Apple Invents a Future Home Security Camera System that Recognizes visitors or intruders using both Face ID & new 'Bodyprint' ID
In early December (2022), Patently Apple posted an IP report titled "Apple invents a camera system for a Home's Front Door with facial recognition that communicates with a HomePod mini, Smart TV+." Last week the US Patent & Trademark Office published a patent application from Apple that expands on the December HomePod Security system patent. The patent notes that the security system will go beyond mere facial recognition and introduce "Bodyprint" recognition.
The system that Apple is working on and patenting, stems in-part from their acquisition of 'Lighthouse' in March 2019. Two of Lighthouse engineers are listed on today's patent's credit.
Although today's patent focus is new to this project, knowing that Apple is expanding on Lighthouse IP in a larger project is worth noting.
Identity Recognition including new Bodyprint Technology
Apple's invention describes enabling the performance of recognition of an identity of a particular person based on physical characteristics of the particular person. The physical characteristics of the particular person may be associated with their identity based on previously performing facial recognition of the particular person. In one example, a device may receive a first video feed, for example, showing a particular person (e.g., including their face and torso portion of their body) walking towards a camera. The device may perform facial recognition to identify the identity of the particular person. The device may further identify physical characteristics of the particular person from the first video feed, for example, based on analyzing other body features of the particular person (e.g., including their torso, clothing worn, etc.).
The resident device may generate a bodyprint of the first person. The bodyprint may include a multidimensional vector that is associated with (e.g., represents) the one or more physical characteristics of the first person, whereby a dimension of the vector may be associated with at least one characteristic of the body of the contact.
The home resident will be able to view the person at the door using a home TV with a picture-in-picture feature, Tablet, HomePod (with a tablet), iPhone and more.
Apple's camera system will use a deep learning model to train itself in identifying bodyprints. Over time, the system will be able to identify false bodyprints.
Apple's patent FIG. 4 below illustrates at least some example techniques for providing a notification based on determining the presence of a particular person at a location. In diagram #400 of FIG. 4, several elements are depicted, including observation camera #402, a video feed #404, body croppings #408, a user device #406, a pop-up notification #410, and a video presentation #412.
Apple's patent FIG. 8 above is a simplified flow diagram illustrating a process for determining whether to add a bodyprint image to a cluster of bodyprint images corresponding to a recognized person.
Apple patent dives deep into bodyprints, listing the term 229 times. To review Apple's patent application in full, read patent number US 20230013117 A1 here.
- Hendrik Dahlkamp: HomeKit Secure Video / Machine Learning Manager
- Vinay Sharma: AI/ML, Computer Vision, Deep Learning. Human and Object Understanding
- Floris Chabert: Applied research
- Jingwen Zhu: Research Engineer (previous employers: Konica Minolta and Samsung)
- Nitin Gupta: Machine Learning Engineer (came to Apple in 'Lighthouse' acquisition)
- Jonghoon J.: Deep learning for computer vision (came to Apple via Lighthouse acquisition)