Search results

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.

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.

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.

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.

Supplier selection for capital procurement is a major strategic decision for any automobile company. The decision determines the success of the company and must be taken systematically with the utmost transparency. The purpose of this paper is to construct capital procurement decision-making model to optimize supplier selection in the Indian automobile industry.

To achieve the stated objective, a combined approach of fuzzy theory and AHP-DEMATEL is applied. Evaluation parameters are identified through an extensive literature review and criteria validation has been introduced through a Fuzzy Delphi method by using fuzzy linguistic scales to handle the vagueness of information. AHP is employed to find the priority weight of criteria, although an inter-relationship map among criteria is not possible through AHP alone since it considers all criteria as independent. To overcome this, DEMATEL is used to establish cause-effect relationships among criteria.

The results show that the total cost of ownership (TOC) is the first weighted criterion in supplier selection for capital procurement, followed by manufacturing flexibility and maintainability, then conformity with requirement. The cause-effect model shows that supplier profile, TOC, service support and conformity with requirement are in the cause group and are considered to be the most critical factors in selecting the supplier.

The study’s outcome can help the automobile industry to optimize their selection process in selecting their suppliers for capital procurement; the proposed model can provide guidelines and direction in this regard.

Micro, small and medium enterprise (MSME) is the kingpin of Indian economy. It contributes to 48% of India's exports and provides employment to 110 million people. As a result, it is critical to evaluate the obstacles, expose them and find a way to overcome the crisis due to the pandemic. The study aims to analyse the impact of financial and non-financial measures for the revival of MSME and its impact on firm sustainability and future opportunity as perceived by MSME owners/heads during the COVID-19 outbreak.

This study, based on a cross-sectional survey of 197 export-oriented Indian MSMEs, attempts to investigate covid crisis mitigation strategies/measures in the context of the COVID-19 crisis. The confirmatory factor analysis (CFA) model was applied to check model fit, and structural equation modelling (SEM) was employed for data analysis.

The results of this study show the financial and non-financial revival measures such as firm revival, marketing training, customer relationship management (CRM), financial incentive and firm support, extending worker social security and financial access and price control positively impact MSMEs' business sustainability and future opportunity as perceived by the respondents that lent good support to the hypothesis.

The study emphasizes management in association with government and financial institutions to design short-term as well as long-term strategies that may enhance their sustainability in the market. MSMEs are being forced to reassess their business strategy and modify their operating model as a result of the uncertain/unpredictable climate. Many levels of strategy aid in revitalizing the company and providing future possibilities to move forward if the government schemes positively impact the perception of entrepreneurs. Further, the study identifies the immediate measures to tide over the crisis over this sector and then furnishes recommendations for closing the identified gaps in the present understanding.

The impact of COVID-19 on Indian MSMEs and how these MSMEs are dealing with it are highlighted in this paper, which is quite scarce and insufficient to cover the gap. It also provides a comprehensive view of firm sustainability and perceived opportunity among MSMEs.

The COVID-19 health crisis has brought about a set of extra health and safety regulations, and procedures to the construction industry which could influence projects' economic performance (EP). The aim of this paper is to examine the effect of adopting COVID-19 safety protocols on construction sites on the economic performance (EP) of construction projects.

Employing the survey method using a structured questionnaire, data were collected from small- and large-sized construction projects in Nigeria and analysed using partial least squares structural equation modelling (PLS-SEM) technique.

The findings reveal that job re-organization and sanitization have negative significant effects on EP, while social distancing and specific training have no effect on EP. Furthermore, project size moderates the relationship between job re-organization, sanitization, specific training and EP with the stronger effect on the relationships observed in big projects, except for the relationship between sanitization and EP where the moderating relationship is stronger in small projects. However, there is no significant moderating effect of project size on the relationship between social distancing and EP.

As construction project sites continue to operate amidst strict safety protocols, this study offers theoretical and practical insights on how construction projects can adhere to the safety protocols while performing economically.

The originality of this study's findings stems from the fact that it is among the first to provide greater insight on how construction projects have fared economically considering the impact of the various COVID-19 protocols.