TY  - EJOU
AU  - Zhang, Dengyong 
AU  - Hu, Jiawei 
AU  - Li, Feng 
AU  - Ding, Xiangling 
AU  - Sangaiah, Arun Kumar 
AU  - Sheng, Victor S. 

TI  - Small Object Detection via Precise Region-Based Fully Convolutional Networks
T2  - Computers, Materials \& Continua

PY  - 2021
VL  - 69
IS  - 2
SN  - 1546-2226

AB  - In the past several years, remarkable achievements have been made in the field of object detection. Although performance is generally improving, the accuracy of small object detection remains low compared with that of large object detection. In addition, localization misalignment issues are common for small objects, as seen in GoogLeNets and residual networks (ResNets). To address this problem, we propose an improved region-based fully convolutional network (R-FCN). The presented technique improves detection accuracy and eliminates localization misalignment by replacing position-sensitive region of interest (PS-RoI) pooling with position-sensitive precise region of interest (PS-Pr-RoI) pooling, which avoids coordinate quantization and directly calculates two-order integrals for position-sensitive score maps, thus preventing a loss of spatial precision. A validation experiment was conducted in which the Microsoft common objects in context (MS COCO) training dataset was oversampled. Results showed an accuracy improvement of  for object detection tasks and an increase of  for small objects.
KW  - Small object detection; precise R-FCN; PS-Pr-RoI pooling; two-stage detector

DO  - 10.32604/cmc.2021.017089