An Occlusion‐aware Edge‐Based Method for Monocular 3D Object Tracking using Edge Confidence

Huang, Hong; Zhong, Fan; Sun, Yuqing; Qin, Xueying

doi:10.1111/cgf.14154

Cited by 18 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, our method takes robust estimation with α < 2 to handle erroneous correspondences. In previous methods α = 2, so the optimization process is sensitive to the correspondence errors, and complex filtering and weighting techniques thus are necessary [8,17]. We will show that, by setting α as a small value, erroneous correspondences can be well suppressed with a simple weighting function ω i (see Section 3.3).…”

Section: Robust Contour-based Trackingmentioning

confidence: 88%

See 1 more Smart Citation

Large-displacement 3D Object Tracking with Hybrid Non-local Optimization

Tian¹,

Lin²,

Fan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Optimization-based 3D object tracking is known to be precise and fast, but sensitive to large inter-frame displacements. In this paper we propose a fast and effective non-local 3D tracking method. Based on the observation that erroneous local minimum are mostly due to the out-of-plane rotation, we propose a hybrid approach combining non-local and local optimizations for different parameters, resulting in efficient non-local search in the 6D pose space. In addition, a precomputed robust contour-based tracking method is proposed for the pose optimization. By using long search lines with multiple candidate correspondences, it can adapt to different frame displacements without the need of coarse-to-fine search. After the pre-computation, pose updates can be conducted very fast, enabling the non-local optimization to run in real time. Our method outperforms all previous methods for both small and large displacements. For large displacements, the accuracy is greatly improved (81.7% v.s. 19.4%). At the same time, real-time speed (>50fps) can be achieved with only CPU. The source code is available at https://github.com/cvbubbles/nonlocal-3dtracking.

show abstract

Section: Robust Contour-based Trackingmentioning

confidence: 88%

“…However, early contour-based methods are known to be sensitive to background clutters that may cause wrong contour correspondences. To solve this problem, local color information is leveraged for improving the correspondences [8,17], which effectively improves accuracy.…”

Section: Related Workmentioning

confidence: 99%

Large-displacement 3D Object Tracking with Hybrid Non-local Optimization

Tian¹,

Lin²,

Fan³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Edge‐based methods [HS90, DC02, SPP*14, IP15, WZQ17, CRV*18, WZQ19, HZSQ20] generally begin by detecting the object's edges and then matching them with the contours projected by the 3D model to optimize the object's pose. However, these methods can be easily disrupted by chaotic backgrounds.…”

Section: Related Workmentioning

confidence: 99%

3D Object Tracking for Rough Models

Song,

Xie,

et al. 2023

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

Visual monocular 6D pose tracking methods for textureless or weakly‐textured objects heavily rely on contour constraints established by the precise 3D model. However, precise models are not always available in reality, and rough models can potentially degrade tracking performance and impede the widespread usage of 3D object tracking. To address this new problem, we propose a novel tracking method that handles rough models. We reshape the rough contour through the probability map, which can avoid explicitly processing the 3D rough model itself. We further emphasize the inner region information of the object, where the points are sampled to provide color constrains. To sufficiently satisfy the assumption of small displacement between frames, the 2D translation of the object is pre‐searched for a better initial pose. Finally, we combine constraints from both the contour and inner region to optimize the object pose. Experimental results demonstrate that the proposed method achieves state‐of‐the‐art performance on both roughly and precisely modeled objects. Particularly for the highly rough model, the accuracy is significantly improved (40.4% v.s. 16.9%).

show abstract

“…Key-point features such as SIFT (Lowe 2004), ORB (Rublee et al 2011), or BRISK (Leutenegger et al 2011) have been widely used for 3D object tracking (Wagner et al 2010;Vacchetti et al 2004), with more recent developments like LIFT (Yi et al 2016) and SuperGlue (Sarlin et al 2020) introducing deep learning at various stages. Explicit edges provide an additional source of information that is used by many approaches (Huang et al 2020;Bugaev et al 2018;Seo et al 2014;Comport et al 2006;Drummond and Cipolla 2002;Harris and Stennett 1990). Also, direct methods (Engel et al 2018;Seo and Wuest 2016;Crivellaro and Lepetit 2014), which optimize a photometric error and can be traced back to Lucas and Kanade (1981), have been proposed.…”

Section: D Object Trackingmentioning

confidence: 99%

“…Results of the evaluation are shown in Table 1. Our approach is compared to the current state of the art in regionbased tracking, as well as the edge-based methods of Huang et al (2020), algorithms of Li et al (2021) and Sun et al (2021) that combine edge and region information, and the method of Liu et al (2021) that uses descriptor fields in addition to region-based techniques. The comparison shows that SRT3D performs significantly better than previous methods, achieving superior results for most objects and performing best on average.…”

Section: Rbot Datasetmentioning

confidence: 99%

SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World

et al. 2022

View full text Add to dashboard Cite

Region-based methods have become increasingly popular for model-based, monocular 3D tracking of texture-less objects in cluttered scenes. However, while they achieve state-of-the-art results, most methods are computationally expensive, requiring significant resources to run in real-time. In the following, we build on our previous work and develop SRT3D, a sparse region-based approach to 3D object tracking that bridges this gap in efficiency. Our method considers image information sparsely along so-called correspondence lines that model the probability of the object’s contour location. We thereby improve on the current state of the art and introduce smoothed step functions that consider a defined global and local uncertainty. For the resulting probabilistic formulation, a thorough analysis is provided. Finally, we use a pre-rendered sparse viewpoint model to create a joint posterior probability for the object pose. The function is maximized using second-order Newton optimization with Tikhonov regularization. During the pose estimation, we differentiate between global and local optimization, using a novel approximation for the first-order derivative employed in the Newton method. In multiple experiments, we demonstrate that the resulting algorithm improves the current state of the art both in terms of runtime and quality, performing particularly well for noisy and cluttered images encountered in the real world.

show abstract

An Occlusion‐aware Edge‐Based Method for Monocular 3D Object Tracking using Edge Confidence

Cited by 18 publications

References 36 publications

Large-displacement 3D Object Tracking with Hybrid Non-local Optimization

Large-displacement 3D Object Tracking with Hybrid Non-local Optimization

3D Object Tracking for Rough Models

SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World

Contact Info

Product

Resources

About