Open AccessEfficient Object Detection based on Deep Feature Fusion Network
Author(s) -
Bo Zhao,
Shuyun Liu,
Guizhong Liu,
Zhonglin Yang,
Zhiyang Ma,
Huini Fu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1848/1/012005
Subject(s) - computer science , fuse (electrical) , artificial intelligence , object detection , feature (linguistics) , feature extraction , pattern recognition (psychology) , image (mathematics) , convolution (computer science) , deep learning , backbone network , computer vision , scale (ratio) , object (grammar) , artificial neural network , engineering , computer network , linguistics , philosophy , physics , quantum mechanics , electrical engineering
Real-time object detection is crucial for many applications, such as automatic driving, security monitoring. It is vital for these application to perform accurate detection while keeping real-time performance. This paper propose an efficient object detection method based on deep feature fusing strategy. The feature extraction network employs deep convolution neural network to fuse multi-channel input, including colored image, infrared image and motion image. Multiple sources of images can provide complementary information, which is beneficial to accurate object detection. The backbone network is based on darknet-53 while integrating with feature aggression modules to capture features of shallow and deep activation maps. Our network is first trained on large-scale IMAGENET and COCO datasets, and then fine-tuned on small-scale datasets collected in real world. A series of quantitatively and qualitatively experiments are conducted to show superiority and efficiency of our method.