Inventor

MEDIONI GERARD GUY

US94 patents

⚠️ This page may combine multiple inventors who share the name “MEDIONI GERARD GUY”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

MEDIONI GERARD GUY

AMAZON TECH INC

Associating an agent with an event based on multiple inputs

Multiple sensor data fusion system

Tracking objects in three-dimensional space using calibrated visual cameras and depth cameras

Image processing system for image rectification

Associating items with actors based on digital imagery

Generating tracklets from digital imagery

Associating events with actors based on digital imagery

Multi-video annotation

Agent re-verification and resolution using imaging

System for multi-modal anomaly detection

Utilizing sensor data for automated user identification

Associating events with actors using digital imagery and machine learning

Associating events with actors using digital imagery and machine learning

System to determine item weight using data from weight sensors

Associating events with actors using digital imagery and machine learning

Interaction determination using data from weight sensors

System to determine user interaction with fixture

Inferred determination of interaction using data from weight sensors

Fusion of sensor data for detecting interactions at an inventory location

Image data illumination detection

System for determining embedding using spatial data

Locally and globally locating actors by digital cameras and machine learning

Locally and globally locating actors by digital cameras and machine learning

Tracking objects in three-dimensional space using calibrated visual cameras and depth cameras

Vision-based event detection

Detecting interactions with non-discretized items and associating interactions with actors using digital images

Multi-video annotation

Determination of untidy item return to an inventory location

System using multimodal decorrelated embedding model

Utilizing sensor data for automated user identification

System to determine user presence

Detecting interactions from features determined from sequences of images captured using one or more cameras

Agent re-verification and resolution using imaging

Concurrent ensemble model training for open sets

Image partitioning for re-identification

Calibration of networked imaging devices to a global color space

System for mapping images to a canonical space

Tracking objects in three-dimensional space

Updating identification data in automated user-identification systems

Image-based detection of planogram product spaces

Utilizing sensor data for automated user identification

Joint inference determination of interaction using data from weight sensors

Signal processing techniques

Non-contact biometric identification system

UNIV SOUTHERN CALIFORNIA

3D body modeling, from a single or multiple 3D cameras, in the presence of motion

3-D reconstruction and registration

3D body modeling from one or more depth cameras in the presence of articulated motion

Tracking multiple moving targets in digital video

SYMAH VISION SA

“Midlink” virtual insertion system

MEDIONI GERARD GUY

Visual tracking in video images in unconstrained environments by exploiting on-the-fly context using supporters and distracters