Machine Learning Computer Vision Applications for Spatial AI Object Recognition in Orange County, California
This work addresses automated spatial data and public asset inventory for urban planning in Orange County, but appears incremental as it applies existing methods to new geographic data.
The researchers tackled spatial object recognition in Orange County, California by developing an integrated AI approach using convolutional neural networks on photosphere imagery, achieving detection results for stop signs and fire hydrants across over 800,000 cardinal directions in two areas.
We provide an integrated and systematic automation approach to spatial object recognition and positional detection using AI machine learning and computer vision algorithms for Orange County, California. We describe a comprehensive methodology for multi-sensor, high-resolution field data acquisition, along with post-field processing and pre-analysis processing tasks. We developed a series of algorithmic formulations and workflows that integrate convolutional deep neural network learning with detected object positioning estimation in 360° equirectancular photosphere imagery. We provide examples of application processing more than 800 thousand cardinal directions in photosphere images across two areas in Orange County, and present detection results for stop-sign and fire hydrant object recognition. We discuss the efficiency and effectiveness of our approach, along with broader inferences related to the performance and implications of this approach for future technological innovations, including automation of spatial data and public asset inventories, and near real-time AI field data systems.