LWIRPOSE: A novel LWIR Thermal Image Dataset and Benchmark

• URL: http://arxiv.org/abs/2404.10212v1
• Date: Tue, 16 Apr 2024 01:49:35 GMT
• Title: LWIRPOSE: A novel LWIR Thermal Image Dataset and Benchmark
• Authors: Avinash Upadhyay, Bhipanshu Dhupar, Manoj Sharma, Ankit Shukla, Ajith Abraham,
• Abstract summary: This dataset comprises over 2,400 high-quality LWIR (thermal) images. Each image is meticulously annotated with 2D human poses, offering a valuable resource for researchers and practitioners. We benchmark state-of-the-art pose estimation methods on the dataset to showcase its potential.
• Score: 9.679771580702258
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Human pose estimation faces hurdles in real-world applications due to factors like lighting changes, occlusions, and cluttered environments. We introduce a unique RGB-Thermal Nearly Paired and Annotated 2D Pose Dataset, comprising over 2,400 high-quality LWIR (thermal) images. Each image is meticulously annotated with 2D human poses, offering a valuable resource for researchers and practitioners. This dataset, captured from seven actors performing diverse everyday activities like sitting, eating, and walking, facilitates pose estimation on occlusion and other challenging scenarios. We benchmark state-of-the-art pose estimation methods on the dataset to showcase its potential, establishing a strong baseline for future research. Our results demonstrate the dataset's effectiveness in promoting advancements in pose estimation for various applications, including surveillance, healthcare, and sports analytics. The dataset and code are available at https://github.com/avinres/LWIRPOSE

Related papers

• LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment [59.320414108383055]
  We present LiveHPS, a novel single-LiDAR-based approach for scene-level human pose and shape estimation. We propose a huge human motion dataset, named FreeMotion, which is collected in various scenarios with diverse human poses.
  arXiv  Detail & Related papers  (2024-02-27T03:08:44Z)
• Multi-Modal Dataset Acquisition for Photometrically Challenging Object [56.30027922063559]
  This paper addresses the limitations of current datasets for 3D vision tasks in terms of accuracy, size, realism, and suitable imaging modalities for photometrically challenging objects. We propose a novel annotation and acquisition pipeline that enhances existing 3D perception and 6D object pose datasets.
  arXiv  Detail & Related papers  (2023-08-21T10:38:32Z)
• Improving 2D Human Pose Estimation in Rare Camera Views with Synthetic Data [24.63316659365843]
  We introduce RePoGen, an SMPL-based method for generating synthetic humans with comprehensive control over pose and view. Experiments on top-view datasets and a new dataset of real images with diverse poses show that adding the RePoGen data to the COCO dataset outperforms previous approaches.
  arXiv  Detail & Related papers  (2023-07-13T13:17:50Z)
• 6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark [17.493403705281008]
  We present a new dataset for 6-DoF pose estimation of known objects, with a focus on robotic manipulation research. We provide 3D scanned textured models of toy grocery objects, as well as RGBD images of the objects in challenging, cluttered scenes. Using semi-automated RGBD-to-model texture correspondences, the images are annotated with ground truth poses that were verified empirically to be accurate to within a few millimeters. We also propose a new pose evaluation metric called ADD-H based upon the Hungarian assignment algorithm that is robust to symmetries in object geometry without requiring their explicit enumeration.
  arXiv  Detail & Related papers  (2022-03-11T01:19:04Z)
• Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking [98.91894395941766]
  We propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame. Specifically, we derive this prediction of dynamics through a graph neural network(GNN) that explicitly accounts for both spatial-temporal and visual information. Experiments on PoseTrack 2017 and PoseTrack 2018 datasets demonstrate that the proposed method achieves results superior to the state of the art on both human pose estimation and tracking tasks.
  arXiv  Detail & Related papers  (2021-06-07T16:36:50Z)
• Salient Objects in Clutter [130.63976772770368]
  This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. We propose a new high-quality dataset and update the previous saliency benchmark.
  arXiv  Detail & Related papers  (2021-05-07T03:49:26Z)
• TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild [77.59069361196404]
  TRiPOD is a novel method for predicting body dynamics based on graph attentional networks. To incorporate a real-world challenge, we learn an indicator representing whether an estimated body joint is visible/invisible at each frame. Our evaluation shows that TRiPOD outperforms all prior work and state-of-the-art specifically designed for each of the trajectory and pose forecasting tasks.
  arXiv  Detail & Related papers  (2021-04-08T20:01:00Z)
• Deep Learning-Based Human Pose Estimation: A Survey [66.01917727294163]
  Human pose estimation has drawn increasing attention during the past decade. It has been utilized in a wide range of applications including human-computer interaction, motion analysis, augmented reality, and virtual reality. Recent deep learning-based solutions have achieved high performance in human pose estimation.
  arXiv  Detail & Related papers  (2020-12-24T18:49:06Z)
• Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos [8.571131862820833]
  State-of-the-art pose estimators struggle in obtaining high-quality 2D or 3D pose data due to truncation and low-resolution in real-world un-annotated videos. We propose a Selective Spatio-Temporal Aggregation mechanism, named SST-A, that refines and smooths the keypoint locations extracted by multiple expert pose estimators. We demonstrate that the skeleton data refined by our Pose-Refinement system (SSTA-PRS) is effective at boosting various existing action recognition models.
  arXiv  Detail & Related papers  (2020-11-10T19:19:51Z)
• Simultaneously-Collected Multimodal Lying Pose Dataset: Towards In-Bed Human Pose Monitoring under Adverse Vision Conditions [15.12849597272402]
  In-bed human pose estimation has significant values in many healthcare applications. In this paper, we introduce our Simultaneously-collected multimodal Lying Pose dataset. We show that state-of-the-art 2D pose estimation models can be trained effectively with SLP data with promising performance as high as 95% at PCKh@0.5 on a single modality.
  arXiv  Detail & Related papers  (2020-08-20T02:20:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.