# US 2026/0100115 A1 · Item detection system and method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0100115 A1
- Document ID: US20260100115A1
- Status: Published application
- Kind: A1
- Application number: 19/351,021
- Filed: 2025-10-06
- Published: 2026-04-09
- Earliest claimed: 2024-10-04
- Assignees: Mashgin Inc.
- Applicants: Mashgin Inc.
- Inventors: Abhinai Srivastava; Mukul Dhankhar
- Web page: https://patentgrep.com/patent/US20260100115A1

## CPC

- G07G 1/0063: {with means for detecting the geometric dimensions of the article of which the code is read, such as its size or height, for the verification of the registration}
- G06Q 20/208: {Input by product or record sensing, e.g. weighing or scanner processing}
- G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G07G 1/0018: {Constructional details, e.g. of drawer, printing means, input means}
- G07G 1/01: Details for indicating
- G07G: REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

In variants, the system can include a base and a set of supports cooperatively defining an measurement volume, and a processing system configured to identify items places within the measurement volume.

## Claims

### Claim 1

A kiosk system, comprising:
a static base;
a set of supports mounted offset from opposing regions of the base, wherein the set of supports cooperatively define a measurement volume with the base,
wherein the measurement volume comprises a physically unenclosed top;
a set of optical sensors mounted to each support of the set of supports, wherein the set of optical sensors are directed toward the measurement volume and comprise fixed fields of view, wherein the fields of view of the set of optical sensors cooperatively encompasses an entirety of the base; and
a processing system configured to automatically identify a set of items based on a set of measurements from the set of optical sensors.

### Claim 2 (depends on 1)

The system of claim 1, wherein an optical sensor of the set of optical sensors comprises a stereo camera pair.

### Claim 3 (depends on 1)

The system of claim 1, wherein the set of measurements comprises a height map.

### Claim 4 (depends on 1)

The system of claim 1, wherein automatically identifying the set of items based on the set of measurements comprises:
segmenting the set of measurements into a set of item segments;
determining a set of item embeddings based on the set of item segments; and
determining an item identifier for each item using the set of item embeddings.

### Claim 5 (depends on 4)

The system of claim 4, wherein the set of item embeddings comprises an appearance embedding and a geometric embedding for each item.

### Claim 6 (depends on 1)

The system of claim 1, wherein the set of supports consists essentially of two supports.

### Claim 7 (depends on 1)

The system of claim 1, wherein the set of supports each comprise a post and an arm extending laterally from the respective post, wherein each arm comprises a first subset of optical sensors mounted proximal a joint between the post and the arm, and comprises a second subset of optical sensors mounted proximal an arm end.

### Claim 8 (depends on 1)

The system of claim 1, wherein the measurement volume has an unobstructed front, back, left, and right side.

### Claim 9 (depends on 1)

The system of claim 1, wherein the base comprises a display that displays an item indicator for an item of the set of items.

### Claim 10 (depends on 1)

The system of claim 1, wherein the set of optical sensors cooperatively define an optically enclosed space, wherein the measurement volume is fully encompassed by the optically enclosed space.

### Claim 11

A system, comprising:
a base;
a set of supports mounted to the base, wherein each support in the set of supports comprise a set of optical sensors;
a measurement volume geometrically defined by the base and the set of supports,
wherein the measurement volume comprises an unobstructed top, front, back, left, and right side; and
a processing system configured to identify objects based on a set of measurements of the measurement volume sampled by the set of optical sensors.

### Claim 12 (depends on 11)

The system of claim 11, wherein the optical sensors define an optically enclosed space, wherein the measurement volume is encompassed within the optically enclosed space.

### Claim 13 (depends on 11)

The system of claim 11, wherein the set of supports consists of a single support.

### Claim 14 (depends on 11)

The system of claim 11, wherein the set of supports consists of two supports, wherein the two supports are mounted to a same side of the base.

### Claim 15 (depends on 11)

The system of claim 11, wherein the set of optical sensors consists essentially of four static cameras.

### Claim 16 (depends on 11)

The system of claim 11, wherein the base comprises an interactive display configured to display:
a calibration pattern when the system is in a calibration mode; and
a set of item indicators around each of a set of identified items when the system is in an item identification mode.

### Claim 17 (depends on 11)

The system of claim 11, further comprising a set of user interfaces mounted to the set of supports, wherein different user interfaces are mounted to different supports at exterior regions of the respective supports, wherein the exterior regions are oriented away from base.

### Claim 18 (depends on 11)

The system of claim 11, wherein the processing system identifies objects by:
segmenting the set of measurements into a set of item segments;
extracting a set of item embeddings for each item from the respective item segments;
identifying each item based on the respective set of item embeddings.

### Claim 19 (depends on 18)

The system of claim 18, wherein segmenting the set of measurements comprises:
segmenting a geometric measurement of the set of measurements into a set of
geometric item segments using a set of heuristics; and
projecting the set of geometric item segments into an image to determine a set of image item segments; wherein the set of item embeddings comprises geometric embeddings extracted from the set of geometric item segments and appearance embeddings extracted from the set of image item segments.

### Claim 20 (depends on 11)

The system of claim 11, further comprising a set of guard sensors, wherein the system is operable between a sleep and awake mode based on measurements sampled by the set of guard sensors.
