Real Time Video Analytics Based on Deep Learning and Big Data for Smart Station

Hidayat, Fadhil; Hamami, Faqih; Dahlan, Iqbal Ahmad; Supangkat, Suhono Harso; Fadillah, Amar; Hidayatuloh, Akbar

doi:10.1088/1742-6596/1577/1/012019

Cited by 8 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The device will emit a sound indicating that social distancing is necessary. These previous works [13], [14], [16] have identified how to present improving technologies such as CCTV surveillance with AI in the railway area case. The previous research discusses algorithms, architecture, concepts, and deployments for social distancing monitoring guidelines.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…This research proposed a system to solve the social distancing aspect in public using CCTV analytics and deep learning algorithms, especially convolutional neural networks (CNN), which is also supported by the data integration using MongoDB to collect and store the data that has been processed [13], [14], [16]. The following research can be improved by big data technology such as Hadoop, Kafka, Cassandra, and another data engine to enhance the data transmission.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time passenger social distance monitoring with video analytics using deep learning in railway station

Dahlan

Putra

Supangkat

et al. 2022

IJEECS

View full text Add to dashboard Cite

<span lang="EN-US">Recently, at the end of December, the world faced a severe problem which is a pandemic that is caused by coronavirus disease. It also must be considered by the railway station's authorities that it must have the capability of reducing the covid transmission risk in the pandemic condition. Like a railway station, public transport plays a vital role in managing the COVID-19 spread because it is a center of public mass transportation that can be associated with the acquisition of infectious diseases. This paper implements social distance monitoring with a YOLOv4 object detection model for crowd monitoring using standard CCTV cameras to track visitors using the DeepSORT algorithm. This paper used CCTV surveillance with the actual implementation in Bandung Railway Station with the accuracy at 96.5 % result on people tracking with tested in real-time processing by using minicomputer Intel(R) Xeon(R) CPU E3-1231 v3 3.40GHz RAM 6 GB around at 18 FPS.</span>

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-time passenger social distance monitoring with video analytics using deep learning in railway station

Dahlan

Putra

Supangkat

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…Video analytics has become an active research field in image and video processing [1]. Human Activity Recognition (HAR) applications are mainly categorized into active and assisted living, healthcare monitoring, surveillance systems, and tele-immersion.…”

Section: Introductionmentioning

confidence: 99%

SADY: Student Activity Detection Using YOLO-based Deep Learning Approach

Deshpande,

Warhade

2023

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Automating human activity recognition is one of computer vision's most appealing and pragmatic research areas. In this article, we have addressed the problem of video-based student activity detection. The studentâ€™s activity detection using YOLO (SADY) aims to recognize the normal and abnormal student activities to ensure immediate intervention in case of any risk or necessity. We created our classroom data set of around 220 recordings depicting seven student classroom activities. The YOLOv4 Tiny model was retrained using 5000 labeled keyframes extracted from the train videos. The model was then tested for single or multiple activity detections. We presented the evaluated results for various values of hyperparameters like confidence threshold and Intersection Over Union (IoU) thresholds for the proposed model. The model assigns a unique confidence score and action label to each frame for the test videos by positioning recurrent activity labels. The proposed approach achieved a mean average precision (mAP) of 95% and a frame per second rate (FPS) of 45 for the student activity Class Room (CR) dataset and mAP of 95.18 % for the LIRIS dataset. The experimental findings using the Class Room recorded and LIRIS publicly accessible dataset show that our proposed approach outperforms existing approaches regarding recognition accuracy and speed. The comparable results obtained in this research work imply that the proposed framework could effectively monitor studentâ€™s activities in schools, colleges, and universities.

show abstract

“…The video is then compressed to be stored and sent with minimal resources. At the same time, the ROIs are subjected to a scrambling process (Hidayat et al 2020). Consequently, the persons in the scene are unrecognizable, but the background is unobscured, solving the problem of invasion of privacy.…”

Section: Introductionmentioning

confidence: 99%

Smart evaluation of videos for unusual-event identification in automated vehicle monitoring systems

Yadav,

Sharma,

Ojha

2023

Multidiscip. Sci. J.

View full text Add to dashboard Cite

Many methods have been tried to perfect vehicle recognition, which includes quickly locating the same objects in cameras with different sensor types and perhaps propagating trustworthy information across cameras to improve detection. In this study, we look at various important issues and provide a new method for spotting certain abnormalities. We suggest an automated vehicle monitoring system (AVMS) to enhance detection accuracy. If the current reading from a certain local monitor is out of the ordinary, that monitor will issue a notification, and all of those alerts will go toward deciding whether or not an abnormal event has occurred. The effective implementation of any large-scale surveillance system relies on our algorithm meeting several parameters. It simply takes a few minutes to set up and is completely hands-free. The experimental findings demonstrate the effectiveness and simplicity of the suggested approach, with the assembled image quality being on the level with that of state-of-the-art techniques.

show abstract

Real Time Video Analytics Based on Deep Learning and Big Data for Smart Station

Cited by 8 publications

References 2 publications

Real-time passenger social distance monitoring with video analytics using deep learning in railway station

Real-time passenger social distance monitoring with video analytics using deep learning in railway station

SADY: Student Activity Detection Using YOLO-based Deep Learning Approach

Smart evaluation of videos for unusual-event identification in automated vehicle monitoring systems

Contact Info

Product

Resources

About