CN-115909288-B - Object anti-lost method, device and storage medium

CN115909288BCN 115909288 BCN115909288 BCN 115909288BCN-115909288-B

Abstract

The application provides a method and a device for preventing objects from being lost and a storage medium, which are applied to the field of signal processing. The method includes obtaining a target user and a distance of the target user from a vehicle. And when the distance is smaller than a first preset threshold value, acquiring the identity of the target user and the carried target object identification. Then, when the user to be detected is detected to enter the vehicle, the identity of the user to be detected and the carried object to be detected are obtained. And if the identity of the user to be detected and the carried object identity to be detected are inconsistent with the identity of the target user and the carried target object identity, carrying out object drop warning on the target user. Therefore, the user is reminded of carrying out object drop inspection through the consistency comparison of the user identity and the carried object inside and outside the vehicle, so that the object drop in the running process caused by the fact that the user drops the object outside the vehicle is avoided, and the safety of the vehicle in the running process is improved.

Inventors

WANG YUNHANG
GUO YUJIE
LIU GUIBO
CHEN HANJUN
CHEN XIANLING

Assignees

长城汽车股份有限公司

Dates

Publication Date: 20260505
Application Date: 20220816

Claims (9)

1. A method for preventing objects from being lost, the method comprising: acquiring a target user, wherein the target user is a user with a distance from a vehicle within a preset range; Acquiring the distance from a target user to a vehicle; Acquiring an identity of a target user and a carried target object identifier in response to the distance from the target user to the vehicle being smaller than a first preset threshold; Responding to the fact that a user to be detected enters the vehicle, and acquiring an identity of the user to be detected and a carried object to be detected; Judging whether the carried object identification to be detected is consistent with the carried target object identification according to a preset object identification algorithm in response to the identity identification of the user to be detected being identical with the identity identification of the target user, wherein the object identification algorithm is obtained through deep neural network training based on softmax or is obtained through cosine similarity algorithm calculation; and responding to the inconformity of the carried object identification to be detected and the carried target object identification, and carrying out object drop alarming operation on the target user.
2. The method of claim 1, wherein the obtaining the identity of the target user and the carried target object identifier includes: acquiring image data of a target user, wherein the image data of the target user is acquired through acquisition equipment; Acquiring an identity of a first user and a carried target object identification according to a first preset target detection algorithm and image data of the target user; The first preset target detection algorithm is used for identifying a target user in the image data and detecting an identity of the target user and a carried object.
3. The method according to claim 1, wherein the obtaining the identity of the user to be detected and the carried identity of the object to be detected includes: acquiring image data of the user to be detected, wherein the image data of the user to be detected is acquired through acquisition equipment in a vehicle; Acquiring the identity of the user to be detected and the carried object to be detected according to a second preset target detection algorithm and the image data of the user to be detected; The second preset target detection algorithm is used for identifying a user to be detected in the image data and detecting an identity mark and a carried object of the user to be detected.
4. A method according to any one of claims 1-3, wherein, in response to the user to be detected entering the interior of the vehicle, the method further comprises: Acquiring the residence time of the target user at the periphery of the vehicle in response to the distance from the target user to the vehicle being smaller than a second preset threshold; and judging whether the user to be detected enters the vehicle or not in response to the residence time being lower than a preset residence time threshold value.
5. The method of claim 4, wherein the method further comprises: And responding to the residence time exceeding a preset residence time threshold value, and carrying out object drop alarm operation on the target user.
6. An anti-lost device for an object, the device comprising: the first acquisition unit is used for target users, wherein the target users are users with distance traffic within a preset range; A second acquisition unit configured to acquire a distance from the target user to the vehicle; the first response unit is used for responding to the fact that the distance from the target user to the vehicle is smaller than a first preset threshold value, and acquiring the identity of the target user and the carried target object identification; the second response unit is used for responding to the fact that the user to be detected enters the vehicle to acquire the identity of the user to be detected and the carried object to be detected; The third response unit is used for responding that the identity of the user to be detected is the same as the identity of the target user, judging whether the carried object to be detected is consistent with the carried target object according to a preset object consistency recognition algorithm, wherein the object consistency recognition algorithm is obtained through deep neural network training based on softmax or is obtained through cosine similarity algorithm calculation; And the fourth response unit is used for responding to the inconformity of the carried object identification to be detected and the carried target object identification and carrying out object drop alarming operation on the target user.
7. The apparatus of claim 6, wherein the first response unit comprises: The first acquisition module is used for acquiring image data of a target user, wherein the image data of the target user is acquired through acquisition equipment; the first detection module is used for acquiring the identity of the first user and the carried target object identification according to a first preset target detection algorithm and the image data of the target user; The first preset target detection algorithm is used for identifying a target user in the image data and detecting an identity of the target user and a carried object.
8. The apparatus of claim 6, wherein the second response unit comprises: the second acquisition module is used for acquiring the image data of the user to be detected, wherein the image data of the user to be detected is acquired through acquisition equipment in a vehicle; the second detection module is used for acquiring the identity of the user to be detected and the carried object identification to be detected according to a second preset target detection algorithm and the image data of the user to be detected; The second preset target detection algorithm is used for identifying a user to be detected in the image data and detecting an identity mark and a carried object of the user to be detected.
9. A computer-readable storage medium, wherein a program for implementing an object anti-lost method is stored on the computer-readable storage medium, and the program for implementing the object anti-lost method, when executed by a processor, implements the steps of the method according to any one of claims 1-5.

Description

Object anti-lost method, device and storage medium Technical Field The present application relates to the field of signal processing and transmission and communication engineering, and in particular, to a method, an apparatus, and a storage medium for preventing objects from being lost. Background In recent years, the popularity of vehicles such as automobiles and subways is gradually increasing, and more people select vehicles when traveling. Road safety issues therewith are also a concern. Users sometimes encounter temporary placement of a carried object or the like on the periphery of a vehicle before entering the vehicle, but forget to carry the object or the like when entering the vehicle, such as placing a carried water cup, a mobile phone, a wallet or the like on the roof of an automobile, and forget to carry the object or the like when entering the vehicle, resulting in the object being left at the temporary placement. At this time, if the vehicle runs, objects placed at the periphery of the vehicle are easily dropped, thereby causing a road safety hazard. And the object can also cause property loss to the owner of the object when the object falls. Therefore, how to avoid the object carried by the user from falling outside the vehicle and causing the object to fall during the driving process, and to improve the safety of the road, is a technical problem to be solved. Disclosure of Invention In view of the above, embodiments of the present application provide a method, an apparatus, and a storage medium for preventing objects from being lost, which aim to prevent objects carried by a user from being lost outside a vehicle and causing the objects to fall during driving, so as to improve the safety of a road. In a first aspect, an embodiment of the present application provides a method for preventing objects from being lost, where the method includes: acquiring a target user, wherein the target user is a user of which the distance traffic is within a preset range; Acquiring the distance from a target user to a vehicle; Acquiring an identity of a target user and a carried target object identifier in response to the distance from the target user to the vehicle being smaller than a first preset threshold; Responding to the fact that a user to be detected enters the vehicle, and acquiring an identity of the user to be detected and a carried object to be detected; Judging whether the carried object to be detected is consistent with the carried target object identification or not in response to the fact that the identity of the user to be detected is identical with the identity of the target user; and responding to the inconformity of the carried object identification to be detected and the carried target object identification, and carrying out object drop alarming operation on the target user. Optionally, the obtaining the identity of the target user and the carried target object identifier includes: acquiring image data of a target user, wherein the image data of the target user is acquired through acquisition equipment; Acquiring an identity of a first user and a carried target object identification according to a first preset target detection algorithm and image data of the target user; The first preset target detection algorithm is used for identifying a target user in the image data and detecting an identity of the target user and a carried object. Optionally, the obtaining the identity of the user to be detected and the carried object to be detected includes: acquiring image data of the user to be detected, wherein the image data of the user to be detected is acquired through acquisition equipment in a vehicle; Acquiring the identity of the user to be detected and the carried object to be detected according to a second preset target detection algorithm and the image data of the user to be detected; The second preset target detection algorithm is used for identifying a user to be detected in the image data and detecting an identity mark and a carried object of the user to be detected. Optionally, the determining whether the carried object identifier to be detected is consistent with the carried target object identifier includes: and judging whether the carried object identification to be detected is consistent with the carried target object identification or not according to a preset object consistency recognition algorithm. Optionally, before the user to be detected enters the vehicle interior, the method further comprises: Acquiring the residence time of the target user at the periphery of the vehicle in response to the distance from the target user to the vehicle being smaller than a second preset threshold; and judging whether the user to be detected enters the vehicle or not in response to the residence time being lower than a preset residence time threshold value. Optionally, the method further comprises: And responding to the residence time exceeding a preset residence time threshold value, and