TY - JOUR
T1 - Jointly network image processing
T2 - multi-task image semantic segmentation of indoor scene based on CNN
AU - Huang, Li
AU - He, Meiling
AU - Tan, Chong
AU - Du, Jiang
AU - Li, Gongfa
AU - Yu, Hui
N1 - Funding Information:
This work was supported by grants of the National Natural Science Foundation of China (grant nos. 51575407, 51505349, 61733011, 41906177), the Grants of Hubei Provincial Department of Education (D20191105), the Grants of National Defense Pre-Research Foundation of Wuhan University of Science and Technology (GF201705), the Grants of Scientific Research Project of Education Department of Hubei Province (B2019008) and Open Fund of the Key Laboratory for Metallurgical Equipment and Control of Ministry of Education in Wuhan University of Science and Technology (MECOF2019B05).
Publisher Copyright:
© The Institution of Engineering and Technology 2020.
PY - 2020/12/10
Y1 - 2020/12/10
N2 - Image semantic segmentation has always been a research hotspot in the field of robots. Its purpose is to assign different semantic category labels to objects by segmenting different objects. However, in practical applications, in addition to knowing the semantic category information of objects, robots also need to know the position information of objects to complete more complex visual tasks. Aiming at a complex indoor environment, this study designs an image semantic segmentation network framework of joint target detection. Using the parallel operation of adding semantic segmentation branches to the target detection network, it innovatively implements multi-vision task combining object classification, detection and semantic segmentation. By designing a new loss function, adjusting the training using the idea of transfer learning, and finally verifying it on the self-built indoor scene data set, the experiment proves that the method in this study is feasible and effective, and has good robustness.
AB - Image semantic segmentation has always been a research hotspot in the field of robots. Its purpose is to assign different semantic category labels to objects by segmenting different objects. However, in practical applications, in addition to knowing the semantic category information of objects, robots also need to know the position information of objects to complete more complex visual tasks. Aiming at a complex indoor environment, this study designs an image semantic segmentation network framework of joint target detection. Using the parallel operation of adding semantic segmentation branches to the target detection network, it innovatively implements multi-vision task combining object classification, detection and semantic segmentation. By designing a new loss function, adjusting the training using the idea of transfer learning, and finally verifying it on the self-built indoor scene data set, the experiment proves that the method in this study is feasible and effective, and has good robustness.
UR - http://www.scopus.com/inward/record.url?scp=85090007952&partnerID=8YFLogxK
U2 - 10.1049/iet-ipr.2020.0088
DO - 10.1049/iet-ipr.2020.0088
M3 - Article
AN - SCOPUS:85090007952
SN - 1751-9659
VL - 14
SP - 3689
EP - 3697
JO - IET Image Processing
JF - IET Image Processing
IS - 15
ER -