Pedestrian and safety helmet detection method, device and system

Abstract

The invention discloses a pedestrian and safety helmet detection method, device and system. The method comprises the steps of acquiring a video image; performing pedestrian and safety helmet detectionon the video image through a pedestrian-safety helmet detection model; matching a unique identity label for the detected pedestrian by adopting a target tracking algorithm; and judging whether the pedestrian carrying the identity label wears the safety helmet or not, and if so, marking the pedestrian as wearing the safety helmet and outputting the result. According to the scheme, the problem of data unavailability caused by imbalance of a training convolutional neural network data set and label missing can be solved, and a large amount of manual labeling cost is saved. Moreover, a target tracking method is adopted to objectify pedestrians in the video, a unique ID is allocated to each pedestrian appearing in the video, and multi-frame long-time detection is carried out on whether the pedestrian wears the safety helmet or not, so that the false alarm rate is greatly reduced.

Description

technical field [0001] The invention belongs to the technical field of target detection and recognition, and in particular relates to a pedestrian and safety helmet detection method, device and system. Background technique [0002] Safety helmets are head protection devices that prevent head collisions when objects hit and fall. Construction workers wear safety helmets to protect their heads from falling objects. However, there are often cases where construction workers do not wear safety helmets, and it is very important to monitor the wearing of safety helmets in real time. [0003] In the prior art, machine learning is used to detect the wearing of safety helmets by workers. Due to the large detection area, the characteristics of wearing safety helmets are relatively inconspicuous, which may easily lead to inaccurate detection. In addition, existing detection algorithms cannot use data with missing labels. For example, if you want to detect helmets and pedestrians at the...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, machine learning is used to detect the wearing of safety helmets by workers. Due to the large detection area, the characteristics of wearing safety helmets are relatively inconspicuous, which may easily lead to inaccurate detection.

In addition, existing detection algorithms cannot use data with missing labels. For example, if you want to detect helmets and pedestrians at the same time, both helmets and pedestrians in the image data required for training cannot be missing, so it cannot be used for most recognition networks.

Images