Near Real-Time Object Recognition for Pepper Based on Deep Neural Networks Running on a Backpack

被引：2

作者：

Reyes, Esteban ^{[1
]}

Gomez, Cristopher ^{[1
]}

Norambuena, Esteban ^{[1
]}

Ruiz-del-Solar, Javier ^{[1
,2
]}

机构：

[1] Univ Chile, Dept Elect Engn, Santiago, Chile

[2] Univ Chile, Adv Min Technol Ctr, Santiago, Chile

来源：

ROBOT WORLD CUP XXII, ROBOCUP 2018 | 2019年 / 11374卷

关键词：

Pepper robot; YOLO; Jetson TK1; ROS;

D O I：

10.1007/978-3-030-27544-0_24

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The main goal of this work is to provide Pepper with a near real-time object recognition system based on deep neural networks. The proposed system is based on YOLO (You Only Look Once), a deep neural network that is able to detect and recognize objects robustly and at a high speed. In addition, considering that YOLO cannot be run in the Pepper's internal computer in near real-time, we propose to use a Backpack for Pepper, which holds a Jetson TK1 card and a battery. By using this card, Pepper is able to robustly detect and recognize objects in images of 320 x 320 pixels at about 5 frames per second.

引用

页码：287 / 298

页数：12

共 50 条

[1] Evolving Efficient Deep Neural Networks for Real-time Object Recognition
Lan, Gongjin
de Vries, Lucas
Wang, Shuai
[J]. 2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 2571 - 2578
[2] Real-Time Object Recognition Algorithm Based on Deep Convolutional Neural Network
Yang, Lihong
Wang, Liewei
Wu, Shuo
[J]. 2018 IEEE 3RD INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA ANALYSIS (ICCCBDA), 2018, : 331 - 335
[3] Real-Time Emotional Recognition for Sociable Robotics Based on Deep Neural Networks Ensemble
Benamara, Nadir Kamel
Val-Calvo, Mikel
Ramon Alvarez-Sanchez, Jose
Diaz-Morcillo, Alejandro
Ferrandez Vicente, Jose Manuel
Fernandez-Jover, Eduardo
Stambouli, Tarik Boudghene
[J]. UNDERSTANDING THE BRAIN FUNCTION AND EMOTIONS, PT I, 2019, 11486 : 171 - 180
[4] Real-time Activity Recognition on Smartphones Using Deep Neural Networks
Zhang, Licheng
Wu, Xihong
Luo, Dingsheng
[J]. IEEE 12TH INT CONF UBIQUITOUS INTELLIGENCE & COMP/IEEE 12TH INT CONF ADV & TRUSTED COMP/IEEE 15TH INT CONF SCALABLE COMP & COMMUN/IEEE INT CONF CLOUD & BIG DATA COMP/IEEE INT CONF INTERNET PEOPLE AND ASSOCIATED SYMPOSIA/WORKSHOPS, 2015, : 1236 - 1242
[5] Deep Convolutional Neural Networks Object Detector for Real-Time Waste Identification
Melinte, Daniel Octavian
Travediu, Ana-Maria
Dumitriu, Dan N.
[J]. APPLIED SCIENCES-BASEL, 2020, 10 (20): : 1 - 18
[6] Optimized Deep Neural Networks for Real-Time Object Classification on Embedded GPUs
Rizvi, Syed Tahir Hussain
Cabodi, Gianpiero
Francini, Gianluca
[J]. APPLIED SCIENCES-BASEL, 2017, 7 (08):
[7] Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning
Staroverov, Aleksey
Yudin, Dmitry A.
Belkin, Ilya
Adeshkin, Vasily
Solomentsev, Yaroslav K.
Panov, Aleksandr I.
[J]. IEEE ACCESS, 2020, 8 : 195608 - 195621
[8] Meta-neural-network for real-time and passive deep-learning-based object recognition
Jingkai Weng
Yujiang Ding
Chengbo Hu
Xue-Feng Zhu
Bin Liang
Jing Yang
Jianchun Cheng
[J]. Nature Communications, 11
[9] Meta-neural-network for real-time and passive deep-learning-based object recognition
Weng, Jingkai
Ding, Yujiang
Hu, Chengbo
Zhu, Xue-Feng
Liang, Bin
Yang, Jing
Cheng, Jianchun
[J]. NATURE COMMUNICATIONS, 2020, 11 (01)
[10] Implementation of Deep Learning Neural Network for Real-time Object Recognition in OpenCL Framework
Luo, Yukui
Li, Shuai
Sun, Kuangyuan
Renteria, Raul
Choi, Ken
[J]. PROCEEDINGS INTERNATIONAL SOC DESIGN CONFERENCE 2017 (ISOCC 2017), 2017, : 298 - 299

← 1 2 3 4 5 →