Method and system for detecting multiple moving objects from real-time aerial images

US9940724B2 · kind B2 · utility

Assignee

• INTELLIGENT FUSION TECHNOLOGY, INC. · US

Inventors

• Bin Jia · Germantown, US
• Kui Liu · Hsinchu, TW
• Sixiao WEI · Germantown, US
• Erik Blasch · Rome, US
• Carolyn Sheaff · Rome, US
• Haibin Ling · College Park, US
• Genshe Chen · Germantown, US

Key dates

• Filing date: Sep 13, 2016
• Grant date: Apr 10, 2018
• Expiry date: Sep 13, 2036

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V10/757
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

In accordance with various embodiments of the disclosed subject matter, a method and a system for detecting multiple objects from real-time images are provided. The method comprises: performing, using a CPU host, an image segmentation process to divide real-time input images into a plurality of image partitions; performing, by multiple GPUs, a fast block-wise registration process, a mark setting process, a background generation process, a foreground generation process based on a Hyper-Q computation infrastructure, and a support vector machine classification process; and generating, by the CPU host, visualization classification images.