IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v14y2022i4p2420-d753915.html
   My bibliography  Save this article

Deep Learning Method for Recognition and Classification of Images from Video Recorders in Difficult Weather Conditions

Author

Listed:
  • Aleksey Osipov

    (Information Security Department, Financial University under the Government of the Russian Federation, 4-th Veshnyakovsky Passage, 4, 109456 Moscow, Russia)

  • Ekaterina Pleshakova

    (Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 4-th Veshnyakovsky Passage, 4, 109456 Moscow, Russia)

  • Sergey Gataullin

    (Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 4-th Veshnyakovsky Passage, 4, 109456 Moscow, Russia)

  • Sergey Korchagin

    (Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 4-th Veshnyakovsky Passage, 4, 109456 Moscow, Russia)

  • Mikhail Ivanov

    (Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation, 4-th Veshnyakovsky Passage, 4, 109456 Moscow, Russia)

  • Anton Finogeev

    (CAD Department, Penza State University, 440026 Penza, Russia)

  • Vibhash Yadav

    (Department of Information Technology, Rajkiya Engineering College, Atarra, Banda 210201, India)

Abstract

The sustainable functioning of the transport system requires solving the problems of identifying and classifying road users in order to predict the likelihood of accidents and prevent abnormal or emergency situations. The emergence of unmanned vehicles on urban highways significantly increases the risks of such events. To improve road safety, intelligent transport systems, embedded computer vision systems, video surveillance systems, and photo radar systems are used. The main problem is the recognition and classification of objects and critical events in difficult weather conditions. For example, water drops, snow, dust, and dirt on camera lenses make images less accurate in object identification, license plate recognition, vehicle trajectory detection, etc. Part of the image is overlapped, distorted, or blurred. The article proposes a way to improve the accuracy of object identification by using the Canny operator to exclude the damaged areas of the image from consideration by capturing the clear parts of objects and ignoring the blurry ones. Only those parts of the image where this operator has detected the boundaries of the objects are subjected to further processing. To classify images by the remaining whole parts, we propose using a combined approach that includes the histogram-oriented gradient (HOG) method, a bag-of-visual-words (BoVW), and a back propagation neural network (BPNN). For the binary classification of the images of the damaged objects, this method showed a significant advantage over the classical method of convolutional neural networks (CNNs) (79 and 65% accuracies, respectively). The article also presents the results of a multiclass classification of the recognition objects on the basis of the damaged images, with an accuracy spread of 71 to 86%.

Suggested Citation

  • Aleksey Osipov & Ekaterina Pleshakova & Sergey Gataullin & Sergey Korchagin & Mikhail Ivanov & Anton Finogeev & Vibhash Yadav, 2022. "Deep Learning Method for Recognition and Classification of Images from Video Recorders in Difficult Weather Conditions," Sustainability, MDPI, vol. 14(4), pages 1-16, February.
    • Handle: RePEc:gam:jsusta:v:14:y:2022:i:4:p:2420-:d:753915
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/14/4/2420/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2071-1050/14/4/2420/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Oleg Krakhmalev & Sergey Korchagin & Ekaterina Pleshakova & Petr Nikitin & Oksana Tsibizova & Irina Sycheva & Kang Liang & Denis Serdechnyy & Sergey Gataullin & Nikita Krakhmalev, 2021. "Parallel Computational Algorithm for Object-Oriented Modeling of Manipulation Robots," Mathematics, MDPI, vol. 9(22), pages 1-12, November.
    2. Antonios Kolimenakis & Alexandra D. Solomou & Nikolaos Proutsos & Evangelia V. Avramidou & Evangelia Korakaki & Georgios Karetsos & Georgios Maroulis & Eleftherios Papagiannis & Konstantinia Tsagkari, 2021. "The Socioeconomic Welfare of Urban Green Areas and Parks; A Literature Review of Available Evidence," Sustainability, MDPI, vol. 13(14), pages 1-26, July.
    3. Wei, Yun & Tian, Qing & Guo, Jianhua & Huang, Wei & Cao, Jinde, 2019. "Multi-vehicle detection algorithm through combining Harr and HOG features," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 155(C), pages 130-145.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Jiale Yao & Dengsheng Cai & Xiangsuo Fan & Bing Li, 2022. "Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism," Mathematics, MDPI, vol. 10(9), pages 1-20, April.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Van Oijstaeijen, Wito & Van Passel, Steven & Back, Phil & Cools, Jan, 2022. "The politics of green infrastructure: A discrete choice experiment with Flemish local decision-makers," Ecological Economics, Elsevier, vol. 199(C).
    2. Junran Lin & Cuimei Yang & Yi Lu & Yuxing Cai & Hanjie Zhan & Zhen Zhang, 2022. "An Improved Soft-YOLOX for Garbage Quantity Identification," Mathematics, MDPI, vol. 10(15), pages 1-12, July.
    3. Chorong Song & Harumi Ikei & Yoshifumi Miyazaki, 2022. "Seasonal Differences in Physiological Responses to Walking in Urban Parks," IJERPH, MDPI, vol. 19(19), pages 1-9, September.
    4. Antonios Kolimenakis & Alexandra D. Solomou & Nikolaos Proutsos & Evangelia V. Avramidou & Evangelia Korakaki & Georgios Karetsos & Aimilia B. Kontogianni & Konstantinos Kontos & Christos Georgiadis &, 2022. "Public Perceptions of the Socioeconomic Importance of Urban Green Areas in the Era of COVID-19: A Case Study of a Nationwide Survey in Greece," Land, MDPI, vol. 11(12), pages 1-14, December.
    5. Lamthai Asanok & Torlarp Kamyo & Monthon Norsaengsri & Teeka Yotapakdee & Suwit Navakam, 2021. "Assessment of the Diversity of Large Tree Species in Rapidly Urbanizing Areas along the Chao Phraya River Rim, Central Thailand," Sustainability, MDPI, vol. 13(18), pages 1-13, September.
    6. Zakharov, Konstantin & Mizgajski, Andrzej, 2024. "Socioeconomic and political settings for the land development decreasing urban green. Inside view from Moscow," Land Use Policy, Elsevier, vol. 141(C).
    7. Nikolaos D. Proutsos & Alexandra D. Solomou & Michaela Petropoulou & Nikolaos E. Chatzipavlis, 2022. "Micrometeorological and Hydraulic Properties of an Urban Green Space on a Warm Summer Day in a Mediterranean City (Attica–Greece)," Land, MDPI, vol. 11(11), pages 1-16, November.
    8. Jing, Shaoxue, 2023. "Time-delay Hammerstein system identification using modified cross-correlation method and variable stacking length multi-error algorithm," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 207(C), pages 288-300.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:14:y:2022:i:4:p:2420-:d:753915. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.