IP Library Granted Patent US 12,206,875
Granted Patent B2
US 12,206,875 · App. 18/112,615 · Granted Jan 21, 2025

Systems and methods for improving object tracking in compressed feature data in coding of multi-dimensional data

Inventors: Robert Henzel (Vancouver, WA); Kiran Mukesh Misra (Vancouver, WA); Tianying Ji (Vancouver, WA)
Assignee: SHARP KABUSHIKI KAISHA
H04N19/33H04N19/124H04N19/159H04N19/184H04N19/503
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,206,875
App. No.
18/112,615
Granted
Jan 21, 2025
Kind
B2
Abstract

A method of compressing feature data includes: receiving feature data; performing spatial down sampling on the received feature data by applying a pixel unshuffle operation; and performing channel reduction on the spatially down sampled feature data by applying a non-linear two dimensional convolution with an activation.

Claims (9)

1. A method of compressing feature data, the method comprising:

receiving W×H×C feature data, wherein W and H are spatial dimensions and C is a number of channels and each channel corresponds to a down sampled version of an input image;

performing spatial down sampling on the received W×H×C feature data by applying a pixel unshuffle operation using a downscale factor to generate W/r×H/r×C spatially down sampled feature data, wherein r is the downscale factor;

reducing the number of channels from C to N by applying a non-linear two dimensional convolution with an activation and using a residual connection;

applying a spatial batch normalization layer to W/r×H/r×N feature data;

quantizing the W/r×H/r×N feature data; and

entropy coding the quantized W/r×H/r×N feature data to generate a bitstream.

2. The method of claim 1 , wherein r is equal to 3, C is equal to 256, and N is equal to 16.

3. The method of claim 1 , wherein the received W×H×C feature data includes residual data generated using inter prediction.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 12, 2023
From: HENZEL, ROBERT; MISRA, KIRAN MUKESH; JI, TIANYING
To: SHARP KABUSHIKI KAISHA
Reel/Frame 063308/0143 →
Continuity (2)
Provisional Application 63313536 · Feb 24, 2022
Related Publication 20230269385A1 · Aug 24, 2023
References Cited (8)
US 6628714B1 · Fimoff · 2003 [cited by examiner]
US 20150363634A1 · Yin · 2015 [cited by examiner]
US 20190045168A1 · Chaudhuri · 2019 [cited by examiner]
US 20200280717A1 · Li · 2020 [cited by examiner]
US 20230096567A1 · Nalci · 2023 [cited by examiner]
International Telecommunication Union, ITU-T, Telecommunication Standardization Sector of ITU, H.264, (Aug. 2021). [cited by applicant]
International Telecommunication Union, ITU-T, Telecommunication Standardization Sector of ITU, H.265, (Dec. 2016). [cited by applicant]
Benjamin Bross et al., “Versatile Video Coding Editorial Refinements on Draft 10”, Document: JVET-T2001-v2, Joint Video Experts Team (JVET) of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29, 20th Meeting, by teleconference, O… [cited by applicant]