Marker-Less 3d Object Recognition and 6d Pose Estimation for Homogeneous Textureless Objects: An RGB-D Approach

Abstract

The task of recognising an object and estimating its 6d pose in a scene has received considerable attention in recent years. The accessibility and low-cost of consumer RGB-D cameras, make object recognition and pose estimation feasible even for small industrial businesses. An example is the industrial assembly line, where a robotic arm should pick a small, textureless and mostly homogeneous object and place it in a designated location. Despite all the recent advancements of object recognition and pose estimation techniques in natural scenes, the problem remains challenging for industrial parts. In this paper, we present a framework to simultaneously recognise the object’s class and estimate its 6d pose from RGB-D data. The proposed model adapts a global approach, where an object and the Region of Interest (ROI) are first recognised from RGB images. The object’s pose is then estimated from the corresponding depth information. We train various classifiers based on extracted Histogram of Oriented Gradient (HOG) features to detect and recognize the objects. We then perform template matching on the point cloud based on surface normal and Fast Point Feature Histograms (FPFH) to estimate the pose of the object. Experimental results show that our system is quite efficient, accurate and robust to illumination and background changes, even for the challenging objects of Tless dataset. 6d pose estimation; 3d object recognition; textureless objects; homogeneous objects

Deep Learning-Based 6-DoF Object Pose Estimation Considering Synthetic Dataset

“…Moreover, it introduces a new loss function, known as the transformer loss for 3D coordinate regression, helping in resolving object symmetry issues. Meanwhile, Hajari et al [ 23 ] proposed a method, based on point cloud template matching, to realize some progress in position estimation of weakly textured objects. Within the pose estimation task, it is challenging to cover all object poses during training by just using real data; thus, acquiring pose labels with ground truth values is difficult to realize in several scenarios.…”

“…Advances in DL techniques have led to significant progress not only in the areas of target detection [ 1 , 2 , 3 ] and image segmentation [ 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 ], but also significant progress has been made in pose estimation using these techniques. They can be classified based on the types of datasets into (1) approaches relying on real datasets [ 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 ]; and (2) approaches based on synthetic data [ 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ]. However, the need for labeled real datasets raises a challenge due to the time-consuming and labor-intensive nature of their production, resulting in high dataset production costs [ 33 ].…”

Deep Learning-Empowered Robot Vision for Efficient Robotic Grasp Detection and Defect Elimination in Industry 4.0

“…Many works have been interested in adopting AI in industrial vision applications. The work carried out in [4] provides a methodology to recognize the class of an object while estimating its 6D pose with RGB-D data. Specifically, the proposed model adopts a global approach, first recognizing an object and the region of interest (ROI) from RGB images.…”