Rotational Projection Statistics for 3D Local Surface Description and Object Recognition

The local reference frame (LRF), as an independent coordinate system constructed on the local 3D surface, is broadly employed in 3D local feature descriptors. The benefits of the LRF include rotational invariance and full 3D spatial information, thereby greatly boosting the distinctiveness of a 3D feature descriptor. There are numerous LRF methods in the literature; however, no comprehensive study comparing their repeatability and robustness performance under different application scenarios and nuisances has been conducted. This paper evaluates eight state-of-the-art LRF proposals on six benchmarks with different data modalities (e.g., LiDAR, Kinect, and Space Time) and application contexts (e.g., shape retrieval, 3D registration, and 3D object recognition). In addition, the robustness of each LRF to a variety of nuisances, including varying support radii, Gaussian noise, outliers (shot noise), mesh resolution variation, distance to boundary, keypoint localization error, clutter, occlusion, and partial overlap, is assessed. The experimental study also measures the performance under different keypoint detectors, descriptor matching performance when using different LRFs and feature representation combinations, as well as computational efficiency. Considering the evaluation outcomes, we summarize the traits, advantages, and current limitations of the tested LRF methods.

Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding

This paper proposes a method for recognition and classification of 3D objects using 2D moments and HMLP network. The 2D moments are calculated based on 2D intensity images taken from multiple cameras that have been arranged using multiple views technique. 2D moments are commonly used for 2D pattern recognition. However, the current study proves that with some adaptation to multiple views technique, 2D moments are sufficient to model 3D objects. In addition, the simplicity of 2D moment's calculation reduces the processing time for feature extraction, thus decreases the recognition time. The 2D moments were then fed into a neural network for classification of the 3D objects. In the current study, hybrid multi-layered perceptron (HMLP) network is proposed to perform the classification. Two distinct groups of objects that are polyhedral and free-form objects were used to access the performance of the proposed method. The recognition results show that the proposed method has successfully classified the 3D object with the accuracy of up to 100%.

Abstract3D object recognition has great research and application value in the fields of automatic drive, virtual reality, and commercial manufacturing. Although various deep models have been exploited and achieved remarkable results for 3D object recognition, their computational cost is too high for most mobile applications. This paper combines edge computing and 3D object recognition into a powerful and efficient framework. It consists of a cloud-based rendering stage and a terminal-based recognition stage. In the first stage, inspired by the cloud-based rendering technique, we upload the 3D object data from the mobile device to the edge cloud server for multi-view rendering. The rendering stage utilizes the powerful computing resource in the edge cloud server to generate multiple view images of the given 3D object from different views by parallel high-quality rendering. During the terminal-based recognition stage, we integrate a lightweight CNN architecture and a neural network quantization technique into a 3D object recognition model based on the multiple images rendered in the edge cloud server, which can be executed fast in the mobile device. To reduce the cost of network training, we propose a novel semi-supervised 3D deep learning method with fewer labeled samples. Experiments demonstrate that our method achieves competitive performance compared to the state-of-the-art methods with low latency running in the mobile edge environment.

Inertial reference frames spanning approximately 10°–30° square on the sky and capable of locating objects to few-hundred microarcsecond accuracies are useful for a broad class of astrometric measurements. Deep space tracking and general relativistic angular deflection experiments are examples of astrometric measurements which can profitably reference the positions and/or motions of objects to a field of radio sources in a local frame. A method for defining local inertial reference frames has been developed based on Very Long Baseline Interferometry (VLBI) measurements of extragalactic radio sources. By observing the radio emission from the object to be located in the frame, as well as that from about five radio sources which define the frame, dominant systematic astrometric errors can be minimized through parameter estimation. The entire reference frame measurement is of the order of 30 minutes including all the sources in a frame. The limiting error for single-epoch position determination in a local frame is the unknown structure of both target and reference objects. Structure can cause systematic milliarcsecond-level errors. The limiting error for epoch-to-epoch differential position measurements is tropospheric fluctuations, assuming that the radio source structures do not change from one epoch to the next. Preliminary results of an epoch-to-epoch measurement of relativistic gravitational deflection by Jupiter, in which the total deflection was about 600 microarcseconds, suggest that the local reference frame is stable at the 240-microarcsecond level over twelve days. Data have been taken at longer time intervals to determine the annual stability of the frames. At the time of preparation of these proceedings, those data have not yet been analyzed.

For many practical applications in industrial and medical fields, 3D object recognition has become an actively investigative field. In general, 3D object recognition system can be completed through two stages. Firstly, we use 3D reconstruction of input data to get object expression. Then we use 3D invariant to identify objects. In order to promote further development of this field, this paper summarizes the 3D object recognition technology research, and introduces typical methods of modern 3D object recognition, the concepts of 3D reconstruction, 3D invariants. In the process of 3D object recognition, feature line extraction, 3D invariant calculation, matching strategy, 3D object recognition fields are reviewed. The first section presents the significance of 3D object recognition. The second section presents the development of object recognition. The third section presents the double viewpoint of 3D reconstruction. The fourth section presents the 3D reconstruction of image processing. The fifth section presents the 3D invariant technology. The sixth section presents the problems and development direction.

We propose a framework for three-dimensional (3D) object recognition and classification in very low illumination environments using convolutional neural networks (CNNs). 3D images are reconstructed using 3D integral imaging (InIm) with conventional visible spectrum image sensors. After imaging the low light scene using 3D InIm, the 3D reconstructed image has a higher signal-to-noise ratio than a single 2D image, which is a result of 3D InIm being optimal in the maximum likelihood sense for read-noise dominant images. Once 3D reconstruction has been performed, the 3D image is denoised and regions of interest are extracted to detect 3D objects in a scene. The extracted regions are then inputted into a CNN, which was trained under low illumination conditions using 3D InIm reconstructed images, to perform object recognition. To the best of our knowledge, this is the first report of utilizing 3D InIm and convolutional neural networks for 3D training and 3D object classification under very low illumination conditions.

To improve the performance of appearance-based three-dimensional object recognition system, we propose to extract Hupsilas moment invariants, affine moment invariants and color moments from the 2D images of 3D objects. Hupsilas and affine moment invariants have the properties of rotation, scale, translation invariance and affine transformation invariance respectively for the objects in images, and color moments are used to distinguish objects of similar shape and different color. Then these moments compose a 1-dimensional feature vector of 11 components for each 2D image of 3D objects and presented to the BP neural network for training. The trained network can be used to recognize 3D objects when provided the feature vectors of unseen views. We assessed our method based on both the original and noise corrupted COIL-100 3D objects dataset and achieved 100% correct rate of recognition when training images were presented every 10 degrees.

This paper proposes an effective method for recognition and classification of 3D objects using multiple views technique and neural networks system. In the processing stage, we propose to use 2D moment invariants as the features for modeling 3D objects. 2D moments have been commonly used for 2D object recognition. However, we have proved that with some adaptation to multiple views technique, 2D moments are sufficient to model 3D objects. In addition, the simplicity of 2D moments calculation reduces the processing time for feature extraction, hence increases the system efficiency. In the recognition stage, we propose a cascaded multilayered perceptron (c-MLP) network for matching and classification. The c-MLP contains two MLP networks which are arranged in a serial combination. This proposed method has been tested using two groups of object, polyhedral and free-form objects. We also compare our method with standard MLP network. Our results show that the proposed method can successfully be applied to 3D object recognition. In addition, the proposed network also achieved better performance and faster convergence rate compared to the than standard MLP

3D object recognition is a longstanding task in computer vision and has shown wide applications in computer aided design, virtual reality, etc. Current state-of-the-art methods mainly focus on 3D object representation for recognition. Concerning the multi-modal representations in practice, how to effectively combine such multi-modal information for recognition is still a challenging and urgent requirement. In this paper, we aim to conduct 3D object recognition using multi-modal information through a cross diffusion process on multi-hypergraph structure. Given multi-modal representations of 3D objects, the correlation among these objects is formulated using the multi-hypergraph structure each representation separately, which is able to model complex relationship among objects. To combine multi-modal representation, we propose a cross diffusion process on multi-hypergraph, in which the label information is propagated from multiple hypergraphs alternatively. In this way, the multi-modal information can be jointly combined through this cross diffusion process in multi-hypergraph structure. We have applied the proposed method in 3D object recognition using multiple representations. To evaluate the performance of the proposed cross diffusion method, we provide extensive experiments on two public 3D object datasets. Experimental results demonstrate that the proposed method can achieve satisfied multi-modal combination performance and outperform the current state-of-the-art methods.

3D object recognition is proven superior compared to its 2D counterpart with numerous implementations, making it a current research topic. Local based proposals specifically, although being quite accurate, they limit their performance on the stability of their local reference frame or axis (LRF/A) on which the descriptors are defined. Additionally, extra processing time is demanded to estimate the LRF for each local patch. We propose a 3D descriptor which overrides the necessity of a LRF/A reducing dramatically processing time needed. In addition robustness to high levels of noise and non-uniform subsampling is achieved. Our approach, namely Histogram of Distances is based on multiple L2-norm metrics of local patches providing a simple and fast to compute descriptor suitable for time-critical applications. Evaluation on both high and low quality popular point clouds showed its promising performance.

Three-Dimensional (3D) object recognition has been receiving more and more attention in the field of Computer Vision, as the development of AI algorithms and advancements of hardware components allow for better results nowadays more than ever before. Neural Networks are used to better classify different types of objects, these are being fed with pre-processed 3D objects represented in a 2D domain for better highlighting the important features and for a better performance. In this paper, we propose a strategy of feeding 2D representations of 3D meshes made by using different types of slicing to a CNN. In this way, we want to minimize the information loss and the redundancy the data suffers going from a 3D representation to a 2D one. To assess the results, we used Princeton's state-of-the-art ModelNet10 dataset, consisting of 4899 3D objects divided into 10 categories.

Three-dimensional object recognition using joint fractional Fourier transform correlators with the help of digital Fresnel holography

Once the human vision system has seen a 3D object from a few different viewpoints, depending on the nature of the object, it can generally recognize that object from new arbitrary viewpoints. This useful interpolative skill relies on the highly complex pattern matching systems in the human brain, but the general idea can be applied to a computer vision recognition system using comparatively simple machine learning techniques. An approach to the recognition of 3D objects in arbitrary pose relative the the vision equipment given only a limited training set of views is presented. This approach involves computing a disparity map using stereo cameras, extracting a set of features from the disparity map, and classifying it via a fuzzy associative map to a trained object.

In this paper, we propose a modularized architecture for a robot arm object fetching system integrated with 3D CAD-model based object recognition system that can cope with objects in random types and poses. The interface and the core functionality of each module in the architecture are discussed in detail. Implementation of each module is also conducted. Furthermore, the assumptions and the working conditions behind each module are carefully examined. We develop the system based on our previous work and enhance the recognition module. To proof the feasibility of our architecture, 3D object recognition and fetching demonstration are successfully implemented, and the result of object recognition, teaching by touching, and fast grasp synthesis are successfully demonstrated.