Comparative analysis of identification of dynamic objects by scale-invariant feature transform and deep neural networks

Ivliev, Evgeniy; Obukhov, Pavel

doi:10.1088/1757-899x/1029/1/012085

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the article [2], the authors consider the methods of localization of the baggage tag and identification of the digit-letter information of the IATA airport code. A system for identifying information from a baggage tag based on several neural networks with the SSD InceptionV2 architecture has been developed.…”

Section: Review Literature and Associated Workmentioning

confidence: 99%

Improving the energy efficiency of sorting centers by identifying objects and digit-letter information with neural networks

et al. 2021

View full text Add to dashboard Cite

The article is devoted to the development and analysis of methods of identifying dynamic objects. A neural network with the architecture of SSD MobileNetV2 has been developed to solve the problem of detecting baggage tags and barcodes. Several approaches are considered to solve the problem of identifying digital-letter information: Tesseract, SSD InceptionV2, OpenCV and a convolutional neural network. The efficiency of the methods on real images was checked. It was concluded that electricity consumption can be reduced by 49.43%.

show abstract

Section: Review Literature and Associated Workmentioning

confidence: 99%

Improving the energy efficiency of sorting centers by identifying objects and digit-letter information with neural networks

et al. 2021

View full text Add to dashboard Cite

show abstract

Cognitive system for analysis behavioral of dynamic objects of video surveillance

Marshakov

Fathi

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The necessary measures to ensure the safety of technical structures, freight/passenger stations and other transport infrastructure facilities include continuous video monitoring with a comprehensive analysis of the scene. In conditions of high density of numerous objects continuously moving through the observation area, one of the main available signs of detecting anomalies in their behavior is their trajectory of the object. In this paper, we propose an approach to building a system for analyzing the behavior of dynamic video surveillance objects based on their tracking, implemented by means of cognitive modeling. The proposed procedures for intelligent analysis of the nature of movement of video surveillance objects are based on a combination of neural network technologies and the logical inference mechanism of the expert system, which expands the basic algorithms for technical equipment of video surveillance systems. The practical significance of the considered solutions is to increase the efficiency of detecting suspicious situations in conditions of high traffic density by conducting a parallel analysis of the movement of numerous objects of the scene, which entails the prevention of possible illegal actions in places of mass presence of people, including transport infrastructure facilities.

show abstract

Comparative analysis of identification of dynamic objects by scale-invariant feature transform and deep neural networks

Cited by 2 publications

References 2 publications

Improving the energy efficiency of sorting centers by identifying objects and digit-letter information with neural networks

Improving the energy efficiency of sorting centers by identifying objects and digit-letter information with neural networks

Cognitive system for analysis behavioral of dynamic objects of video surveillance

Contact Info

Product

Resources

About