Detection and classification of vehicles for traffic video analytics

Arinaldi, Ahmad; Pradana, Jaka Arya; Gurusinga, Arlan Arventa

doi:10.1016/j.procs.2018.10.527

Cited by 113 publications

(52 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Arinaldi et al [30] exploited the computer vision technique for identifying and classifying vehicles from the observed traffic videos. The computer vision technique relies on a recurrent convolution neural network for estimating the properties of the road and vehicle density.…”

Section: Related Workmentioning

confidence: 99%

CMRS: A Classifier Matrix Recognition System for Traffic Management and Analysis in a Smart City Environment

et al. 2019

View full text Add to dashboard Cite

The application of the Internet of Things (IoT) in a smart city improves its efficiency in terms of communication and installation costs by scaling geographical distance through intelligent devices and digital information. Different applications in a smart city, including health care, road safety, industry and home automation, rely on the IoT. Considering the significance of the IoT in smart city road applications, this manuscript introduces a classifier matrix recognition system (CMRS) for improving realtime traffic optimization. This classifier matrix system performs an independent and matching analysis of the real-time traffic images and constructs a decision factor for deriving its conclusion. The conclusion is served as responding notifications through the connected IoT systems for the users employing roadsidecommunication-assisted applications. CMRS exploits the advantages of block classification and matrix operations for improving the correlation accuracy and similarity index. The experimental results indicate that the proposed CMRS improves correlation accuracy with a high similarity index and less processing time and dissimilarity rate. INDEX TERMS Block classification, image recognition, IoT, ITS, smart city, traffic management. I. INTRODUCTION The rapid development of the IoT is resulting in its services being used in different real-world applications. This communication platform is capable of connecting various elements, including humans, computers, machines, tiny sensors and other objects [1], [2]. More specifically, the connected devices are heterogeneous in nature, which facilitates pervasive access to resources, applications and services [3], [4]. The intelligence of the communicating devices in this paradigm provides anywhere and anytime access to resources the end user requests [5]. Because the interconnection of this platform incorporates heterogeneous devices, it supports various communication technologies ranging from device-todevice (D2D) to distributed cloud computing [6]. The independent operations of the devices are assisted via a wireless communication medium in which the protocol and technology are adopted appropriately. Distributed and concurrent The associate editor coordinating the review of this manuscript and approving it for publication was Chao Chen.

show abstract

Section: Related Workmentioning

confidence: 99%

CMRS: A Classifier Matrix Recognition System for Traffic Management and Analysis in a Smart City Environment

et al. 2019

View full text Add to dashboard Cite

show abstract

“…It is also same as Machine Learning, as part of a broader family of machine learning methods based on artificial neural networks. Currently, Deep Learning with a convolutional architecture (CNN) have emerged as a popular method for solving problems related to visual object recognition either in images or videos and has given the state of the art performance in various optical recognition tasks, such as image classification, object detection and localisation and image segmentation [16]. Learning can be supervised, semi supervised or unsupervised.…”

Section: Deep Learningmentioning

confidence: 99%

“…It can reduce the count of bounding box. These region proposals are then warped using an affine transform into 227x227 size images, that are then fed into a pre-trained neural network [19]. Instead of…”

Section: B Rcnnmentioning

confidence: 99%

See 1 more Smart Citation

Various Methods for Object Detection Based on Deep Learning

Scaria*,

V V

2019

IJRTE

View full text Add to dashboard Cite

The growing technology in the world made-up the deep learning method, which classifies different vehicles from a video. In deep learning technology use different strategies such as RCNN, Fast RCNN, RPN, faster RCNN, YOLO, SSD. All methods offer various accuracy of the identification of the vehicle. The convolutional natural network determining an object detection task exploitation in deep learning. Object detection is very important in AI as well as in videos using pc vision. Through this paper demystifies the important role of deep learning supported by CNN for object detection. And the methodology offers additional correct result. Deep learning techniques shows the development of object detection in various area and the different technics are assessed during this paper.

show abstract

“…This system extracts the feature from the satellite image through CNN using the satellite image as an input value and performs the binary classification with SVM to detect the vehicle BBox. Besides, Arinaldi, Pradana, and Gurusinga [3] developed a system to estimate the speed of the vehicle, classify vehicle type, and analyze traffic volume. This system utilizes BBox obtained by object detection based on videos or images.…”

Section: Introductionmentioning

confidence: 99%

An Application of a Deep Learning Algorithm for Automatic Detection of Unexpected Accidents Under Bad CCTV Monitoring Conditions in Tunnels

Lee

Shin

2019

2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-Ml)

View full text Add to dashboard Cite

In this paper, Object Detection and Tracking System (ODTS) in combination with a well-known deep learning network, Faster Regional Convolution Neural Network (Faster R-CNN), for Object Detection and Conventional Object Tracking algorithm will be introduced and applied for automatic detection and monitoring of unexpected events on CCTVs in tunnels, which are likely to (1) Wrong-Way Driving (WWD), (2) Stop, (3) Person out of vehicle in tunnel (4) Fire. ODTS accepts a video frame in time as an input to obtain Bounding Box (BBox) results by Object Detection and compares the BBoxs of the current and previous video frames to assign a unique ID number to each moving and detected object. This system makes it possible to track a moving object in time, which is not usual to be achieved in conventional object detection frameworks. A deep learning model in ODTS was trained with a dataset of event images in tunnels to Average Precision (AP) values of 0.8479, 0.7161 and 0.9085 for target objects: Car, Person, and Fire, respectively. Then, based on trained deep learning model, the ODTS based Tunnel CCTV Accident Detection System was tested using four accident videos which including each accident. As a result, the system can detect all accidents within 10 seconds. The more important point is that the detection capacity of ODTS could be enhanced automatically without any changes in the program codes as the training dataset becomes rich.

show abstract

Detection and classification of vehicles for traffic video analytics

Cited by 113 publications

References 17 publications

CMRS: A Classifier Matrix Recognition System for Traffic Management and Analysis in a Smart City Environment

CMRS: A Classifier Matrix Recognition System for Traffic Management and Analysis in a Smart City Environment

Various Methods for Object Detection Based on Deep Learning

An Application of a Deep Learning Algorithm for Automatic Detection of Unexpected Accidents Under Bad CCTV Monitoring Conditions in Tunnels

Contact Info

Product

Resources

About