본문 바로가기

Robust approach to supervised deep neural network training for real-time object classification in cluttered indoor environment

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q2
저널
APPLIED SCIENCES-BASEL11(15) · 2021
피인용
Web of Science 3Scopus 4
FWCI (Scopus)
0.22
JCR IF
JCR 2020 2.679
ISSN
2076-3417

저자

  1. 엔델 제메츄 베다바제1저자Pusan Natl Univ, Dept Aerosp Engn, Busan 46241, South Korea
  2. Tullu, AberaSejong Univ, Dept Aerosp Engn, 209 Neungdong Ro, Seoul 05006, South Korea
  3. 시하영Pusan Natl Univ, Dept Aerosp Engn, Busan 46241, South Korea
  4. 강범수교신저자Pusan Natl Univ, Dept Aerosp Engn, Busan 46241, South Korea

초록

© 2021 by the authors. Licensee MDPI, Basel, Switzerland.Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

키워드

Convolutional neural networkDeep learningNetwork architectureObject classification

식별자

Scopus EID
2-s2.0-85112646975
WoS UID
000681906400001