TY - JOUR
T1 - OLCN
T2 - An Optimized Low Coupling Network for Small Objects Detection
AU - Yuan, Yuan
AU - Zhang, Yuanlin
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2022
Y1 - 2022
N2 - In remotely sensed images, it is quite common to run into small objects, such as cars and small storage tanks. However, these small objects are quite easy to get ignored because of the positioning difficulty. Thus, small objects detection is very challenging for the remote sensing object detection task. In order to deal with this challenge, the optimized low coupling network (OLCN) is proposed. First, a low coupling robust regression (LCRR) module improves the positioning accuracy to avoid small objects getting missed. Second, a receptive field optimizing layer (RFOL) is proposed to train better classifiers by providing more accurate regions of interest (RoIs). Experimental results on the public dataset HRRSD verify the effectiveness of the proposed OLCN. Small objects detection metric is improved from 5.70% of the baseline to 22.90% of the OLCN. Moreover, the proposed method has reached state-of-the-art performance on the HRRSD dataset.
AB - In remotely sensed images, it is quite common to run into small objects, such as cars and small storage tanks. However, these small objects are quite easy to get ignored because of the positioning difficulty. Thus, small objects detection is very challenging for the remote sensing object detection task. In order to deal with this challenge, the optimized low coupling network (OLCN) is proposed. First, a low coupling robust regression (LCRR) module improves the positioning accuracy to avoid small objects getting missed. Second, a receptive field optimizing layer (RFOL) is proposed to train better classifiers by providing more accurate regions of interest (RoIs). Experimental results on the public dataset HRRSD verify the effectiveness of the proposed OLCN. Small objects detection metric is improved from 5.70% of the baseline to 22.90% of the OLCN. Moreover, the proposed method has reached state-of-the-art performance on the HRRSD dataset.
KW - Convolutional neural networks (CNNs)
KW - object localization
KW - remote sensing
KW - small object detection
UR - http://www.scopus.com/inward/record.url?scp=85118527238&partnerID=8YFLogxK
U2 - 10.1109/LGRS.2021.3122190
DO - 10.1109/LGRS.2021.3122190
M3 - 文章
AN - SCOPUS:85118527238
SN - 1545-598X
VL - 19
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
ER -