Neural network based 2D/3D fusion for robotic object recognition
نویسندگان
چکیده
We present a neural network based fusion approach for realtime robotic object recognition which integrates 2D and 3D descriptors in a flexible way. The presented recognition architecture is coupled to a real-time segmentation step based on 3D data, since a focus of our investigations is real-world operation on a mobile robot. As recognition must operate on imperfect segmentation results, we conduct tests of recognition performance using complex everyday objects in order to quantify the overall gain of performing 2D/3D fusion, and to discover where it is particularly useful. We find that the fusion approach is most powerful when generalization is required, for example to significant viewpoint changes and a large number of object categories, and that a perfect segmentation is apparently not a necessary prerequisite for successful discrimination.
منابع مشابه
Hand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملFeature based 3D Object Recognition using Artificial Neural Networks
The recognition of objects is one of the main goals for computer vision research. This paper formulates and solves the problem of three-dimensional (3D) object recognition for Polyhedral objects. A multiple view of 2D intensity images are taken from multiple cameras and used to model the 3D objects. The proposed methodology is based on extracting set of features from the 2D images which include...
متن کامل3D Convolutional Neural Network for Object Recognition
3D Object recognition is an important task in computer vision applications. After the success of convolutional neural networks for object recognition in 2D images, many researchers have designed convolution neural network (CNN) for 3D object recognition. The state of art methods provide favourable results. However, the availability of large/dynamic 3D dataset and computational complexity of CNN...
متن کاملRGB-D Object Recognition Using Deep Convolutional Neural Networks
We address the problem of object recognition from RGB-D images using deep convolutional neural networks (CNNs). We advocate the use of 3D CNNs to fully exploit the 3D spatial information in depth images as well as the use of pretrained 2D CNNs to learn features from RGB-D images. There exists currently no large scale dataset available comprising depth information as compared to those for RGB da...
متن کاملApplication of Combined Local Object Based Features and Cluster Fusion for the Behaviors Recognition and Detection of Abnormal Behaviors
In this paper, we propose a novel framework for behaviors recognition and detection of certain types of abnormal behaviors, capable of achieving high detection rates on a variety of real-life scenes. The new proposed approach here is a combination of the location based methods and the object based ones. First, a novel approach is formulated to use optical flow and binary motion video as the loc...
متن کامل