Title:
SYSTEM FOR NEURAL ARCHITECTURE SEARCH FOR MONOCULAR DEPTH ESTIMATION AND METHOD OF USING THE SAME
Document Type and Number:
Japanese Patent JP2023070183
Kind Code:
A
Abstract:
To provide an in-vehicle model training system.SOLUTION: An in-vehicle model training system includes a non-transitory computer readable medium; and a processor. The processor is configured to receive an input image; perform object detection, using an encoder, on the input image to identify an object, wherein the encoder includes an in-vehicle neural network (NN) model; and generate a first heatmap based on the determined distance to each identified object. The processor is configured to compare the first heatmap with a second heatmap generated by a trained neural network (NN); update the in-vehicle NN model based on differences between the first heatmap and the second heatmap; and determine whether a latency of the encoder satisfies a latency specification. The processor is configured to output the in-vehicle NN model in response to the latency satisfying the latency specification and the difference between the first heatmap and the second heatmap satisfying an accuracy specification.SELECTED DRAWING: Figure 1
Inventors:
KAWANA YUKI
Application Number:
JP2022178092A
Publication Date:
May 18, 2023
Filing Date:
November 07, 2022
Export Citation:
Assignee:
WOVEN ALPHA INC
International Classes:
G06T7/00; G06T7/50; G06V20/58; G08G1/00
Attorney, Agent or Firm:
Atsushi Aoki
Shinji Mihashi
Junichi Tsuruta
Kouichi Ito
Nobuo Sekine
Tsutomu Kawano
Shinji Mihashi
Junichi Tsuruta
Kouichi Ito
Nobuo Sekine
Tsutomu Kawano
Previous Patent: Nickel paste and films for conductors
Next Patent: Method for producing C-aryl glycoside derivative
Next Patent: Method for producing C-aryl glycoside derivative