RGB-D Training for Convolutional Neural Network with Final Fuzzy Layer for Depth Weighting
نویسندگان
چکیده
This paper presents training of novel hybrid network based on three deep convolutional neural network architectures applied to object recognition, based on the depth information supplied for a RGBD camera. For this case, the depth information allows to set the dataset of training images of each network, its architecture and its characteristics, generating a dynamic recognition application by variation of the image capture point, whose final layer is determined by a diffuse inference system. The general architecture designed allows an efficient object recognition applicable to robotic mobile agents, whose perspective of the object varies when approaching or moving away from them, showing an overall performance of 90.19%.
منابع مشابه
A Convolutional Neural Network based on Adaptive Pooling for Classification of Noisy Images
Convolutional neural network is one of the effective methods for classifying images that performs learning using convolutional, pooling and fully-connected layers. All kinds of noise disrupt the operation of this network. Noise images reduce classification accuracy and increase convolutional neural network training time. Noise is an unwanted signal that destroys the original signal. Noise chang...
متن کاملPDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detection
Fully convolutional neural networks (FCNs) have shown outstanding performance in many computer vision tasks including salient object detection. However, there still remains two issues needed to be addressed in deep learning based saliency detection. One is the lack of tremendous amount of annotated data to train a network. The other is the lack of robustness for extracting salient objects in im...
متن کاملHand 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 کاملDepth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs
Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that ...
متن کاملCombining Models from Multiple Sources for RGB-D Scene Recognition
Depth can complement RGB with useful cues about object volumes and scene layout. However, RGB-D image datasets are still too small for directly training deep convolutional neural networks (CNNs), in contrast to the massive monomodal RGB datasets. Previous works in RGB-D recognition typically combine two separate networks for RGB and depth data, pretrained with a large RGB dataset and then fine ...
متن کامل