An Improved YOLO Feature Extraction Algorithm and Its Application to Privacy Situation Detection of Social Robots

To address the limitation of YOLO algorithm in recognizing small objects and information loss during feature extraction, we propose FYOLO, an improved feature extraction algorithm based on YOLO. The algorithm uses a novel neural network structure inspired by the deformable parts model (DPM) and region-based fully convolutional networks (R-FCN). A sliding window merging algorithm based on region proposal networks (RPN) is then combined with the neural network to form the FYOLO algorithm. To evaluate the performance of the proposed algorithm, we develop a social robot platform for privacy situation detection. We consider six types of situations in a smart home and prepare three datasets including training dataset, validation dataset, and test dataset. Experimental parameters such as training step and learning rate are set in terms of their relationships with the prediction accuracy. Extensive privacy situation detection experiments on the social robot show that FYOLO is capable of recognizing privacy situations with an accuracy of 94.48 %, indicating the good robustness of our FYOLO algorithm. Finally, the comparison results between FYOLO and YOLO show that the proposed FYOLO outperforms YOLO in recognition accuracy. Copyright © 2018 Acta Automatica Sinica. All rights reserved.