Jianwei Wan

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

3D object recognition in cluttered scenes is a rapidly growing research area. Based on the used types of features, 3D object recognition methods can broadly be divided into two categories-global or local feature based methods. Intensive research has been done on local surface feature based methods as they are more robust to occlusion and clutter which are frequently present in a real-world scene. This paper presents a comprehensive survey of existing local surface feature based 3D object recognition methods. These methods generally comprise three phases: 3D keypoint detection, local surface feature description, and surface matching. This paper covers an extensive literature survey of each phase of the process. It also enlists a number of popular and contemporary databases together with their relevant attributes.

A Comprehensive Performance Evaluation of 3D Local Feature Descriptors

A number of 3D local feature descriptors have been proposed in the literature. It is however, unclear which descriptors are more appropriate for a particular application. A good descriptor should be descriptive, compact, and robust to a set of nuisances. This paper compares ten popular local feature descriptors in the contexts of 3D object recognition, 3D shape retrieval, and 3D modeling. We first evaluate the descriptiveness of these descriptors on eight popular datasets which were acquired using different techniques. We then analyze their compactness using the recall of feature matching per each float value in the descriptor. We also test the robustness of the selected descriptors with respect to support radius variations, Gaussian noise, shot noise, varying mesh resolution, distance to the mesh boundary, keypoint localization error, occlusion, clutter, and dataset size. Moreover, we present the performance results of these descriptors when combined with different 3D keypoint detection methods. We finally analyze the computational efficiency for generating each descriptor.

An Accurate and Robust Range Image Registration Algorithm for 3D Object Modeling

Range image registration is a fundamental research topic for 3D object modeling and recognition. In this paper, we propose an accurate and robust algorithm for pairwise and multi-view range image registration. We first extract a set of Rotational Projection Statistics (RoPS) features from a pair of range images, and perform feature matching between them. The two range images are then registered using a transformation estimation method and a variant of the Iterative Closest Point (ICP) algorithm. Based on the pairwise registration algorithm, we propose a shape growing based multi-view registration algorithm. The seed shape is initialized with a selected range image and then sequentially updated by performing pairwise registration between itself and the input range images. All input range images are iteratively registered during the shape growing process. Extensive experiments were conducted to test the performance of our algorithm. The proposed pairwise registration algorithm is accurate, and robust to small overlaps, noise and varying mesh resolutions. The proposed multi-view registration algorithm is also very accurate. Rigorous comparisons with the state-of-the-art show the superiority of our algorithm.

A novel local surface feature for 3D object recognition under clutter and occlusion

This paper presents a highly distinctive local surface feature called the TriSI feature for recognizing 3D objects in the presence of clutter and occlusion. For a feature point, we first construct a unique and repeatable Local Reference Frame (LRF) using the implicit geometrical information of neighboring triangular faces. We then generate three signatures from the three orthogonal coordinate axes of the LRF. These signatures are concatenated and then compressed into a TriSI feature. Finally, we propose an effective 3D object recognition algorithm based on hierarchical feature matching. We tested our TriSI feature on two popular datasets. Rigorous experimental results show that the TriSI feature was highly descriptive and outperformed existing algorithms under all levels of Gaussian noise, Laplacian noise, shot noise, varying mesh resolutions, occlusion, and clutter. Moreover, we tested our TriSI-based 3D object recognition algorithm on four standard datasets. The experimental results show that our algorithm achieved the best overall recognition results on these datasets.

3D free form object recognition using rotational projection statistics

Recognizing 3D objects in the presence of clutter and occlusion is a challenging task. This paper presents a 3D free form object recognition system based on a novel local surface feature descriptor. For a randomly selected feature point, a local reference frame (LRF) is defined by calculating the eigenvectors of the covariance matrix of a local surface, and a feature descriptor called rotational projection statistics (RoPS) is constructed by calculating the statistics of the point distribution on 2D planes defined from the LRF. It finally proposes a 3D object recognition algorithm based on RoPS features. Candidate models and transformation hypotheses are generated by matching the scene features against the model features in the library, these hypotheses are then tested and verified by aligning the model to the scene. Comparative experiments were performed on two publicly available datasets and an overall recognition rate of 98.8% was achieved. Experimental results show that our method is robust to noise, mesh resolution variations and occlusion.

RoPS: A local feature descriptor for 3D rigid objects based on rotational projection statistics

The proper choice of local surface feature descriptors is a key step for an accurate and robust surface matching between different range images. This paper presents a novel 3D feature descriptor for free form objects based on rotational projection statistics. A rotation invariant local reference frame for each feature point is defined by performing an eigenvalue decomposition on the covariance matrix formed by all points lying on the local surface. The feature descriptor is then constructed by rotationally projecting the neighboring 3D points onto 2D planes and by calculating low order moments and the entropy of the 2D distribution matrix on these planes. Experiments were performed on a dataset comprised of 45 scenes, and the results show that the proposed method is robust to noise and variations in mesh resolution.

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

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.

Benchmark datasets for 3D computer vision

With the rapid development of range image acquisition techniques, 3D computer vision has became a popular research area. It has numerous applications in various domains including robotics, biometrics, remote sensing, entertainment, civil construction, and medical treatment. Recently, a large number of algorithms have been proposed to address specific problems in the area of 3D computer vision. Meanwhile, several benchmark datasets have also been released to stimulate the research in this area. The availability of benchmark datasets plays an significant role in the process of technological progress. In this paper, we first introduce several major 3D acquisition techniques. We also present an overview on various popular topics in 3D computer vision including 3D object modeling, 3D model retrieval, 3D object recognition, 3D face recognition, RGB-D vision, and 3D remote sensing. Moreover, we present a contemporary summary of the existing benchmark datasets in 3D computer vision. This paper can therefore, serve as a handbook for those who are working in the related areas.

Fast and Accurate Registration of Structured Point Clouds with Small Overlaps

To perform registration of structured point clouds with large rotation and small overlaps, this paper presents an algorithm based on the direction angles and the projection information of dense points. This algorithm fully employs the geometric information of structured environment. It consists of two parts: rotation estimation and translation estimation. For rotation estimation, a direction angle is defined for a point cloud and then the rotation matrix is obtained by comparing the difference between the distributions of angles. For translation estimation, the point clouds are projected onto three orthogonal planes and then a correlation operation is performed on the projection images to calculate the translation vector. Experiments have been conducted on several datasets. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art approaches in terms of both accuracy and efficiency.

Integrating shape and color cues for textured 3D object recognition

3D object recognition is a fundamental research topic. However, shape only feature descriptors for 3D object recognition have been the main focus of research. With the availability of low cost range plus color sensors, color based descriptors have attracted increasing attention lately. In this paper we present novel 3D object recognition algorithms which use not only shape but also color cues. We first extend our previously proposed Shape only Rotational Projection Statistics (hereby denoted S-RoPS) to obtain a Color only RoPS (C-RoPS) feature descriptor. The C-RoPS descriptor is based on the color space instead of the 3D shape coordinates. We then use feature level and decision level fusion approaches to combine the shape and color information. Experiments were performed on two popular datasets. The results show that decision level fusion achieves better results than either modality when they are used independently. The performance of C-RoPS was further tested using various color spaces e.g., RGB, HSV, YCbCr and CIELAB.