- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 25th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) - Stuttgart, Germany (2018.11.20-2018.11.22)] 2018 25th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) - Vehicle and Pedestrian Recognition Using Multilayer Lidar based on Support Vector Machine
摘要： Moving-object tracking (estimating position and velocity of moving objects) is a key technology for autonomous driving systems and driving assistance systems in mobile robotics and vehicle automation domains. To predict and avoid collisions, the tracking system has to recognize objects as accurately as possible. This paper presents a method for recognizing vehicles (cars and bicyclists) and pedestrians using multilayer lidar (3D lidar). Lidar data are clustered, and eight-dimensional features are extracted from each of clustered lidar data, such as distance from the lidar, velocity, object size, number of lidar-measurement points, and distribution of reflection intensities. A multiclass support vector machine is applied to classify cars, bicyclists, and pedestrians from these features. Experiments using “The Stanford Track Collection” data set allow us to compare the proposed method with a method based on the random forest algorithm and a conventional 26-dimensional feature-based method. The comparison shows that the proposed method improves recognition accuracy and processing time over the other methods. Therefore, the proposed method can work well under low computational environments.
关键词： multiclass classification,support vector machine,low-dimensional features,multilayer lidar,object recognition
更新于2025-09-23 15:22:29
-
Color Constancy in Two-Dimensional and Three-Dimensional Scenes: Effects of Viewing Methods and Surface Texture
摘要： There has been debate about how and why color constancy may be better in three-dimensional (3-D) scenes than in two-dimensional (2-D) scenes. Although some studies have shown better color constancy for 3-D conditions, the role of specific cues remains unclear. In this study, we compared color constancy for a 3-D miniature room (a real scene consisting of actual objects) and 2-D still images of that room presented on a monitor using three viewing methods: binocular viewing, monocular viewing, and head movement. We found that color constancy was better for the 3-D room; however, color constancy for the 2-D image improved when the viewing method caused the scene to be perceived more like a 3-D scene. Separate measurements of the perceptual 3-D effect of each viewing method also supported these results. An additional experiment comparing a miniature room and its image with and without texture suggested that surface texture of scene objects contributes to color constancy.
关键词： color,constancy,3-D perception,object recognition,adaptation
更新于2025-09-23 15:22:29
-
Automatic robot path integration using three-dimensional vision and offline programming
摘要： In manufacturing industries, offline programming (OLP) platforms provide an independent methodology for robot integration using 3D model simulation away from the actual robot cell and production process, reducing integration time and costs. However, traditional OLP platforms still require prior knowledge of the workpiece position in a predefined environment, which requires complex human operations and specific-purpose designs, highly reducing the autonomy of the systems. The presented approach proposes to overcome these problems by defining a novel automated offline programming system (AOLP), which integrates a flexible and intuitive OLP platform with a state-of-the-art autonomous object pose estimation method, to achieve an environment and model independent platform for automatic robotic manufacturing. The autonomous recognition capabilities of the three-dimensional vision system provide the relative position of the workpiece model in the OLP platform, with robustness against clutter, illumination, and object material. After that, the user-friendly OLP platform allows an efficient and automatic path generation, simulation, robot code generation, and robot execution. The proposed system precision and robustness are analyzed and validated in a real-world environment on four different sets of experiment. Finally, the proposed system's features are discussed and compared with other available solutions for practical industrial manufacturing, showing the advantages of the proposed approach. Overall, despite sensor resolution limitations, the proposed system shows a remarkable precision and promising direction towards highly efficient and productive manufacturing solutions.
关键词： Machine vision,Path generation,Industrial manipulator,Automated offline programming,3D object recognition,6D pose estimation
更新于2025-09-23 15:22:29
-
[IEEE SoutheastCon 2018 - St. Petersburg, FL (2018.4.19-2018.4.22)] SoutheastCon 2018 - RGBD-Sphere SLAM
摘要： This article proposes a SLAM algorithm referred to as RGBD-Sphere SLAM. The key innovation of this work is the prototypical system that demonstrates how formal models of 3D geometric shape and appearance can be transformed into generative classification models that detect and recognize these shapes. Object models are specified as shape programs in PSML; a custom-built procedural language for 3D object modeling. Classifiers for each PSML shape are created by simulating how instances of each shape manifest in real-world sensor data, e.g., color images and range images. The proposed RGBD-Sphere SLAM algorithm demonstrates a prototypical example of the PSML program specifies spherical 3D objects having diffuse surface albedos and distinct color appearances. A recognizer uses PSML models of each object’s geometry and appearance to detect instances of these objects within streaming RGBD sensor data. The detected model parameters are then integrated into an RGBD SLAM algorithm; hence the name RGBD-Sphere SLAM. This article describes the PSML programs, the spherical detection and recognition algorithms used, and describes the impact this approach has for improving the performance of RGBD SLAM approaches by incorporating detected objects as landmarks. This is the first example of a prototypical system that externalizes the geometric and appearance modeling to a programming language from which a recognizer is created, and marks an important step towards enabling users to “program” their problem space and allow computers to transform the formal object models, as expressed in PSML, into customized classifiers suited for specific sensor suites, e.g., color imagery and depth imagery.
关键词： object recognition,RGBD,SLAM,3D object modeling,PSML
更新于2025-09-23 15:21:01
-
Canonical Correlation Analysis Regularization: An Effective Deep Multi-View Learning Baseline for RGB-D Object Recognition
摘要： Object recognition methods based on multi-modal data, color plus depth (RGB-D), usually treat each modality separately in feature extraction, which neglects implicit relations between two views and preserves noise from any view to the ?nal representation. To address these limitations, we propose a novel Canonical Correlation Analysis (CCA)-based multi-view Convolutional Neural Network (CNNs) framework for RGB-D object representation. The RGB and depth streams process corresponding images respectively, then are connected by CCA module leading to a common-correlated feature space. In addition, to embed CCA into deep CNNs in a supervised manner, two different schemes are explored. One considers CCA as a regularization term adding to the loss function (CCAR). However, solving CCA optimization directly is neither computationally ef?cient nor compatible with the mini-batch based stochastic optimization. Thus, we further propose an approximation method of CCA regularization (ACCAR), using the obtained CCA projection matrices to replace the weights of feature concatenation layer at regular intervals. Such a scheme enjoys bene?ts of full CCA regularization and is ef?cient by amortizing its cost over many training iterations. Experiments on benchmark RGB-D object recognition datasets have shown that the proposed methods outperform most existing methods using the very same of their network architectures.
关键词： Deep learning,Canonical Correlation Analysis,Multi-view feature learning,RGB-D object recognition
更新于2025-09-23 15:21:01
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Curvature Augmented Deep Learning for 3D Object Recognition
摘要： This paper presents a new method to incorporate shape information into convolutional neural network (CNN)s for 3D object recognition. Voxel CNNs have been very successful with the task of 3D object recognition. However, continuous shape information that is useful for recognition is often lost in their conversion to a voxel representation. We propose a single dimensional feature that can be applied to voxel CNNs. This paper presents a novel rotation-invariant feature based on mean curvature that improves shape recognition for voxel CNNs. We augment the recent voxel CNN Octnet architecture with our feature and demonstrate a 1% overall accuracy increase on the ModelNet10 dataset.
关键词： 3D Object Recognition,Convolutional Neural Networks,Computational Geometry,Deep Learning
更新于2025-09-19 17:15:36
-
The Rotating Glass Illusion: Material Appearance Is Bound to Perceived Shape and Motion
摘要： We report a novel illusion in which a rotating transparent and refractive triangular prism (glass object) is perceived as being made of a specular reflective material (mirror), and simultaneously, its direction of rotation (clockwise or anticlockwise) is also misperceived. Our findings suggest that physical motion strongly influences viewers’ judgements of material in some situations.
关键词： shapes/objects,surfaces/materials,motion,object recognition
更新于2025-09-19 17:15:36
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - R-Covnet: Recurrent Neural Convolution Network for 3D Object Recognition
摘要： Point cloud is a very precise digital format for recording objects in space. Point clouds have received increasing attention lately, due to the higher amount of information it provides compared to images. In this paper, we propose a new deep learning architecture called R-CovNet, designed for 3D object recognition. Unlike previous architectures that usually sample or convert point cloud into three-dimensional grids before processing, R-CovNet does not require any preprocessing. Our main goal is to provide a permutation invariant architecture especially designed for point clouds data of any size. Experiments with well-known benchmarks show that R-CovNet can achieve an accuracy of 92.7%, thus outperforming all the volumetric methods.
关键词： Point Cloud,RNN,3D Object Recognition
更新于2025-09-10 09:29:36
-
Indoor Object Recognition in RGBD Images with Complex-Valued Neural Networks for Visually-Impaired People
摘要： We present a new multi-modal technique for assisting visually-impaired people in recognizing objects in public indoor environment. Unlike common methods which aim to solve the problem of multi-class object recognition in a traditional single-label strategy, a comprehensive approach is developed here allowing samples to take more than one label at a time. We jointly use appearance and depth cues, specifically RGBD images, to overcome issues of traditional vision systems using a new complex-valued representation. Inspired by complex-valued neural networks (CVNNs) and multi-label learning techniques, we propose two methods in order to associate each input RGBD image to a set of labels corresponding to the object categories recognized at once. The first one, ML-CVNN, is formalized as a ranking strategy where we make use of a fully complex-valued RBF network and extend it to be able to solve multi-label problems using an adaptive clustering method. The second method, L-CVNNs, deals with problem transformation strategy where instead of using a single network to formalize the classification problem as a ranking solution for the whole label set, we propose to construct one CVNN for each label where the predicted labels will be later aggregated to construct the resulting multi-label vector. Extensive experiments have been carried on two newly collected multi-labeled RGBD datasets prove the efficiency of the proposed techniques.
关键词： Multi-label learning,Complex-Valued Neural Networks,RGBD,Object Recognition,Visually-impaired people
更新于2025-09-10 09:29:36
-
Quality Inspection of Remote Radio Units using Depth-free Image based Visual Servo with Acceleration Command
摘要： The problem of quality inspection of remote radio unit (RRU) has been approached using the image based visual servo (IBVS) control. A novel computer vision pipeline has been designed which recognized the power port of RRU and tracked it from the stream of images. For control part, a new depth independent interaction matrix was designed which related the depth information with the area of the region of interest (ROI) surrounding the power port. Based on this, an acceleration command was generated to drive the robot’s trajectories. Furthermore, a PD type controller was designed based on the idea of sliding surface in variable structure control. This reduced the number of design parameters to a single parameter. The designed controllers were proven to be stable using the Lyapunov stability analysis. Simulation results and experimental validations were provided to support the research arguments.
关键词： industrial manipulation,object recognition,automatic optical inspection,visual servoing,multi-view object tracking
更新于2025-09-09 09:28:46