System and method for detecting remnants in automobile cabin

Abstract

The invention relates to the technical field of intelligent detection, in particular to a system and method for detecting remnants in an automobile cabin. The method comprises the steps of setting a frame number threshold value according to the characteristic that a monitoring video in the automobile cabin is stable before a passenger gets on the automobile, and building a seat background image, enabling a pressure sensor under the seat to record the number and sitting positions of passengers and continuously monitoring the change of pressure, when the pressure quantity is changed, starting remnant detection on the front-row seats, and conducting remnant detection on the vacated position areas of the rear-row seats, after detecting and judging the remnants, identifying the types of the remnants according to the proposed image classification algorithm, after the identification is successful, enabling the automobile machine system to send a short message to the mobile phone of the passenger or notify the driver to remind the passenger who just gets off the automobile to pick up the lost articles. According to the method, the target detection method is used for tracking the remnants,the thought that a target tracking method is usually used is replaced, a detection-tracking method is achieved, and the difficulty that the calculation amount of a target tracking algorithm is large is overcome.

Description

technical field [0001] The invention relates to the technical field of intelligent detection, in particular to a detection system and a detection method for leftovers in an automobile cockpit. Background technique [0002] Existing algorithms for remnants detection are generally divided into three categories. One is the method of background modeling. Items left in the picture, this kind of method is more dependent on the quality of the background picture; the second is the method of target tracking, this kind of method needs to consume a lot of resources, will bring a huge calculation burden, and it is difficult to apply in the scene of general application Meet this requirement, so this solution is usually not used on the mobile side, and tracking methods are generally difficult to deal with the challenges brought about by object deformation and occlusion; the last category is the target detection method, which has a fast speed , Intuitive, easy to operate and other advanta...

AI Technical Summary

Problems solved by technology

[0004] The patent with the patent application number CN201911244307.5 uses the same vision method as the present invention. It proposes to use multi-camera and multi-view method to track and locate the remnants in the car. The technology involves the cooperative work of multi-camera, but it increases the calculation burden; at the same time, the patent does not involve the serious impact of light on the effect, and the actual application scenarios are limited

Images