Method for training autoencoder, electronic device, and storage medium
AssigneeHon Hai Precision Industry Co., Ltd.
InventorsCHIN-PIN KUO, CHIH-TE LU, TZU-CHEN LIN, JUNG-HAO YANG
Life of this patent
Estimating the term…
Abstract
A method for training an autoencoder implemented in an electronic device includes obtaining a stereoscopic image as the vehicle is in motion, the stereoscopic image includes a left image and a right image; generating a stereo disparity map according to the left image; generating a predicted right image according to the left image and the stereo disparity map; and calculating a first mean square error between the predicted right image and the right image.
Claims20
An electronic device comprising:
- at least one processor;
- and
- a storage device coupled to the at least one processor and that stores instructions, which when executed by the at least one processor, cause the at least one processor to:
- obtain a stereoscopic image as a vehicle is in motion, the stereoscopic image comprising a left image and a right image;
- generate a stereo disparity map according to the left image;
- generate a predicted right image according to the left image and the stereo disparity map;
- and
- calculate a first mean square error (MSE) between the predicted right image and the right image.
A method for training an autoencoder implemented in an electronic device comprising:
- obtaining a stereoscopic image as a vehicle is in motion, the stereoscopic image comprising a left image and a right image;
- generating a stereo disparity map according to the left image;
- generating a predicted right image according to the left image and the stereo disparity map;
- and
- calculating a first MSE between the predicted right image and the right image.
A computer-readable storage medium having instructions stored thereon, when the instructions are executed by a processor of an electronic device, the processor is configured to perform a method for training an autoencoder, wherein the method comprises:
- obtaining a stereoscopic image as a vehicle is in motion, the stereoscopic image comprising a left image and a right image;
- generating a stereo disparity map according to the left image;
- generating a predicted right image according to the left image and the stereo disparity map;
- and
- calculating a first MSE between the predicted right image and the right image.
Dependencies are inferred from the claim text.