A Pedestrian Recognition Method Based on Positive and Negative Generalized Max Pooling

Abstract

The invention discloses a pedestrian identification method based on positive and negative generalized maximum pooling. features, and encodes local features through a deep hierarchical encoding method composed of spatial aggregation restricted Boltzmann machines to form the feature encoding vector of the training sample, and then uses the positive and negative generalized maximum pooling method to obtain the high-level image feature representation vector , input the obtained feature data into the support vector machine classifier to complete the training; preprocess the pedestrian image to be tested to obtain the test sample, and obtain the feature representation vector of the test sample in the same way; input the feature representation vector of the test sample into the training The completed SVM classifier, identifying whether the test image is a pedestrian or a non-pedestrian. The invention can improve the accuracy of pedestrian identification and enhance the robustness of the pedestrian identification algorithm.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a pedestrian recognition method based on positive and negative generalized maximum pooling. Background technique [0002] Pedestrian recognition has broad application prospects in intelligent transportation systems and intelligent monitoring systems, but it is still an open problem in the field of computer vision, because pedestrian appearance and background environment, such as clothing, posture, lighting, viewing angle, etc., vary greatly. Coupled with the complex background, the recognition accuracy is not high. [0003] Feature pooling is becoming more and more important in the entire pedestrian detection system. The idea of ​​feature pooling comes from the study of complex cells in the striate cortex, and it has become a common method for image / video feature representation and encoding. The basic pooling methods for pedestrian recognition are max poolin...

AI Technical Summary

Problems solved by technology

Sum pooling is suitable for any encoding, however, due to the fact that non-informative descriptors frequently affect the result representation, while potential highly informative descriptors have little effect on the result representation, sum pooling lacks discriminative power

Average pooling is a quantization method that considers all elements of the pooled area in average pooling. However, this method easily loses the spatial information of each block.

l p Pooling has ideal discriminative pooling results, l p Pooling is to model it in a more exhaustive way, but l p The pooling stage algorithm needs further research

Images