Leaf-shielding-resistant CIM real-time imaging method for detecting abnormal parking of shared bicycle

Abstract

The invention provides a leaf-shielding-resistant CIM real-time imaging method for detecting abnormal parking of a shared bicycle, and the method comprises the steps: constructing a CIM of a target region which comprises a region of interest and other regions; processing the acquired image to obtain an adaptive occlusion image and leaf occlusion prompt information; sending the adaptive occlusion image into two branches, obtaining an image coordinate of a handlebar center point through the first branch, projecting the image coordinate into the CIM, and combining the image coordinate with the position information of the region of interest to obtain a shared bicycle abnormal parking detection result; enabling the second branch to perform projection transformation on the input self-adaptive occlusion image, and projecting the image into the CIM to realize real-time imaging after being spliced; and sending a detection result to the CIM for storage, performing visualization processing by using a Web GIS technology, and displaying the CIM of the target area at a Web end. According to the method, the utilization rate of information collected by the camera is improved, and related personnelcan be reminded to take measures in time when leaves shield the camera.

Description

technical field [0001] The invention relates to the field of deep learning, in particular to a CIM real-time imaging method for detecting abnormal parking of shared bicycles against leaf occlusion. Background technique [0002] In 2010, IBM officially proposed the concept of "smart city". After ten years of exploration, smart city has already achieved initial results. However, it has not been well reflected in the daily work related to the city. In many jobs, human resources are still used as the main method and technical resources are supplemented. This mode of judging and working based on subjective identification of people leads to a heavy workload and a long time-consuming. [0003] Shared bicycles have been integrated into daily life and become an indispensable part of life. Regarding the parking of shared bicycles, the current parking method is to set up a large area, and the car users only need to park the shared bicycles in this area. At present, the parking detect...

AI Technical Summary

Problems solved by technology

[0002] In 2010, IBM officially proposed the concept of "smart city". After ten years of exploration, smart city has already achieved initial results. However, it has not been well reflected in the daily work related to the city.

At present, the parking detection of shared bicycles is limited to the use of sensors to determine whether the bicycles are parked in the large area through sensor positioning, but it is impossible to judge whether the shared bicycles are parked in the set bicycle area in accordance with the regulations in this large area

[0004] The method of using cameras to detect abnormal parking of shared bicycles usually processes the images collected by each camera separately when processing the collected images, but due to the repetitiveness of the collected information, it is difficult to integrate the information , which leads to the inability to make good use of the image information acquired by the camera

At the same time, for the problem of leaves blocking the camera, the existing method requires staff to check and monitor regularly, which is random and often cannot take corresponding measures in time

Images