Multimodal Convolutional Neural Network for Object Detection Using RGB-D Images

被引:0
作者
Mocanu, Irina [1 ]
Clapon, Cosmin [1 ]
机构
[1] Univ Politehn Bucuresti, Comp Sci Dept, Bucharest, Romania
来源
2018 41ST INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP) | 2018年
基金
欧盟地平线“2020”;
关键词
object detection; convolutional neural network; RGB-D images;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper presents a new convolutional neural network architecture for performing object detection based on RGB-D images. The network is an extension of the Faster-RCNN network where we add an additional input network branch for processing the depth image. The network was evaluated on the SUN RGB-D dataset for object detection and we obtained a positive difference in mAP score of about 4%, compared to the original one.
引用
收藏
页码:307 / 310
页数:4
相关论文
共 18 条
[1]  
[Anonymous], 2016, Lecture Notes in Computer Science, DOI [10.1007/978-3-319-46493-0_38, DOI 10.1007/978-3-319-46493-0_38]
[2]  
[Anonymous], 2016, DEEP SLIDING SHAPES
[3]  
Bo L., 2009, Advances in neural information processing systems, P135
[4]  
Eitel A, 2015, IEEE INT C INT ROBOT, P681, DOI 10.1109/IROS.2015.7353446
[5]   Fast R-CNN [J].
Girshick, Ross .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1440-1448
[6]   Learning Rich Features from RGB-D Images for Object Detection and Segmentation [J].
Gupta, Saurabh ;
Girshick, Ross ;
Arbelaez, Pablo ;
Malik, Jitendra .
COMPUTER VISION - ECCV 2014, PT VII, 2014, 8695 :345-360
[7]  
Janoch A., 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), P1168, DOI 10.1109/ICCVW.2011.6130382
[8]   Using spin images for efficient object recognition in cluttered 3D scenes [J].
Johnson, AE ;
Hebert, M .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (05) :433-449
[9]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[10]  
Lai K, 2011, IEEE INT CONF ROBOT, P1817