Probabilistic object recognition and pose estimation by fusing multiple algorithms

Joint object recognition and pose estimation using multiple-anchor triplet learning of canonical plane

The next generation of service robots is to offer services relying heavily on visually guided manipulation, besides navigation, such services as errand, logistics, appliance, home keeping, etc. For the successful introduction of these services, it is critical to establish the consumer-level dependability in 3D object recognition and pose estimation in a natural setting where a large variation of environment, e.g., perspective, texture, form factor, illumination, occlusion, etc., is common. To address this problem, we propose an approach of the two-layered particle filter to the dependability in 3D object recognition and pose estimation. In the upper layer, a set of object pose candidates is identified and maintained in the search space as a set of super-particles, each of which is assigned a probability of the true pose and evolved in time along with the accumulation of further evidences. To define the object pose candidates, first, we acquire initially weak evidences quickly and interpret them in terms of possible object poses in space. These interpretations serve as the region of interest for detailed investigation by which the pose probabilities are computed for individual interpretations based on the likelihood and unlikelihood of various features available in the corresponding regions of interest. During the process of probability computation, we select the object pose candidates to be used as super-particles in the upper layer. In the lower level, the pose uncertainties associated with the individual candidates are represented as particles that are subject to the propagation in time. Finally, the experimental results support the strength of the proposed approach in the real environment in terms of its dependability in 3D object recognition and pose estimation.

Object recognition and pose estimation are critical components in autonomous robot manipulation systems, playing a crucial role in enabling robots to interact effectively with the environment. During actual execution, the robot must recognize the object in the current scene, estimate its pose, and then select a feasible grasp pose from the pre-defined grasp configurations. While most existing methods primarily focus on pose estimation, they often neglect the graspability and reachability aspects. This oversight can lead to inefficiencies and failures during execution. In this study, we introduce an innovative graspability-aware object pose estimation framework. Our proposed approach not only estimates the poses of multiple objects in clustered scenes but also identifies graspable areas. This enables the system to concentrate its efforts on specific points or regions of an object that are suitable for grasping. It leverages both depth and color images to extract geometric and appearance features. To effectively combine these diverse features, we have developed an adaptive fusion module. In addition, the fused features are further enhanced through a graspability-aware feature enhancement module. The key innovation of our method lies in improving the discriminability and robustness of the features used for object pose estimation. We have achieved state-of-the-art results on public datasets when compared to several baseline methods. In real robot experiments conducted on a Franka Emika robot arm equipped with an Intel Realsense camera and a two-finger gripper, we consistently achieved high success rates, even in cluttered scenes.

State-of-the-art object recognition and pose estimation systems often utilize point feature algorithms, which in turn usually require the computing power of conventional PC hardware. In this paper, we describe two embedded systems for object detection and pose estimation using sophisticated point features. The feature detection step of the “Speeded-up Robust Features (SURF)” algorithm is accelerated by a special IP core. The first system performs object detection and is completely implemented in a single medium-size Virtex-5 FPGA. The second system is an augmented reality platform, which consists of an ARM-based microcontroller and intelligent FPGA-based cameras which support the main system.

In this paper, a novel global point cloud descriptor is proposed for reliable object recognition and pose estimation, which can be effectively applied to robot grasping operation. The viewpoint feature histogram (VFH) is widely used in three-dimensional (3D) object recognition and pose estimation in real scene obtained by depth sensor because of its recognition performance and computational efficiency. However, when the object has a mirrored structure, it is often difficult to distinguish the mirrored poses relative to the viewpoint using VFH. In order to solve this difficulty, this study presents an improved feature descriptor named orthogonal viewpoint feature histogram (OVFH), which contains two components: a surface shape component and an improved viewpoint direction component. The improved viewpoint component is calculated by the orthogonal vector of the viewpoint direction, which is obtained based on the reference frame estimated for the entire point cloud. The evaluation of OVFH using a publicly available data set indicates that it enhances the ability to distinguish between mirrored poses while ensuring object recognition performance. The proposed method uses OVFH to recognize and register objects in the database and obtains precise poses by using the iterative closest point (ICP) algorithm. The experimental results show that the proposed approach can be effectively applied to guide the robot to grasp objects with mirrored poses.

The SIFT algorithm (Scale Invariant Feature Transform) proposed by Lowe [1] is an approach for extracting distinctive invariant features from images. It has been successfully applied to a variety of computer vision problems based on feature matching including object recognition, pose estimation, image retrieval and many others. However, in real-world applications there is still a need for improvement of the algorithm’s robustness with respect to the correct matching of SIFT features. In this paper, an improvement of the original SIFT algorithm providing more reliable feature matching for the purpose of object recognition is proposed. The main idea is to divide the features extracted from both the test and the model object image into several sub-collections before they are matched. The features are divided into several sub-collections considering the features arising from different octaves, that is from different frequency domains. The SIFT algorithm (Scale Invariant Feature Transform) proposed by Lowe [1] is an approach for extracting distinctive invariant features from images. It has been successfully applied to a variety of computer vision problems based on feature matching including object recognition, pose estimation, image retrieval and many others. However, in real-world applications there is still a need for improvement of the algorithm’s robustness with respect to the correct matching of SIFT features. In this paper, an improvement of the original SIFT algorithm providing more reliable feature matching for the purpose of object recognition is proposed. The main idea is to divide the features extracted from both the test and the model object image into several sub-collections before they are matched. The features are divided into several sub-collections considering the features arising from different octaves, that is from different frequency domains.

This paper presents an appearance-based method for object pose recognition using single camera image. The basic idea of our method is to find the correlation between object image and its pose, and use it for object recognition and pose estimation. Canonical correlation analysis is introduced to derive such correlation and build a compact appearance model. In the approach, we first obtain a pair of training data set, i.e., object images and their pose parameters. The appearance model is given as the subspace spanned by the canonical vectors that maximize the correlation between images and poses. Pose parameters of currently observed image is predicted by finding the regression coefficient in this subspace. We also introduce the kernel methods to cope with the non-linearity lies in training data set. Experiments are conducted on object pose estimation and vehicle type classification problem. Performance of our appearance models is discussed through the comparison with conventional subspace method

Purpose Accurate 6D object pose estimation is essential for various robotic tasks. Uncertain pose estimates can lead to task failures; however, a certain degree of error in the pose estimates is often acceptable. This paper aims to enable the robots to make informed decisions by quantifying errors in the object pose estimate and acceptable errors for task success. Design/methodology/approach In this paper, the authors introduce a framework for evaluating robotic task success under object pose uncertainty, representing both the estimated error space of the object pose and the acceptable error space for task success using multi-modal non-parametric probability distributions. The proposed framework pre-computes the acceptable error space for task success using dynamic simulations and subsequently integrates the pre-computed acceptable error space over the estimated error space of the object pose to predict the likelihood of the task succes. Findings The authors evaluated the proposed framework on two mobile manipulation tasks. Their results show that by representing the estimated and the acceptable error space using multi-modal non-parametric distributions, the authors achieve higher task success rates and fewer failures. Research limitations/implications Their proposed framework is generic and can be applied to a wide range of robotic tasks requiring object pose estimation. Hence, given the recent advancements in object pose uncertainty estimation and dynamic simulations, the proposed framework, in conjunction with these advancements, has the potential to enable robots to make reliable and informed decisions under pose uncertainty. Originality/value Unlike related works that model both acceptable error space and estimated error space using parametric uni-modal distributions, the authors model them as multi-modal distributions which is often the case in the real world.

In this paper, an object recognition method and a pose estimation approach using stereo vision is presented. The proposed approach was used for position based visual servoing of a 6 DoF manipulator. The object detection and recognition method was designed with the purpose of increasing robustness. A RGB color-based object descriptor and an online correction method is proposed for object detection and recognition. Pose was estimated by using the depth information derived from stereo vision camera and an SVD based method. Transformation between the desired pose and object pose was calculated and later used for position based visual servoing. Experiments were carried out to verify the proposed approach for object recognition. The stereo camera was also tested to see whether the depth accuracy is adequate. The proposed object recognition method is invariant to scale, orientation and lighting condition which increases the level of robustness. The accuracy of stereo vision camera can reach 1 mm. The accuracy is adequate for tasks such as grasping and manipulation.

6D pose estimation is an important branch in the field of vision measurement, and is widely used in the fields of robotics, autonomous driving and reality augmentation. The latest research trend in 6D pose estimation is to train a deep neural network to directly predict the 2D projection position of the 3D keypoint from the image, establish the corresponding relationship, and finally use the perspective-n-point (PnP) algorithm to perform pose estimation. The current challenge of pose estimation is that when objects are textureless, occluded or scene-clutterd, the detection accuracy is reduced, and most of the existing algorithm models are large and cannot accommodate real-time requirements. In this paper, we introduce a densely connected feature pyramid network (DFPN) that can efficiently integrate and utilize features. We combine the cross-stage partial network (CSPNet) with DFPN to design a new network for 6D pose estimation, DFPN-6D, a new approach for 6D object pose estimation. DFPN-6D can efficiently and accurately handle objects with textureless, occluded and scene clutter and estimate their full 6D poses in a single shot. Furthermore, we propose a new confidence calculation method and loss function for object pose estimation, which can fully consider spatial information. Finally, we propose a novel augmentation method for direct 6D pose estimation approaches to improve performance and generalization ability in the case of occlusion, which is called 6D augmentation. Our approach achieves a new state-of-the-art accuracy of 98.06 and 87.09 in terms of the ADD(-S) metric on the Linemod dataset and Occluded-Linemod dataset, and our method also achieves the best result in terms of the different metric on the MULT-I dataset, BIN-P dataset and T-LESS dataset, respectively, while still running end-to-end at over 65 FPS. The experimental results demonstrate that our algorithm is robust to textureless materials and occlusion while running more efficiently than other methods. We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose.

In this paper, we present an ANN hybrid ensemble scheme for simultaneous object recognition and pose estimation from 2D multiple-view image sequence, and realized human vision simulation within an intelligent machine. Based on the notion of similarity measure at various metrics, the paradox between information simplicity and accuracy is balanced by a model view generation procedure. An ANN hierarchical hybrid ensemble framework, much like a decision tree, is then set up, with multiple weights and radial basis function neural networks respectively employed for different tasks. The strategy adopted not only determines object identity by spatial geometrical cognition and omnidirectional accumulation through connectivity, but also assigns an initial pose estimation on a viewing sphere in a coarse to fine process. Simulation experiment has achieved encouraging results, proved the approach effective, superior and feasible in large-scale database and parallel computation.KeywordsObject RecognitionRadial Basis Function Neural NetworkModel ViewObject NodeInformation SimplicityThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Object recognition and pose estimation are of significant importance for robotic visual servoing, manipulation and grasping tasks. Traditionally, contour and shape based methods have been considered as most adequate for estimating stable and feasible grasps (Bicchi and Kumar, 2000). A new research direction has been advocated in visual servoing where image moments are used to define a suitable error function to be minimized. Compared to appearance based methods, contour and shape based approaches are also suitable for use with range sensors such as, for example, lasers. In this paper, we evaluate a contour based object recognition system building on the method in Nelson and Selinger (1998), suitable for objects of uniform color properties such as cups, cutlery, fruits etc. This system is one of the building blocks of a more complex object recognition system based both on stereo and appearance cues, (Bjorkman and Kragic, 2004). The system has a significant potential both in terms of service robot and programming by demonstration tasks. Experimental evaluation shows promising results in terms of robustness to occlusion and noise

Enabling robots to automatically locate and pick up randomly placed and oriented objects from a bin is an important challenge in factory automation, replacing tedious and heavy manual labor. A system should be able to recognize and locate objects with a predefined shape and estimate the position with the precision necessary for a gripping robot to pick it up. We describe a system that consists of a structured light instrument for capturing 3D data and a robust approach for object location and pose estimation. The method does not depend on segmentation of range images, but instead searches through pairs of 2D manifolds to localize candidates for object match. This leads to an algorithm that is not very sensitive to scene complexity or the number of objects in the scene. Furthermore, the strategy for candidate search is easily reconfigurable to arbitrary objects. Experiments reported in this paper show the utility of the method on a general random bin picking problem, in this paper exemplified by localization of car parts with random position and orientation. Full pose estimation is done in less than 380 ms per image. We believe that the method is applicable for a wide range of industrial automation problems where precise localization of 3D objects in a scene is needed.

We propose a joint object pose estimation and categorization approach which extracts information about object poses and categories from the object parts and compositions constructed at different layers of a hierarchical object representation algorithm, namely Learned Hierarchy of Parts (LHOP) [7]. In the proposed approach, we first employ the LHOP to learn hierarchical part libraries which represent entity parts and compositions across different object categories and views. Then, we extract statistical and geometric features from the part realizations of the objects in the images in order to represent the information about object pose and category at each different layer of the hierarchy. Unlike the traditional approaches which consider specific layers of the hierarchies in order to extract information to perform specific tasks, we combine the information extracted at different layers to solve a joint object pose estimation and categorization problem using distributed optimization algorithms. We examine the proposed generative-discriminative learning approach and the algorithms on two benchmark 2-D multi-view image datasets. The proposed approach and the algorithms outperform state-of-the-art classification, regression and feature extraction algorithms. In addition, the experimental results shed light on the relationship between object categorization, pose estimation and the part realizations observed at different layers of the hierarchy.

Automatic object recognition capabilities are traditionally tuned to exploit the specific sensing modality they were designed to. Their successes (and shortcomings) are tied to object segmentation from the background, they typically require highly skilled personnel to train them, and they become cumbersome with the introduction of new objects. In this paper we describe a sensor independent algorithm based on the biologically inspired technology of map seeking circuits (MSC) which overcomes many of these obstacles. In particular, the MSC concept offers transparency in object recognition from a common interface to all sensor types, analogous to a USB device. It also provides a common core framework that is independent of the sensor and expandable to support high dimensionality decision spaces. Ease in training is assured by using commercially available 3D models from the video game community. The search time remains linear no matter how many objects are introduced, ensuring rapid object recognition. Here, we report results of an MSC algorithm applied to object recognition and pose estimation from high range resolution radar (1D), electrooptical imagery (2D), and LIDAR point clouds (3D) separately. By abstracting the sensor phenomenology from the underlying a prior knowledge base, MSC shows promise as an easily adaptable tool for incorporating additional sensor inputs.