Pedestrian detecting method based on improved HOG feature and PCA (Principal Component Analysis)

Abstract

The invention relates to a pedestrian detecting method based on improved HOG feature and PCA (Principal Component Analysis). The method comprises the following steps: extracting a sample feature by using a feature extracting algorithm for HOG feature cascaded PCA in a concentrated area of gradient information of a pedestrian in a sample image; training a SVM classifier by utilizing the feature extracted from the sample; and utilizing a feature extracting method to extract a feature vector for a detected sample and utilizing the trained and obtained SVM classifier to detect the pedestrian. The invention provides a pedestrian detecting method based on improved HOG feature and PCA, with the capabilities of efficiently reducing the training speed and reducing the false detecting rate and missing report rate.

Description

technical field [0001] The invention relates to the technical field of intelligent monitoring, in particular to a pedestrian detection method. Background technique [0002] The current classification method of pedestrian detection technology is mainly divided into two aspects, one is the template matching method, and the other is to train the classifier based on different pedestrian characteristics. The current pedestrian detection system generally adopts the second method. The HOG feature has become the mainstream feature extraction algorithm in pedestrian detection because it can well represent the appearance and shape of local objects and is not sensitive to illumination. The main disadvantage of HOG is that for a sample set of specified size, the dimensionality of HOG features is too high, resulting in low training speed. Currently, the commonly used classification algorithms mainly include AdaBoost cascade classifier and SVM classifier. For example, the patent applica...

AI Technical Summary

Problems solved by technology

The algorithm cascades two classifiers, which can reduce the false detection rate of pedestrians, but the cascade of the two classifiers obviously increases the complexity of the algorithm and reduces the detection speed, and does not consider the situation of missing pedestrians, and Can not really improve the detection rate of pedestrians

Moreover, the algorithm is proposed based on the vehicle-mounted pedestrian detection system. The processing of the region of interest in the image has certain limitations, such as removing the sky and ground scenes of the upper and lower pixels of the image, and the scenes on both sides of the road with the left and right pixels of the image, etc.

The scenes captured by the sensors in many occasions are not the same, so the application of this algorithm has certain limitations

Images