs a neural network once to detect the objects in an image, which is why it is powerful and fast. Cameras are found at many different crossroads and locations, but video processing of the feed through an object detection algorithm allows determining and tracking what is captured. For video surveillance of traffic cameras, this has many applications, such as car tracking and person tracking for crime prevention. In this research, the implemented algorithm with the proposed methodology is compared against several different prior existing methods in literature. The proposed method was found to have the highest object detection accuracy for object detection and activity recognition, better than other existing methods.
Findings
The results indicate that the proposed deep learning–based model can be implemented in real-time for object detection and activity recognition. The added features of car crash detection, fall detection and social distancing detection can be used to implement a real-time video surveillance system that can help save lives and protect people. Such a real-time video surveillance system could be installed at street and traffic cameras and in CCTV systems. When this system would detect a car crash or a fatal human or pedestrian fall with injury, it can be programmed to send automatic messages to the nearest local police, emergency and fire stations. When this system would detect a social distancing violation, it can be programmed to inform the local authorities or sound an alarm with a warning message to alert the public to maintain their distance and avoid spreading their aerosol particles that may cause the spread of viruses, including the COVID-19 virus.
Originality/value
This paper proposes an improved and augmented version of the YOLOv3 model that has been extended to perform activity recognition, such as car crash detection, human fall detection and social distancing detection. The proposed model is based on a deep learning convolutional neural network model used to detect objects in images. The model is trained using the widely used and publicly available Common Objects in Context data set. The proposed model, being an extension of YOLO, can be implemented for real-time object and activity recognition. The proposed model had higher accuracies for both large-scale and all-scale object detection. This proposed model also exceeded all the other previous methods that were compared in extending and augmenting the object detection to activity recognition. The proposed model resulted in the highest accuracy for car crash detection, fall detection and social distancing detection.
Details
Keywords
Automated dust monitoring in workplaces helps provide timely alerts to over-exposed workers and effective mitigation measures for proactive dust control. However, the cluttered…
Abstract
Purpose
Automated dust monitoring in workplaces helps provide timely alerts to over-exposed workers and effective mitigation measures for proactive dust control. However, the cluttered nature of construction sites poses a practical challenge to obtain enough high-quality images in the real world. The study aims to establish a framework that overcomes the challenges of lacking sufficient imagery data (“data-hungry problem”) for training computer vision algorithms to monitor construction dust.
Design/methodology/approach
This study develops a synthetic image generation method that incorporates virtual environments of construction dust for producing training samples. Three state-of-the-art object detection algorithms, including Faster-RCNN, you only look once (YOLO) and single shot detection (SSD), are trained using solely synthetic images. Finally, this research provides a comparative analysis of object detection algorithms for real-world dust monitoring regarding the accuracy and computational efficiency.
Findings
This study creates a construction dust emission (CDE) dataset consisting of 3,860 synthetic dust images as the training dataset and 1,015 real-world images as the testing dataset. The YOLO-v3 model achieves the best performance with a 0.93 F1 score and 31.44 fps among all three object detection models. The experimental results indicate that training dust detection algorithms with only synthetic images can achieve acceptable performance on real-world images.
Originality/value
This study provides insights into two questions: (1) how synthetic images could help train dust detection models to overcome data-hungry problems and (2) how well state-of-the-art deep learning algorithms can detect nonrigid construction dust.
Details
Keywords
This paper aims to design an AI-based drone that can facilitate the complicated and time-intensive control process for detecting healthy and defective solar panels. Today, the use…
Abstract
Purpose
This paper aims to design an AI-based drone that can facilitate the complicated and time-intensive control process for detecting healthy and defective solar panels. Today, the use of solar panels is becoming widespread, and control problems are increasing. Physical control of the solar panels is critical in obtaining electrical power. Controlling solar panel power plants and rooftop panel applications installed in large areas can be difficult and time-consuming. Therefore, this paper designs a system that aims to panel detection.
Design/methodology/approach
This paper designed a low-cost AI-based unmanned aerial vehicle to reduce the difficulty of the control process. Convolutional neural network based AI models were developed to classify solar panels as damaged, dusty and normal. Two approaches to the solar panel detection model were adopted: Approach 1 and Approach 2.
Findings
The training was conducted with YOLOv5, YOLOv6 and YOLOv8 models in Approach 1. The best F1 score was 81% at 150 epochs with YOLOv5m. In total, 87% and 89% of the best F1 score and mAP values were obtained with the YOLOv5s model at 100 epochs in Approach 2 as a proposed method. The best models at Approaches 1 and 2 were used with a developed AI-based drone in the real-time test application.
Originality/value
The AI-based low-cost solar panel detection drone was developed with an original data set of 1,100 images. A detailed comparative analysis of YOLOv5, YOLOv6 and YOLOv8 models regarding performance metrics was realized. Gaussian, salt-pepper noise addition and wavelet transform noise removal preprocessing techniques were applied to the created data set under the proposed method. The proposed method demonstrated expressive and remarkable performance in panel detection applications.
Details
Keywords
D.S. Vohra, Pradeep Kumar Garg and Sanjay Ghosh
The purpose is to design a system in which drones can control traffic most effectively using a deep learning algorithm.
Abstract
Purpose
The purpose is to design a system in which drones can control traffic most effectively using a deep learning algorithm.
Design/methodology/approach
Drones have now started entry into each facet of life. The entry of drones has made them a subject of great relevance in the present technological era. The span of drones is, however, very broad due to various kinds of usages leading to different types of drones. Out of the many usages, one usage which is presently being widely researched is traffic monitoring as traffic monitoring can hover over a particular area. This paper specifically brings out the basic algorithm You Look Only Once (YOLO) which may be used for identifying the vehicles. Consequently, using deep learning YOLO algorithm, identification of vehicles will, therefore, help in easy regulation of traffic in streetlights, avoiding accidents, finding out the culprit drivers due to which traffic jam would have taken place and recognition of a pattern of traffic at various timings of the day, thereby announcing the same through radio (namely, Frequency Modulation (FM)) channels, so that people can take the route which is the least jammed.
Findings
The study found that the object(s) detected by the deep learning algorithm is almost the same as if seen from a naked eye from the top view. This led to the conclusion that the drones may be used for traffic monitoring, in the days to come, which was not the case earlier.
Originality/value
The main research content and key algorithm have been introduced. The research is original. None of the parts of this research paper has been published anywhere.
Details
Keywords
The purpose of this paper is to present a deep ensemble neural network model for the detection of forest fires in aerial vehicle videos.
Abstract
Purpose
The purpose of this paper is to present a deep ensemble neural network model for the detection of forest fires in aerial vehicle videos.
Design/methodology/approach
Presented deep ensemble models include four convolutional neural networks (CNNs): a faster region-based CNN (Faster R-CNN), a simple one-stage object detector (RetinaNet) and two different versions of the you only look once (Yolo) models. The presented method generates its output by fusing the outputs of these different deep learning (DL) models.
Findings
The presented fusing approach significantly improves the detection accuracy of fire incidents in the input data.
Research limitations/implications
The computational complexity of the proposed method which is based on combining four different DL models is relatively higher than that of using each of these models individually. On the other hand, however, the performance of the proposed approach is considerably higher than that of any of the four DL models.
Practical implications
The simulation results show that using an ensemble model is quite useful for the precise detection of forest fires in real time through aerial vehicle videos or images.
Social implications
By this method, forest fires can be detected more efficiently and precisely. Because forests are crucial breathing resources of the earth and a shelter for many living creatures, the social impact of the method can be considered to be very high.
Originality/value
This study fuses the outputs of different DL models into an ensemble model. Hence, the ensemble model provides more potent and beneficial results than any of the single models.
Details
Keywords
Lalitha Ramadass, Sushanth Arunachalam and Sagayasree Z.
The purpose of this paper is to inspect whether the people in a public place maintain social distancing. It also checks whether every individual is wearing face mask. If both are…
Abstract
Purpose
The purpose of this paper is to inspect whether the people in a public place maintain social distancing. It also checks whether every individual is wearing face mask. If both are not done, the drone sends alarm signal to nearby police station and also give alarm to the public. In addition, it also carries masks and drop them to the needed people. Nearby, traffic police will also be identified and deliver water packet and mask to them if needed.
Design/methodology/approach
The proposed system uses an automated drone which is used to perform the inspection process. First, the drone is being constructed by considering the parameters such as components selection, payload calculation and then assembling the drone components and connecting the drone with the mission planner software for calibrating the drone for its stability. The trained yolov3 algorithm with the custom data set is being embedded in the drone’s camera. The drone camera runs the yolov3 algorithm and detects the social distance is maintained or not and whether the people in public is wearing masks. This process is carried out by the drone automatically.
Findings
The proposed system delivers masks to people who are not wearing masks and tells importance of masks and social distancing. Thus, this proposed system would work in an efficient manner after the lockdown period ends and helps in easy social distance inspection in an automatic manner. The algorithm can be embedded in public cameras and then details can be fetched to the camera unit same as the drone unit which receives details from the drone location details and store it in database. Thus, the proposed system favours the society by saving time and helps in lowering the spread of corona virus.
Practical implications
It can be implemented practically after lockdown to inspect people in public gatherings, shopping malls, etc.
Social implications
Automated inspection reduces manpower to inspect the public and also can be used in any place.
Originality/value
This is the original project done with the help of under graduate students of third year B.E. CSE. The system was tested and validated for accuracy with real data.
Details
Keywords
Cemalettin Akdoğan, Tolga Özer and Yüksel Oğuz
Nowadays, food problems are likely to arise because of the increasing global population and decreasing arable land. Therefore, it is necessary to increase the yield of…
Abstract
Purpose
Nowadays, food problems are likely to arise because of the increasing global population and decreasing arable land. Therefore, it is necessary to increase the yield of agricultural products. Pesticides can be used to improve agricultural land products. This study aims to make the spraying of cherry trees more effective and efficient with the designed artificial intelligence (AI)-based agricultural unmanned aerial vehicle (UAV).
Design/methodology/approach
Two approaches have been adopted for the AI-based detection of cherry trees: In approach 1, YOLOv5, YOLOv7 and YOLOv8 models are trained with 70, 100 and 150 epochs. In Approach 2, a new method is proposed to improve the performance metrics obtained in Approach 1. Gaussian, wavelet transform (WT) and Histogram Equalization (HE) preprocessing techniques were applied to the generated data set in Approach 2. The best-performing models in Approach 1 and Approach 2 were used in the real-time test application with the developed agricultural UAV.
Findings
In Approach 1, the best F1 score was 98% in 100 epochs with the YOLOv5s model. In Approach 2, the best F1 score and mAP values were obtained as 98.6% and 98.9% in 150 epochs, with the YOLOv5m model with an improvement of 0.6% in the F1 score. In real-time tests, the AI-based spraying drone system detected and sprayed cherry trees with an accuracy of 66% in Approach 1 and 77% in Approach 2. It was revealed that the use of pesticides could be reduced by 53% and the energy consumption of the spraying system by 47%.
Originality/value
An original data set was created by designing an agricultural drone to detect and spray cherry trees using AI. YOLOv5, YOLOv7 and YOLOv8 models were used to detect and classify cherry trees. The results of the performance metrics of the models are compared. In Approach 2, a method including HE, Gaussian and WT is proposed, and the performance metrics are improved. The effect of the proposed method in a real-time experimental application is thoroughly analyzed.
Details