MSRP-TODNet: a multi-scale reinforced region wise analyser for tiny object detection.

Journal: BMC research notes
Published Date:

Abstract

OBJECTIVE: Detecting small, faraway objects in real-time surveillance is challenging due to limited pixel representation, affecting classifier performance. Deep Learning (DL) techniques generate feature maps to enhance detection, but conventional methods suffer from high computational costs. To address this, we propose Multi-Scale Region-wise Pixel Analysis with GAN for Tiny Object Detection (MSRP-TODNet). The model is trained and tested on VisDrone VID 2019 and MS-COCO datasets. First, images undergo two-fold pre-processing using Improved Wiener Filter (IWF) for artifact removal and Adjusted Contrast Enhancement Method (ACEM) for blurring correction. The Multi-Agent Reinforcement Learning (MARL) algorithm splits the pre-processed image into four regions, analyzing each pixel to generate feature maps. These are processed by the Enhanced Feature Pyramid Network (EFPN), which merges them into a single feature map. Finally, a Generative Adversarial Network (GAN) detects objects with bounding boxes.

Authors

  • Thulasi Bikku
    Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Amaravati, Andhra Pradesh, 522503, India.
  • K P N V Satya Sree
    Department of Computer Science and Engineering, Usha Rama College of Engineering and Technology, Telaprolu, India.
  • Srinivasarao Thota
    Department of Mathematics, Amrita School of Physical Sciences, Amrita Vishwa Vidyapeetham, Amaravati, Andhra Pradesh, 522503, India.
  • Malligunta Kiran Kumar
    Department of Electrical and Electronics Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India.
  • P Shanmugasundaram
    Department of Mathematics, College of Natural and Computational Science, Mizan-Tepi University, Tepi, Ethiopia. psserode@mtu.edu.et.