An early warning system for vehicle thermal imaging detection for targets with different danger levels

Abstract

The invention discloses an early warning system for vehicle thermal imaging detection aiming at targets of different danger levels, belonging to the field of vehicle thermal imaging detection. The output end of the detection module is electrically connected to the FrameBuffer, and the output end of the FrameBuffer is connected to the DRM module. Through the conversion of the relative position of the target, the threshold division of the relative depth parameter, the image expression and sound prompting of the distance information, to achieve a more significant and intuitive reminder to the target, especially the dangerous target, so that people can obtain the target position information more intuitively , make pre-judgment and avoid it in advance; solve the low-risk state light warning, minimize the distraction of the driver when the risk is low; high-risk time red warning, and trigger high-decibel high-risk warning; light warning can reduce more False alarms trigger distractions for drivers.

Description

technical field [0001] The invention belongs to the field of vehicle-mounted thermal imaging detection, in particular to an early-warning system for vehicle-mounted thermal imaging detection aiming at targets of different risk levels. Background technique [0002] Vehicle-mounted target detection can help drivers to assist in judging some targets that will affect driving, such as pedestrians, cars, bicycles and other dangerous targets. The existing vehicle-mounted thermal imaging night vision system will obtain target parameters from the target detection module, and give them according to the target detection module. The target size, target position parameters, regardless of the target distance, the target detection bounding box of the same target type (pedestrian or bicycle, etc.) is drawn on the FrameBuffer in the same color, and then projected on the screen through the DRM system for display. ; All detected targets are also prompted with the same warning sound. The curre...

AI Technical Summary

Problems solved by technology

The current vehicle-mounted thermal imaging night vision system cannot combine the different distances of dangerous targets to provide image and sound prompts for different danger levels. Too many early warnings for mild risky targets will distract the driver's attention, and the driver is prone to a single early warning method. Fatigue, ignoring high-level dangerous targets, based on a limited computing power platform, there is no early warning of different risk levels, which will trigger more false alarms and distract the driver's attention

Images