CoSPAIR: Colored Histograms of Spatial Concentric Surflet-Pairs for 3D object recognition

Date

2016-01-01

Author

Logoglu, K. Berker
Kalkan, Sinan
Temizel, Alptekin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

49
views

0
downloads

Introduction of RGB-D sensors together with the efforts on open-source point-cloud processing tools boosted research in both computer vision and robotics. One of the key areas which have drawn particular attention is object recognition since it is one of the crucial steps for various applications. In this paper, two spatially enhanced local 3D descriptors are proposed for object recognition tasks: Histograms of Spatial Concentric Surflet-Pairs (SPAIR) and Colored SPAIR (CoSPAIR). The proposed descriptors are compared against the state-of-the-art local 3D descriptors that are available in Point Cloud Library (PCL) and their object recognition performances are evaluated on several publicly available datasets. The experiments demonstrate that the proposed CoSPAIR descriptor outperforms the state-of-the-art descriptors in both category-level and instance-level recognition tasks. The performance gains are observed to be up to 9.9 percentage points for category-level recognition and 16.49 percentage points for instance-level recognition over the second-best performing descriptor.

Subject Keywords

3D descriptors, 3D object recognition, Point clouds, RGB-D

URI

https://hdl.handle.net/11511/30296

Journal

ROBOTICS AND AUTONOMOUS SYSTEMS

DOI

https://doi.org/10.1016/j.robot.2015.09.027

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

Spatial 3D local descriptors for object recognition in RGB-D images Loğoğlu, K. Berker; Temizel, Alptekin; Kalkan, Sinan; Department of Information Systems (2016) Introduction of the affordable but relatively high resolution color and depth synchronized RGB-D sensors, along with the efforts on open-source point-cloud processing tools boosted research in both computer vision and robotics. One of the key areas which have drawn particular attention is object recognition since it is one of the crucial steps for various applications. In this thesis, two spatially enhanced local 3D descriptors are proposed for object recognition tasks: Histograms of Spatial Concentric Surf...
Real-time object-oriented framework for fmi co-simulation Çam Silik, Merve; Oğuztüzün, Mehmet Halit S.; Department of Computer Engineering (2020) Development of models, their integration into FMI-compliant co-simulation and performing the simulation in real-time environment are crucial tasks in embedded system development. To introduce an object-oriented co-simulation environment to real-time domain, promote model reuse and minimize effort for co-simulation environment generation a Real-Time Object-Oriented Framework for FMI Co-Simulation was developed for completion of this thesis. A case study which comprises of a control actuation system and sine ...
High performance readout electronics for uncooled infrared detector arrays Yıldırım, Ömer Özgür; Akın, Tayfun; Department of Electrical and Electronics Engineering (2006) This thesis reports the development of high performance readout electronics for resistive microbolometer detector arrays that are used for uncooled infrared imaging. Three different readout chips are designed and fabricated by using a standard 0.6 m CMOS process. Fabricated chips include a conventional capacitive transimpedance amplifier (CTIA) type readout circuit, a novel readout circuit with dynamic resistance nonuniformity compensation capability, and a new improved version of the CTIA circuit. The fabr...
A novel fault tolerant architecture on a runtime reconfigurable FPGA Coşkuner, İbrahim Aydın; Güran, Hasan; Department of Electrical and Electronics Engineering (2006) Due to their programmable nature, Field Programmable Gate Arrays (FPGAs) offer a good test environment for reconfigurable systems. FPGAs can be reconfigured during the operation with changing demands. This feature, known as Runtime Reconfiguration (RTR), can be used to speed-up computations and reduce system cost. Moreover, it can be used in a wide range of applications such as adaptable hardware, fault tolerant architectures. This thesis is mostly concentrated on the runtime reconfigurable architectures. C...
FPGA implementation of field oriented control forpermanent magnet synchronous motor Irmak, Gizem; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2019) The thesis study focuses on the fully operational FPGA implementation for the current/torque control of a Permanent Magnet Synchronous Motor. 3-phase synchronous motors with permanent magnets can be categorized into two categories as Permanent Magnet Synchronous Motor (PMSM) and Brushless Direct Current (BLDC) motor. The main difference between PMSM and BLDC is the shape of the induced back-EMF voltage. While BLDC motors have trapezoidal shaped back-EMF, PMSMs have a sinusoidal back-EMF. In order to take ad...

Citation Formats

K. B. Logoglu, S. Kalkan, and A. Temizel, “CoSPAIR: Colored Histograms of Spatial Concentric Surflet-Pairs for 3D object recognition,” ROBOTICS AND AUTONOMOUS SYSTEMS, pp. 558–570, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/30296.