A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking

• URL: http://arxiv.org/abs/2401.03872v1
• Date: Mon, 8 Jan 2024 13:04:28 GMT
• Title: A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking
• Authors: Alan Lukezic, Ziga Trojer, Jiri Matas, Matej Kristan
• Abstract summary: Performance of modern trackers degrades substantially on transparent objects compared to opaque objects. We propose the first transparent object tracking training dataset Trans2k that consists of over 2k sequences with 104,343 images overall. We also present a new distractor-aware transparent object tracker (DiTra) that treats localization accuracy and target identification as separate tasks.
• Score: 34.08943612955157
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Performance of modern trackers degrades substantially on transparent objects compared to opaque objects. This is largely due to two distinct reasons. Transparent objects are unique in that their appearance is directly affected by the background. Furthermore, transparent object scenes often contain many visually similar objects (distractors), which often lead to tracking failure. However, development of modern tracking architectures requires large training sets, which do not exist in transparent object tracking. We present two contributions addressing the aforementioned issues. We propose the first transparent object tracking training dataset Trans2k that consists of over 2k sequences with 104,343 images overall, annotated by bounding boxes and segmentation masks. Standard trackers trained on this dataset consistently improve by up to 16%. Our second contribution is a new distractor-aware transparent object tracker (DiTra) that treats localization accuracy and target identification as separate tasks and implements them by a novel architecture. DiTra sets a new state-of-the-art in transparent object tracking and generalizes well to opaque objects.

Related papers

• Transparent Object Tracking with Enhanced Fusion Module [56.403878717170784]
  We propose a new tracker architecture that uses our fusion techniques to achieve superior results for transparent object tracking. Our results and the implementation of code will be made publicly available at https://github.com/kalyan05TOTEM.
  arXiv  Detail & Related papers  (2023-09-13T03:52:09Z)
• TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation [6.844391823478345]
  We propose a two-stage pipeline that estimates category-level transparent object pose using localized depth completion and surface normal estimation. Results show that TransNet achieves improved pose estimation accuracy on transparent objects. We use TransNet to build an autonomous transparent object manipulation system for robotic pick-and-place and pouring tasks.
  arXiv  Detail & Related papers  (2023-07-23T18:38:42Z)
• Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking [41.039837388154]
  We propose the first transparent object tracking training dataset Trans2k that consists of over 2k sequences with 104,343 images overall. We quantify domain-specific attributes and render the dataset containing visual attributes and tracking situations not covered in the existing object training datasets. The dataset and the rendering engine will be publicly released to unlock the power of modern learning-based trackers and foster new designs in transparent object tracking.
  arXiv  Detail & Related papers  (2022-10-07T10:08:13Z)
• TransNet: Category-Level Transparent Object Pose Estimation [6.844391823478345]
  The lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. A second challenge is that common depth sensors typically used for opaque object perception cannot obtain accurate depth measurements on transparent objects. We propose TransNet, a two-stage pipeline that learns to estimate category-level transparent object pose using localized depth completion and surface normal estimation.
  arXiv  Detail & Related papers  (2022-08-22T01:34:31Z)
• Robust Visual Tracking by Segmentation [103.87369380021441]
  Estimating the target extent poses a fundamental challenge in visual object tracking. We propose a segmentation-centric tracking pipeline that produces a highly accurate segmentation mask. Our tracker is able to better learn a target representation that clearly differentiates the target in the scene from background content.
  arXiv  Detail & Related papers  (2022-03-21T17:59:19Z)
• Learning to Track with Object Permanence [61.36492084090744]
  We introduce an end-to-end trainable approach for joint object detection and tracking. Our model, trained jointly on synthetic and real data, outperforms the state of the art on KITTI, and MOT17 datasets.
  arXiv  Detail & Related papers  (2021-03-26T04:43:04Z)
• Transparent Object Tracking Benchmark [58.19532269423211]
  Transparent Object Tracking Benchmark consists of 225 videos (86K frames) from 15 diverse transparent object categories. To the best of our knowledge, TOTB is the first benchmark dedicated to transparent object tracking. To encourage future research, we introduce a novel tracker, named TransATOM, which leverages transparency features for tracking.
  arXiv  Detail & Related papers  (2020-11-21T21:39:43Z)
• Segmenting Transparent Objects in the Wild [98.80906604285163]
  This work proposes a large-scale dataset for transparent object segmentation, named Trans10K, consisting of 10,428 images of real scenarios with carefully manual annotations. To evaluate the effectiveness of Trans10K, we propose a novel boundary-aware segmentation method, termed TransLab, which exploits boundary as the clue to improve segmentation of transparent objects.
  arXiv  Detail & Related papers  (2020-03-31T04:44:31Z)

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.