Traffic Monitoring Using Video Analytics in Clouds

Abdullah, Tariq; Anjum, Ashiq; Tariq, Muhammad; Baltaci, Yusuf; Antonopoulos, Nick

doi:10.1109/ucc.2014.12

Cited by 34 publications

(18 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thirdly, achieve high accuracy in object detection and classification during the video analysis process. This work is an extended version of our previous work [10].…”

Section: Classification High Performancementioning

confidence: 97%

Framework of Object Detection and Classification High Performance Using Video Analytics in Cloud

bharathy¹

2018

IJTSRD

View full text Add to dashboard Cite

Video analytics framework detection performance is worked at cloud. Object detection and classification are the basic tasks in video analytics and become initial point for other complex submissions. Old fashioned video analytics approaches are manual and time consuming. These are particular due to the very participation of human factor. This paper present a cloud based video analytics framework for acc and robust analysis of video streams. The framework enables an operative by programing the object detection and classification process from recorded video streams. An operative only specifies an analysis criteria and period of video streams to anal streams are then realized from cloud storage, cracked and analyzed on the cloud. The framework performs compute severe parts of the analysis to CPU powered servers in the cloud. Vehicle and face finding are accessible as two case studies for asses framework, with one month of data and a 15 node cloud. The framework consistently performed object detection and classification on the data, comprising of 21,600 video streams and 175 GB in size, in 6.52 hours. The GPU enabled placement of the fra took 3 hours to perform analysis on the same number of video streams, thus making it at least double as fast than the cloud deployment Without GPUs. The analysis framework is high.

show abstract

“…Thirdly, achieve high accuracy in object detection and classification during the video analysis process. This work is an extended version of our previous work [10].…”

Section: Classification High Performancementioning

confidence: 97%

Framework of Object Detection and Classification High Performance Using Video Analytics in Cloud

bharathy¹

2018

IJTSRD

View full text Add to dashboard Cite

show abstract

“…Another Hadoop-based video analytics solution is given in [10] that speedup the demonstrated video using multiple small video files. Although the method in [9] also splits a single video file for parallel processing, it does not effectively utilize the Map and Reduce phases of MapReduce for the video processing operations. Instead of utilizing the Map phase for parallelizing the operations a single map task for splitting a video file is used and Reduce phase for video processing operations.…”

Section: Background Studymentioning

confidence: 99%

Survey on Multiple Objects Tracking in Video Analytics

Parihar¹,

Nagarkar²,

Bhosale³

et al. 2019

IJCA

View full text Add to dashboard Cite

Multiple object tracking is being used for many applications nowdays such as automated surveillance, Robotics,self driving cars,medical and many more. There have been continuous improvements in existing state of art MOT(multiple object tracking) methods through many methods and global optimization techniques.This paper focuses on various MOT techniques and how to achieve speedup and efficiency using MOT methods.

show abstract

“…A number of studies worked on multimodal features. They used hidden Markov models, Guassian density functions, and local pattern features in their system. Carrasco et al used a probabilistic fusion scheme to fuse the features from different modalities and then performed the classification.…”

Section: Related Workmentioning

confidence: 99%

Cloud‐based video analytics using convolutional neural networks

et al. 2018

Self Cite

View full text Add to dashboard Cite

Object classification is a vital part of any video analytics system, which could aid in complex applications such as object monitoring and management. Traditional video analytics systems work on shallow networks and are unable to harness the power of distributed processing for training and inference. We propose a cloud-based video analytics system based on an optimally tuned convolutional neural network to classify objects from video streams. The tuning of convolutional neural network is empowered by in-memory distributed computing. The object classification is performed by comparing the target object with the prestored trained patterns, generating a set of matching scores. The matching scores greater than an empirically determined threshold reveal the classification of the target object. The proposed system proved to be robust to classification errors with an accuracy and precision of 97% and 96%, respectively, and can be used as a general-purpose video analytics system.

show abstract

Traffic Monitoring Using Video Analytics in Clouds

Cited by 34 publications

References 17 publications

Framework of Object Detection and Classification High Performance Using Video Analytics in Cloud

Framework of Object Detection and Classification High Performance Using Video Analytics in Cloud

Survey on Multiple Objects Tracking in Video Analytics

Cloud‐based video analytics using convolutional neural networks

Contact Info

Product

Resources

About