• Home
  • Search
  • Viewpoint Selection for DermDrone using Deep Reinforcement Learning
  • Cite Icon3
  • https://doi.org/10.23919/iccas52745.2021.9649799Copy DOI Icon

Viewpoint Selection for DermDrone using Deep Reinforcement Learning

  • Oct 12, 2021
  • Mojtaba Ahangar Arzati +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper presents an RL-based method to improve the performance of real-time 3D human pose estimation as a positioning feedback for DermDrone which is a micro sized quadrotor designed MetaOptima to capture high resolution full body images for dermatology application. The camera viewpoint is identified as the key parameter in the accuracy of monocular 3D human pose estimation. We present a deep reinforcement learning based method for determining the best viewpoint given the flight trajectory. Our goal is to present a reliable and accurate positioning feedback for DermDrone using a 3D human pose estimation algorithm. DQN and its variants (Double DQN, and Dueling DQN) were employed and their performances were investigated by conducting several simulations. The results confirm that RL-based viewpoint selection improve the performance of 3D human pose estimation.

Similar Papers
  • Research Article
  • Citations26

Markerless multi-view 3D human pose estimation: A survey

  • Mar 01, 2025
  • Image and Vision Computing
  • Ana Filipa Rodrigues Nogueira +2
  • Research Article
  • Citations52

Boosting Monocular 3D Human Pose Estimation With Part Aware Attention.

  • Jan 01, 2022
  • IEEE Transactions on Image Processing
  • Youze Xue +4
  • Conference Article
  • Citations42

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

  • Jun 01, 2020
  • Sena Kiciroglu +4
  • Research Article

Cross-Constrained Progressive Inference for 3D Hand Pose Estimation with Dynamic Observer-Decision-Adjuster Networks

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zhehan Kan +4
  • Research Article
  • Citations381

Deep 3D human pose estimation: A review

  • May 24, 2021
  • Computer Vision and Image Understanding
  • Jinbao Wang +6
  • Research Article
  • Citations31

Weakly-supervised pre-training for 3D human pose estimation via perspective knowledge

  • Mar 05, 2023
  • Pattern Recognition
  • Zhongwei Qiu +3
  • Research Article
  • Citations1

Local-Global Feature Fusion for Enhancing 3D Human Pose Estimation

  • Jan 01, 2025
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Yuanhong Zhong +5
  • Conference Article
  • Citations3

Monocular 3D human pose estimation by classification

  • Jul 01, 2011
  • Thomas Greif +2
  • Book Chapter
  • Citations6

Anatomy and Geometry Constrained One-Stage Framework for 3D Human Pose Estimation

  • Jan 01, 2021
  • Xin Cao +1
  • Research Article
  • Citations2

3차원 발 자세 추정을 위한 새로운 형상 기술자

  • Feb 27, 2010
  • The Journal of the Korean Institute of Information and Communication Engineering
  • Ho-Geun Song +3
  • Conference Article
  • Citations135

Iterated Second-Order Label Sensitive Pooling for 3D Human Pose Estimation

  • Jun 01, 2014
  • Catalin Ionescu +2
  • Video Transcripts

On the Robustness of 3D Human Pose Estimation

  • Dec 29, 2020
  • Underline Science Inc.
  • Yan Huang +2
  • Conference Article
  • Citations4

Sparse representation and convolutional neural networks for 3D human pose estimation

  • Dec 01, 2017
  • Hassan Alikarami +2
  • Research Article

Modified-EfficientPose: Modifying the Prediction Network of the EfficientPose Method to Improve 6D Pose Estimation Performance

  • May 10, 2025
  • Nusantara Science and Technology Proceedings
  • Budi Nugroho +1
  • Conference Article
  • Citations12

COPE: End-to-end trainable Constant Runtime Object Pose Estimation

  • Jan 01, 2023
  • Stefan Thalhammer +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.