Event Detection on Roads Using Perceptual Video Summarization

Thomas, Sinnu Susan; Gupta, Sumana; Subramanian, V.

doi:10.1109/tits.2017.2769719

Cited by 45 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Total Vehicles feature is the number of bounding boxes provided by the vehicle detector and evaluated for each video frame [10,13,20,21,24,38,39,40,41,42,43].…”

Section: Methodsmentioning

confidence: 99%

“…In the research of Avinash et al [20], Multiple Linear Regression (MLR) Technique was adopted to comprehend the factors influencing pedestrian safety. Koganti et al [21] adopted Lane Distribution Factor (LDF) to describe the distribution of vehicular traffic across the roadway. Thomas et al [22] presented a perceptual video summarization technique on a stack of videos to solve accident detection.…”

Section: Related Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Vehicular Traffic Congestion Classification by Visual Features and Deep Learning Approaches: A Comparison

Impedovo

Balducci

Dentamaro

et al. 2019

Sensors

View full text Add to dashboard Cite

Automatic traffic flow classification is useful to reveal road congestions and accidents. Nowadays, roads and highways are equipped with a huge amount of surveillance cameras, which can be used for real-time vehicle identification, and thus providing traffic flow estimation. This research provides a comparative analysis of state-of-the-art object detectors, visual features, and classification models useful to implement traffic state estimations. More specifically, three different object detectors are compared to identify vehicles. Four machine learning techniques are successively employed to explore five visual features for classification aims. These classic machine learning approaches are compared with the deep learning techniques. This research demonstrates that, when methods and resources are properly implemented and tested, results are very encouraging for both methods, but the deep learning method is the most accurately performing one reaching an accuracy of 99.9% for binary traffic state classification and 98.6% for multiclass classification.

show abstract

“…The Total Vehicles feature is the number of bounding boxes provided by the vehicle detector and evaluated for each video frame [10,13,20,21,24,38,39,40,41,42,43].…”

Section: Methodsmentioning

confidence: 99%

Section: Related Studiesmentioning

confidence: 99%

Vehicular Traffic Congestion Classification by Visual Features and Deep Learning Approaches: A Comparison

Impedovo

Balducci

Dentamaro

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Summarisation frameworks using object motion analysis for surveillance videos is discussed in this section. Thomas et al [3] designs a novel stage in the surveillance video summarisation which is an accident stage study with the type of collision. Accident detection is performed from a stack of videos using optimization problem and submodularity.…”

Section: Surveillance Video Summarisation Frameworkmentioning

confidence: 99%

An aggregated deep convolutional recurrent model for event based surveillance video summarisation: A supervised approach

Sreeja

Kovoor

2021

IET Computer Vision

View full text Add to dashboard Cite

Surveillance video summarisation is characterised by extracting video segments containing abnormal events from surveillance video footages. Accurate identification of abnormal events from surveillance footages is of paramount importance in surveillance video summarisation. Accordingly, the proposed framework builds an aggregated convolutional recurrent model that can precisely detect the suspicious events in a surveillance footage, by employing a supervised learning which is found to yield better results compared with unsupervised counterparts. The preliminary stage in the model is a multilayer Convolutional Neural Network for frame-level feature extraction followed by stacked bidirectional Gated Recurrent Unit for sequence-level feature extraction and classification. Since the video clips used for training are not implicit to surveillance, a block-based approach for testing on surveillance videos is proposed. The results evaluated on two custom datasets, Streets and Campus, prove that the proposed model produces remarkable results leveraging the properties of bidirectional GRU with supervised learning. Extensive experimental analysis on selection of optimum architecture is conducted which substantiates the significance of stacked bidirectional GRUs over unidirectional ones. Additionally, qualitative results ensure that summaries produced are concise, representative, complete, diverse and informative. Moreover, comparison of the performance of the proposed model with state of the art certainly proves the superiority of the proposed model.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…about 20 to 50 million of people are suffering of a non-fatal injury but incurring a disability because of their injuries [1]. Many researchers' discuses road traffic and death rates from many prospective [2][3][4][5][6][7]. Traffic death rate can be decreased if injured persons reach at hospital in the proper time.…”

Section: Introductionmentioning

confidence: 99%

Smart ambulance using IoT for blood transfer facilities

Torad¹,

Hossamel-din²

2021

IJEECS

View full text Add to dashboard Cite

<span>In case of an accident occurrence, ambulance try to transport wounded and injured people to the nearest hospital, but if the injured persons need an urgent blood transfer, the emergency reception (ER) can check the availability of the needed blood type and quantity. If it is available, the emergency reception accepts the injured person, but if it is not available, the reception reroutes the ambulance to the nearest hospital which have the required blood type and quantity. So, a system created that save that wasted time to save injured people life as possible. So, we create a system that save that wasted time to save injured people life as possible. So, the main contribution in this paper is selecting and determining the nearest hospital that own the proper blood types to save injurjed people lives using dijkstra algorithm. In this study, we use an android application at the ambulance which permit the paramedic to login and select the required blood type and quantity needed after determining the injured person’s blood type and the android application automatically determine the nearest hospital using the best shortest path algorithm (SPA) after checking the database and generate a pin code for the paramedic to deliver it with injured person to the ER and get the needed blood. This process will consequently decrease the used blood quantity from the database.</span>

show abstract

Event Detection on Roads Using Perceptual Video Summarization

Cited by 45 publications

References 27 publications

Vehicular Traffic Congestion Classification by Visual Features and Deep Learning Approaches: A Comparison

Vehicular Traffic Congestion Classification by Visual Features and Deep Learning Approaches: A Comparison

An aggregated deep convolutional recurrent model for event based surveillance video summarisation: A supervised approach

Smart ambulance using IoT for blood transfer facilities

Contact Info

Product

Resources

About