A mixed extraction method of large data for pedestrian local features

Abstract

The invention discloses a large data hybrid extraction method of pedestrian local features, comprising: step 1: building a pedestrian motion database; step 2: extracting pedestrian detection frame images of the same pedestrian in consecutive image frames; step 3: extracting the same pedestrian motion energy HOG features of the graph; Step 4: Construct a pedestrian movement and posture recognition model based on support vector machine; Step 5: Use the pedestrian movement and posture recognition model based on Support Vector Machine to judge the pedestrian posture in the current video; Step 6: Calculate and obtain pedestrians The real-time speed of the pedestrian is obtained from the instantaneous speed sequence in the direction of the X-axis and the Y-axis; Step 7: According to the three-dimensional scene in the intersection environment, the position information of the pedestrian in the image is obtained in real time, combined with the posture and real-time speed of the pedestrian, and the real-time speed of the pedestrian is obtained. sporty features. This solution can obtain more comprehensive and useful information, and has the advantages of wide signal detection range and complete target information. It is cost-effective and easy to promote.

Description

technical field [0001] The invention belongs to the field of traffic monitoring, and in particular relates to a large data mixed extraction method of pedestrian local characteristics. Background technique [0002] Nowadays, big data is applied in more and more extensive fields, and has had a profound impact on human society. With the opening of the national policy of "Made in China 2025", big data has already had an impact on transportation, industry, medical care, energy, climate and other fields. obvious impact. In the field of transportation, ensuring the safety of human property is always the first priority. People have been making continuous efforts to explore and improve. However, pedestrian traffic accidents are still common. How to effectively protect the safety of pedestrians’ lives and property is a key issue in the field of transportation. The point is also difficult. [0003] The difficulty of pedestrian detection lies in how to effectively identify pedestrian ...

AI Technical Summary

Problems solved by technology

[0003] The difficulty of pedestrian detection lies in how to effectively identify pedestrian movements. Human motion has non-rigid body characteristics, and there are obvious differences in shape, speed, appearance, and clothing between different individuals, irregular motion, and different motion directions. Reasons for Difficulty in Pedestrian Detection

Traditional pedestrian detection methods mainly include: microwave method, beam method, and pressure sensor method. These methods generally have limitations in detection locations and low accuracy, and cannot use specific and accurate pedestrian information provided by images.

Images