Browsing by Author "Kumar, P.V."

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    A Survey on Semantic Segmentation Models for Underwater Images
    (Springer, 2023) Anand, S.K.; Kumar, P.V.; Saji, R.; Gadagkar, A.V.; Chandavarkar, B.R.
    Semantic segmentation remains a key research field in modern day computer vision and has been used in a myriad of applications across various fields. It can be extremely beneficial in the study of underwater scenes. Various underwater applications, such as unmanned explorations and autonomous underwater vehicles, require accurate object classification and detection to allow the probes to avoid malicious objects. However, the models that work well for terrestrial images rarely work just as well for underwater images. This is because underwater images suffer from high blue light intensity as well as other ill effects such as poor lighting and contrast. This can be fixed using preprocessing techniques to manually improve the image characteristics. Trying to improve the model to account for bad image quality is not a great method as the model may misidentify noise as an image characteristic. In this chapter, 6 different deep learning semantic segmentation models—SegNet, Pyramid Scene Parsing Network (PSP-Net), U-Net, DNN-VGG (Deep Neural Network-VGG), DeepLabv3+, and SUIM-Net—are explored. Their architectures, technical aspects with respect to underwater images, advantages, and disadvantages are all investigated. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
  • No Thumbnail Available
    Item
    Comparative Analysis of Modern Mobile Operating Systems
    (Institute of Electrical and Electronics Engineers Inc., 2021) Chandrashekar, A.; Kumar, P.V.; Chandavarkar, B.R.
    The importance of smartphones has grown exponentially since their emergence. Smartphones have fundamentally modified the way people live by allowing them to easily access information and communicate with one another. With this meteoric rise, the operating systems run by these mobile devices have also come a long way in terms of their functionalities and their features. The operating system plays a vital and essential role in the use of these devices and cannot be overlooked. The operating system acts as the foundation of the device. The quality of the operating system directly impacts the quality of the device and also determines the usability of the device. A wide range of mobile operating systems, each with its own set of characteristics and features, currently exist in the market. This paper looks into some of the popular operating systems used in mobile devices and aims to compare and evaluate their different characteristics like architecture, security, and other attributes. This paper also analyzes a few of the advantages and disadvantages of these operating systems. © 2021 IEEE.
  • No Thumbnail Available
    Item
    Machine Learning Based Data Quality Model for COVID-19 Related Big Data
    (Springer Science and Business Media Deutschland GmbH, 2022) Kumar, P.V.; Chandrashekar, A.; Chandrasekaran, K.
    Big Data is being used in various aspects of technology. The quality of the data being used is essential and needs to be accurate, reliable, and free of defects. The difficulty in improving the quality of big data can be overcome by leveraging computing resources and advanced techniques. In this paper, we propose a solution that utilizes a machine learning (ML) model combined with a data quality model to improve the quality of data. An auto encoder neural network that detects the anomalies in the data is used as the Machine Learning model. This is followed by using the data quality model to ensure the data meets appropriate data quality characteristics. The results obtained from our solution show that the quality of data can be improved efficiently and effortlessly which in turn aids researchers to achieve better results. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Semantic Segmentation of Underwater Images with CNN Based Adaptive Thresholding
    (Springer Science and Business Media Deutschland GmbH, 2025) Anand, S.K.; Kumar, P.V.; Saji, R.; Gadagkar, A.V.; Chandavarkar, B.R.
    Semantic segmentation remains a key research field in modern day computer vision and has been used in a myriad of applications across various fields. It can be extremely beneficial in the study of underwater scenes. Various underwater applications, like unmanned explorations and autonomous underwater vehicles, require accurate object classification and detection to allow the probes to avoid malicious objects. However, the models which work well for terrestrial images rarely work just as well for underwater images. This is because underwater images suffer from high blue light intensity as well as other ill-effects such as poor lighting and contrast. Trying to improve the model to account for bad image quality is not a great method as the model may misidentify noise as an image characteristic. In this paper, a unique CNN-based approach for post-processing image thresholding is proposed, on top of 3 models used for the semantic segmentation itself–Segnet, U-Net, and Deeplabv3+. The models’ outputs are then subject to the CNN-based post-processing technique to binarize the outputs into masks, and provides improved segmentation results compared to the base models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.