TY - JOUR
T1 - Multi-Scale Object Detection Using Feature Fusion Recalibration Network
AU - Guo, Ziyuan
AU - Zhang, Weimin
AU - Liang, Zhenshuo
AU - Shi, Yongliang
AU - Huang, Qiang
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2020
Y1 - 2020
N2 - In this paper, the object detection algorithm based on deep learning running on the robot platform is studied and optimized. The p has high requirements for the detection efficiency and scale invariance of the algorithm. In order to improve the detection accuracy on all scales and keep the balance between speed and accuracy, we propose the following methods: Aiming at the problem of low detection accuracy of object detection algorithm for scale changing objects, the traditional image pyramid technology of computer vision is used to verify its effectiveness in improving the detection accuracy of the algorithm for scale changing objects. Then, by embedding the image pyramid into the network, the memory consumption caused by the traditional pyramid is reduced, and the detection accuracy of the algorithm for different scale objects is improved. A new feature fusion recalibration structure is designed. Feature fusion can fuse the low-level location information and high-level semantic information. The recalibration assigns the importance weight of the channel of the feature maps. This structure can effectively improve the detection accuracy of the algorithm at all scales without losing too much speed. We apply these two structures to YOLO. The accuracy of the improved algorithm has a significant improvement and the algorithm can run at 16 FPS on a TITAN Xp GPU.
AB - In this paper, the object detection algorithm based on deep learning running on the robot platform is studied and optimized. The p has high requirements for the detection efficiency and scale invariance of the algorithm. In order to improve the detection accuracy on all scales and keep the balance between speed and accuracy, we propose the following methods: Aiming at the problem of low detection accuracy of object detection algorithm for scale changing objects, the traditional image pyramid technology of computer vision is used to verify its effectiveness in improving the detection accuracy of the algorithm for scale changing objects. Then, by embedding the image pyramid into the network, the memory consumption caused by the traditional pyramid is reduced, and the detection accuracy of the algorithm for different scale objects is improved. A new feature fusion recalibration structure is designed. Feature fusion can fuse the low-level location information and high-level semantic information. The recalibration assigns the importance weight of the channel of the feature maps. This structure can effectively improve the detection accuracy of the algorithm at all scales without losing too much speed. We apply these two structures to YOLO. The accuracy of the improved algorithm has a significant improvement and the algorithm can run at 16 FPS on a TITAN Xp GPU.
KW - Multi-scale object detection
KW - convolutional neural network
KW - feature fusion
KW - feature recalibration
UR - http://www.scopus.com/inward/record.url?scp=85082533525&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.2980737
DO - 10.1109/ACCESS.2020.2980737
M3 - Article
AN - SCOPUS:85082533525
SN - 2169-3536
VL - 8
SP - 51664
EP - 51673
JO - IEEE Access
JF - IEEE Access
M1 - 9035489
ER -