3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey

Guo, Yulan; Bennamoun, Mohammed; Sohel, Ferdous; Lü, Min; Wan, Jianwei

doi:10.1109/tpami.2014.2316828

Cited by 557 publications

(227 citation statements)

References 110 publications

Supporting

Mentioning

227

Contrasting

Order By: Relevance

“…The UWA data set is a popular and widely used data set for 3-D object detection and recognition [8], [9], [20], [40], [43]- [47]. It consists of four models and 50 scenes.…”

Section: Resultsmentioning

confidence: 99%

“…, f i N F } is extracted from each pointcloud S i for the purpose of feature matching. As demonstrated in [8], [13], and [26], our previously proposed RoPS feature is highly discriminative and very robust to occlusion, clutter, noise, and varying mesh resolutions. Therefore, RoPS is selected as the local surface feature used in this paper.…”

Section: Methods Overviewmentioning

confidence: 94%

“…To the best of our knowledge, there is limited research in the literature that covers the matching between two cluttered scenes for the modeling of isolated 3-D objects (rather than 3-D scenes). For more details on 3-D object recognition algorithms, the reader is referred to a comprehensive and contemporary survey [8]. This paper is motivated by this research niche to detect unknown objects without any prior information, and to model these objects from a set of cluttered scenes.…”

mentioning

confidence: 99%

See 2 more Smart Citations

An Integrated Framework for 3-D Modeling, Object Detection, and Pose Estimation From Point-Clouds

Guo

Bennamoun

Sohel

et al. 2015

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

3-D modeling, object detection, and pose estimation are three of the most challenging tasks in the area of 3-D computer vision. This paper presents a novel algorithm to perform these tasks simultaneously from unordered point-clouds. Given a set of input point-clouds in the presence of clutter and occlusion, an initial model is first constructed by performing pair-wise registration between any two point-clouds. The resulting model is then updated from the remaining point-clouds using a novel model growing technique. Once the final model is reconstructed, the instances of the object are detected and the poses of its instances in the scenes are estimated. This algorithm is automatic, model free, and does not rely on any prior information about the objects in the scene. The algorithm was comprehensively tested on the University of Western Australia data set. Experimental results show that our algorithm achieved accurate modeling, detection, and pose estimation performance.

show abstract

“…The UWA data set is a popular and widely used data set for 3-D object detection and recognition [8], [9], [20], [40], [43]- [47]. It consists of four models and 50 scenes.…”

Section: Resultsmentioning

confidence: 99%

Section: Methods Overviewmentioning

confidence: 94%

mentioning

confidence: 99%

See 1 more Smart Citation

An Integrated Framework for 3-D Modeling, Object Detection, and Pose Estimation From Point-Clouds

Guo

Bennamoun

Sohel

et al. 2015

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Object recognition from point clouds has been successfully applied to detect building elements (Bosche et al 2009) as well as construction equipment (Wang and Cho 2015). However, 3D object recognition techniques suffer from limitations due to sensor noise, clutter and deformations (Guo et al 2014;Salti et al 2011). …”

Section: Existing Object Recognition Methodsmentioning

confidence: 99%

Robotic sensing and object recognition from thermal-mapped point clouds

Kim

Chen

Cho

2017

Int J Intell Robot Appl

View full text Add to dashboard Cite

Many of the civil structures are more than half way through or nearing their intended service life; frequently assessing and maintaining structural integrity is a top maintenance priority. Robotic inspection technologies using ground and aerial robots with 3D scanning and imaging capabilities have the potential to improve safety and efficiency of infrastructure management. To provide more valuable information to inspectors and agency decision makers, automatic environment sensing and semantic information extraction are fundamental issues in this field. This paper introduces an innovative method for generating thermal-mapped point clouds of a robot's work environment and performing automatic object recognition with the aid of thermal data fused to 3D point clouds. The laser scanned point cloud and thermal data were collected using a custom-designed mobile robot. The multimodal data was combined with a data fusion process based on texture mapping. The automatic object recognition was performed by two processes: segmentation with thermal data and classification with scanned geometric features. The proposed method was validated with the scan data collected in an entire building floor. Experimental results show that the thermal integrated object recognition approach achieved better performance than a geometry only-based approach, with an average recognition accuracy of 93%, precision of 83%, and recall rate of 86% for objects in the tested environment including humans, display monitors and light fixtures.

show abstract

“…3D keypoint detection is heavily employed in various applications such as 3D object recognition (Guo et al (2014); Rodolà et al (2012)), Simultaneous Localization and Mapping (Endres et al (2014)), Sparse Depth Odometry (Prakhya et al (2015b)), 3D shape retrieval and point cloud registration (Torsello et al (2011); Prakhya et al (2015a)). A keypoint detector reduces an input point cloud to fewer number of keypoints, which helps in improving the accuracy and reducing the computational requirements of the target application.…”

Section: Introductionmentioning

confidence: 99%