3D object recognition from cluttered and occluded scenes with a compact local feature

Guo, Wulong; Hu, Weiduo; Liu, Chang; Lu, Tingting

doi:10.1007/s00138-019-01027-7

Cited by 16 publications

(7 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detecting objects and estimating the 6D pose from the geometry information represented by the point cloud is getting more and more attention. Extracting robust local features from the scene and objects is an interesting current research topic [19]. Recently, Kehl et al proposed an auto-encoderbased local feature learning method that can improve the quality of local features [20].…”

Section: B Geometry-based Methodsmentioning

confidence: 99%

Detecting 6D Poses of Target Objects From Cluttered Scenes by Learning to Align the Point Cloud Patches With the CAD Models

Chen

You

et al. 2020

IEEE Access

View full text Add to dashboard Cite

6D target object detection is of great importance to many applications such as robotics, industrial automation, and unmanned vehicles and is increasingly influencing broad industries including manufacturing, transportation, and retail industries, to name a few. Unlike the more common object detection methods that use the two-dimensional data such as RGB or depth images, the method proposed here relies on the three-dimensional point cloud of target objects to detect them in cluttered scenes in an end-to-end fashion. However, conventional point cloud-based 6D object detection methods rely on the robustness of key-point detection results that are not straightforward for humans to understand. The drawback makes conventional point cloud-based methods require expert knowledge to tune. In this paper, a point cloud-based 6D target object detection method that uses segmented object point cloud patches to predict object 6D poses and identity is introduced. In this way, the key-point detection is substituted with a point cloud segmentation procedure that is easier to visualize and tune. To extract the object pose and identity information from point cloud patches, we proposed an end-to-end data-driven pose correction model that can be trained with synthetic data and run on real-world data. A simple yet efficient basis spanning layer booster is proposed to accelerate the learning process and improve the pose estimation precision. An alignment error-based loss function is also introduced to make the proposed pose correction model trainable, efficiently. Experiments show that although the proposed model is trained only using object CAD models, its 6D detection performance matches that of the models using view data. Thus, the proposed method is suitable for 6D detection applications that have object CAD models instead of labeled scene data.

show abstract

Section: B Geometry-based Methodsmentioning

confidence: 99%

Detecting 6D Poses of Target Objects From Cluttered Scenes by Learning to Align the Point Cloud Patches With the CAD Models

Chen

You

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Then, HGND calculates the Gaussian point distribution and the normal distribution within each quadrant and finally forms a 1D histogram to represent the feature descriptor. A similar approach to RoPS is the multi‐view depth (MVD) descriptor [48]. Both share an LRF estimation process based on an eigen‐analysis of the weighted point scatter matrix within V and on a feature calculation process by projecting V on the planes of the LRF.…”

Section: 2d/3d Keypoint Detection and Feature Description Methodsmentioning

confidence: 99%

Performance evaluation of single and cross‐dimensional feature detection and description

2020

View full text Add to dashboard Cite

Three-dimensional local feature detection and description techniques are widely used for object registration and recognition applications. Although several evaluations of 3D local feature detection and description methods have already been published, these are constrained in a single dimensional scheme, i.e. either 3D or 2D methods that are applied onto multiple projections of the 3D data. However, cross-dimensional (mixed 2D and 3D) feature detection and description has yet to be investigated. Here, we evaluated the performance of both single and cross-dimensional feature detection and description methods on several 3D datasets and demonstrated the superiority of cross-dimensional over single-dimensional schemes. 2D / 3D Keypoint Detection and Feature Description Methods Keypoint DetectorsKeypoint detectors analyse the structure around a vertex or a pixel depending on the data domain (3D or 2D,

show abstract

“…Due to its fast and accurate nature when used for registration, the SR algorithm has been widely used in various fields [67][68][69][70]; its main steps include feature detection, feature matching, and segment transformation, as shown in figure 5. Before feature detection is performed, histogram equalization is used to preprocess the reference and distorted images.…”

Section: Sr Algorithmmentioning

confidence: 99%

An improved subpixel-level registration method for image-based fault diagnosis of train bodies using SURF features

Liu¹,

Huang²,

Qin³

et al. 2021

Meas. Sci. Technol.

View full text Add to dashboard Cite

Using computer-vision-based fault-diagnosis technologies, anomalies in train bodies can be automatically identified as part of daily maintenance. Nevertheless, since the train speed changes constantly and nonlinearly during the process of image acquisition, the obtained images can be severely distorted. As such, it is necessary to first register the collected images to correct the distortion, so as to accurately extract the key parts of the train body for fault detection. This paper proposes a new accurate registration method for train images based on speeded-up robust features, which improves on the traditional segment registration (SR) method by adding procedures for feature selection, piecewise linearization, and interpolated registration. The novelty of the proposed method is that up to subpixel-level registration accuracy can be achieved. Meanwhile, the robustness of the algorithm is ensured by its strong ability to screen out non-matching pairs when selecting features for registration. To demonstrate the performance of the proposed scheme, experimental comparison and verification are conducted, which show that, compared with the traditional SR method, the registration accuracy is remarkably improved in terms of mean square error, normalization cross-correlation, and structural similarity index.

show abstract

3D object recognition from cluttered and occluded scenes with a compact local feature

Cited by 16 publications

References 55 publications

Detecting 6D Poses of Target Objects From Cluttered Scenes by Learning to Align the Point Cloud Patches With the CAD Models

Detecting 6D Poses of Target Objects From Cluttered Scenes by Learning to Align the Point Cloud Patches With the CAD Models

Performance evaluation of single and cross‐dimensional feature detection and description

An improved subpixel-level registration method for image-based fault diagnosis of train bodies using SURF features

Contact Info

Product

Resources

About