Method and device for detecting whether pedestrian wears safety helmet or not

Abstract

The invention discloses a method and a device for detecting whether a pedestrian wears a safety helmet or not. The method comprises the steps that a pedestrian safety helmet detection model is trained; in the training process, a sample image used for training a pedestrian safety helmet detection model is processed in a secondary marking mode, so that sample features with missing labels in a training sample do not participate in network weight parameter updating when participating in neural network training. According to the method, a human body target rectangular frame and a safety helmet target rectangular frame are detected through the pedestrian safety helmet detection model, then human body features in the human body target rectangular frame are extracted through a feature extraction network, and target pedestrians are tracked and matched with safety helmets in continuous video frames based on the human body features. According to the scheme, the high-accuracy detection model can be trained on the basis of label missing unbalanced data, and multi-frame detection is carried out on the safety helmet wearing condition of each pedestrian by adopting a target tracking method, 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 method and a device for detecting whether a pedestrian wears a safety helmet. 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 staff. However, existing detection algorithms cannot use data with missing labels. For example, if you want to detect helmets and pedestrians at the same time, you usually need to train the helmet detection network or the pedestrian detection network separately, or train the helmet detection chann...

AI Technical Summary

Problems solved by technology

[0005] That is to say, this type of prior art can only judge whether everyone is wearing a helmet in the current frame, and an alarm will be given as long as it is detected that someone is not wearing it. However, this type of prior art cannot identify who is not wearing a helmet, and even It is impossible to track a specific person in the next video, and get the helmet wearing situation of this person over a period of time

However, the detection of a single image is prone to errors. If there are multiple human body images overlapping in the image, it is easy to misdetect using the above method.

Images