Abstract
To ensure public safety, the government has placed a lot of cameras in public places and used them to monitor key targets. In target detection, pedestrian target detection is undoubtedly a research hotspot. How to realize the high efficiency of pedestrian detection is the focus of this field. As a result, this research suggests an algorithm for pedestrian target detection in public spaces that is based on representation learning and similarity learning. The algorithm uses representation learning to extract pedestrian features and Singular Value Decomposition (SVD) to build a more trustworthy Feature Extraction Network (FEN). In addition, the improved Softmax function is used for similarity learning, and the K-Nearest Neighbor algorithm (KNN is applied for image retrieval to fgreatly increase the identification accuracy of pedestrians. The algorithm proposed in this study only needs two rounds of constraint training to achieve the best state. The mean absolute error and mean square error are 0.31 and 9.38, respectively. Its Relative Robustness (RR), Relative Generalization (RG) and Relative Scalability (RS) are excellent. In the final practical test, the model finally achieved 98.8% accuracy and 2.1% false positive rate. The proposed algorithm in this study has good application value in pedestrian target detection, and can better promote the development of social public safety