基于卷积-递归神经网络和费舍尔向量的RGB-D物体识别

Object Recognition for RGB-D Images Based on Convolutional-Recursive Neural Network and Fisher Vector

综合利用彩色和深度信息,采用多数据模式的特征提取策略,提出一种基于卷积-递归神经网络和费舍尔向量的RGB-D物体识别方法.对于彩色图像和深度图像,分别利用卷积-递归神经网络和卷积-费舍尔向量-递归神经网络提取物体的纹理及形状特征.为了更加全面的获取物体信息的特征表述,引入了灰度图像和表面法向量作为原始数据的补充,并利用卷积-递归神经网络提取特征.最后,将4种数据模式下提取到的特征融合起来,输入到softmax分类器中实现RGB-D物体识别.在标准的RGB-D数据库中对算法进行验证,所提算法可以有效提高物体识别率.

Combining the color and depth information, a novel RGB-D object recognition method for RGB-D images based on convolutional-recursive neural network and fisher vector with multiple modalities extraction strategy is proposed. For the original color image and depth map, the convolutional-recursive neural network and convolutional-fisher vector-recursive neural network are used to exact the texture and shape features respectively. In order to capture more comprehensive features for object recognition, the gray image and the surface normal are introduced in our model, and the convolutional-recursive neural network is utilized to explore the corresponding features. At last, these four features extracted from different data modalities are integrated into the softmax classifier to achieve RGB-D object recognition. The proposed algorithm is verified in the standard RGB-D database. Experimental results show that the proposed algorithm achieves higher recognition rate.