RIHOG-BoVWs for Rotation-invariant Human Detection

3rd International Conference on Automation, Control and Robotics Engineering

工业技术;计算机科学;无线电电子学

Liu, Baozhen^1 ; Wu, Hang^2 ; Zhang, Yu^1 ; Xu, Wenlong^1 ; Mu, Kaiyu^1 ; Yao, Yuhua^1

China Astronaut Research and Training Center, Beijing

100094, China^1

Institute of Medical Support Technology, Academy of System Engineering, Academy of Military Sciences, Tianjin

300161, China^2

关键词: Bag-of-visual words;    Description method;    Frequency domains;    Gradient informations;    High-level semantic features;    Histograms of oriented gradients;    Rotation invariant;    Victim detections;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/428/1/012030/pdf
DOI  :  10.1088/1757-899X/428/1/012030

来源: IOP

【 摘 要 】

Rotation-invariant human detection is of vital significance to many applications, including victim detection via a daylight camera on an unmanned aerial vehicle (UAV). With this problem in mind, we propose a powerful rotation-invariant object-level description method, i.e., RIHOG-BoVWs, which is achieved by local-level feature calculation and high-level semantic feature extraction. In local-level feature calculation, we consider Rotation-invariant Histograms of Oriented Gradients (RIHOG) as the local descriptor and project gradient information into the frequency domain, where the rotation-invariant representation vector is constructed. In high-level semantic feature extraction, Bag of Visual Words (BoVWs) model is employed to achieve global description from local features without considering their spatial structures. Experimentally, we first confirm the sufficient discrimination power of the RIHOG-BoVWs on the public Freestyle Motocross dataset, and then demonstrate the high performance of RIHOG-BoVWs on a victim dataset which has varied backgrounds and body postures.