TY - JOUR
T1 - Target detection based on multi-scale feature fusion and cross-channel interactive attention mechanism
AU - Zhao, Chenyang
AU - Song, Yong
AU - Yang, Xin
AU - Zhou, Ya
AU - Yang, Jinqi
N1 - Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
PY - 2023
Y1 - 2023
N2 - Aiming at the problems of complex background, target scale change and small target in aerial image detection, we propose a YOLOv5 target detection algorithm based on multi-scale feature fusion and cross-channel interactive attention mechanism. Including: M-PPM (Multi-scale pyramid pooling module) is designed as a replacement for the SPP (Spatial Pyramid Pooling) structure in YOLOv5, so as to make full use of different scale features to fuse global feature information; CCA (Cross-channel interactive attention mechanism) is designed to realize cross-channel information interaction and utilization, and enhance the network's capability to generalize and fusion efficiency of small target features. Bi-directional Feature Pyramid Network (BiFPN) is utilized to solve scale difference problem in multi-target detection. The proposed algorithm's experimental results is 2.3 % and 1.8 % higher than YOLOv5 on the VisDrone and UAVDT aerial data sets, respectively.
AB - Aiming at the problems of complex background, target scale change and small target in aerial image detection, we propose a YOLOv5 target detection algorithm based on multi-scale feature fusion and cross-channel interactive attention mechanism. Including: M-PPM (Multi-scale pyramid pooling module) is designed as a replacement for the SPP (Spatial Pyramid Pooling) structure in YOLOv5, so as to make full use of different scale features to fuse global feature information; CCA (Cross-channel interactive attention mechanism) is designed to realize cross-channel information interaction and utilization, and enhance the network's capability to generalize and fusion efficiency of small target features. Bi-directional Feature Pyramid Network (BiFPN) is utilized to solve scale difference problem in multi-target detection. The proposed algorithm's experimental results is 2.3 % and 1.8 % higher than YOLOv5 on the VisDrone and UAVDT aerial data sets, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85169454870&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/2562/1/012046
DO - 10.1088/1742-6596/2562/1/012046
M3 - Conference article
AN - SCOPUS:85169454870
SN - 1742-6588
VL - 2562
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 1
M1 - 012046
T2 - 2023 3rd International Conference on Artificial Intelligence and Industrial Technology Applications, AIITA 2023
Y2 - 24 March 2023 through 26 March 2023
ER -
