Map Generation Device Weighting for Occlusion Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
When generating maps, stationary constructions can be incorrectly measured due to occlusion by moving objects like pedestrians and vehicles, which is not considered in existing methods.
Innovation Solution
A map generation device that assigns weight values to map data regions based on the presence of stationary and moving objects, determined by analyzing the traveling route and position of the measurement vehicle, to account for the possibility of occlusion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If map data is collected using sensors on measurement vehicles, then map generation can be performed, but measurement accuracy deteriorates due to occlusion by moving objects such as pedestrians and vehicles
Solution Approach 1:
The system performs preliminary classification of detected objects as stationary or moving before using them for map generation. By预先 identifying and excluding moving objects that cause occlusion, the system prevents measurement errors before they affect the final map accuracy, thereby resolving the contradiction between maintaining measurement precision and dealing with unreliable detections caused by occlusion
Solution Approach 2:
The system applies different processing rules to different regions of the map data based on local conditions. In regions where occlusion by moving objects is detected, the system selectively excludes or weights those measurements differently, allowing high-precision measurements in clear regions while handling occluded regions appropriately, thus maintaining overall measurement precision while accounting for local reliability issues
2Adaptability or versatility
If existing map updating methods are used, then map data can be updated, but the system cannot account for occlusion caused by moving bodies
Solution Approach 1:
The system performs preliminary classification of detected objects as stationary or moving before using them for map generation. By预先 identifying and excluding moving objects that cause occlusion, the system prevents measurement errors before they affect the final map accuracy, thereby resolving the contradiction between maintaining measurement precision and dealing with unreliable detections caused by occlusion
Solution Approach 2:
The system applies different processing rules to different regions of the map data based on local conditions. In regions where occlusion by moving objects is detected, the system selectively excludes or weights those measurements differently, allowing high-precision measurements in clear regions while handling occluded regions appropriately, thus maintaining overall measurement precision while accounting for local reliability issues
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
A server device 200 is a map generation device which assigns, to voxel data in the map DB 20 which is divided into multiple voxels, a first weight value for each voxel, wherein the first weight value is associated with the presence of a stationary object and a moving object. Then, the server device 200 acquires upload information Iu which includes position information relating to a travelling route of a measurement vehicle during measurement of point cloud data needed for generation or update of the voxel data. Then, the server device 200 determines the first weight value for each voxel based on the travelling route of the measurement vehicle identified by the position information included in the upload information Iu.