Back to results
US 11,557,133 B1Granted
Automatic license plate recognition
AssigneeVerkada Inc.
InventorsYi Xu, Yunchao Gong, Suraj Arun Vathsa, Mayank Gupta, Naresh Nagabushan
Life of this patent
Estimating the term…
Abstract
Automatic license plate recognition occurs when a light sensor that continually captures video detects motion as a vehicle is driven through a gate. The light sensor detects the vehicle and license plate in the video stream captured by the light sensor. An algorithm associated with the video stream of the light sensor is trained to detect license plates. The light sensor starts executing the recognition algorithm when it detects motion. Recognition of characters in the license plate is based upon an aggregation of several captured video frames in which a license plate is detected.
Claims18
A method comprising:
- detecting a motion of a moving object proximate to a detector;
- upon detecting the motion, activating a camera;
- recording a video of the moving object,
- wherein the video includes a plurality of frames;
- analyzing a subset of the plurality of frames to detect a license plate;
- upon detecting the license plate in a frame in the subset of the plurality of frames, analyzing neighboring frames associated with the frame to detect the license plate,
- wherein the neighboring frames temporally precede and succeed the frame;
- based on the analysis of the neighboring frames, creating a plurality of frames containing the license plate;
- performing an optical character recognition in each frame in the plurality of frames containing the license plate to obtain a plurality of license plate characters;
- determining a number of characters in each frame in the plurality of frames containing the license plate to obtain a plurality of numbers of characters;
- determining a most frequent number of characters among the plurality of numbers of characters;
- determining whether one or more frames in the plurality of frames containing the license plate contain one or more numbers of characters different from the most frequent number of characters;
- upon determining that the one or more frames in the plurality of frames containing the license plate contain one or more numbers of characters different from the most frequent number of characters, discarding the one or more frames;
- and
- determining a plurality of characters in the license plate by performing the following steps for each character in the plurality of characters:
- determining a location of a character in the plurality of characters;
- based on the location of the character in the plurality of characters, determining corresponding characters in each frame in the plurality of frames containing the license plate;
- determining a most frequent character occurring among the character and the corresponding characters;
- and
- determining the most frequent character to be a part of the plurality of characters in the license plate.
17 more elements
A system comprising:
- at least one hardware processor;
- and
- at least one non-transitory memory storing instructions, which, when executed by the at least one hardware processor, cause the system to:
- detect a motion of a moving object proximate to a detector;
- activate a light sensor;
- record a video of the moving object,
- wherein the video includes a plurality of frames;
- analyze a subset of the plurality of frames to detect a license plate;
- upon detecting the license plate in a frame in the subset of the plurality of frames, analyze neighboring frames associated with the frame to detect the license plate,
- wherein the neighboring frames temporally precede and succeed the frame;
- based on the analysis of the neighboring frames, create a plurality of frames containing the license plate;
- perform an optical character recognition in each frame in the plurality of frames containing the license plate to obtain a plurality of license plate characters;
- determine a number of characters associated with the license plate based on each frame in the plurality of frames containing the license plate by:
- determining a number of characters in each frame in the plurality of frames containing the license plate to obtain a plurality of numbers of characters;
- determining a most frequent number of characters among the plurality of numbers of characters;
- determining whether one or more frames in the plurality of frames containing the license plate contain one or more numbers of characters different from the most frequent number of characters;
- and
- upon determining that the one or more frames in the plurality of frames containing the license plate contain one or more numbers of characters different from the most frequent number of characters, discarding the one or more frames;
- and
- determine a plurality of characters associated with the license plate by:
- determining a location of a character in the plurality of characters;
- based on the location of the character in the plurality of characters, determining corresponding characters in each frame in the plurality of frames containing the license plate;
- determining a most frequent character occurring among the character and the corresponding characters;
- and
- determining the most frequent character to be a part of the plurality of characters associated with the license plate.
22 more elements
At least one computer-readable storage medium, excluding transitory signals and carrying instructions, which, when executed by at least one data processor of a system, cause the system to:
- detect a motion of a moving object proximate to a detector;
- activate a light sensor;
- record a video of the moving object,
- wherein the video includes a plurality of frames;
- analyze a subset of the plurality of frames to detect a license plate;
- upon detecting the license plate in a frame in the subset of the plurality of frames, analyze neighboring frames associated with the frame to detect the license plate,
- wherein the neighboring frames temporally precede and succeed the frame;
- based on the analysis of the neighboring frames, create a plurality of frames containing the license plate;
- perform an optical character recognition in each frame in the plurality of frames containing the license plate to obtain a plurality of license plate characters;
- determine a number of characters associated with the license plate based on each frame in the plurality of frames containing the license plate by:
- determining a number of characters in each frame in the plurality of frames containing the license plate to obtain a plurality of numbers of characters;
- determining a most frequent number of characters among the plurality of numbers of characters;
- determining whether one or more frames in the plurality of frames containing the license plate contain one or more numbers of characters different from the most frequent number of characters;
- and
- upon determining that the one or more frames in the plurality of frames containing the license plate contain one or more numbers of characters different from the most frequent number of characters, discarding the one or more frames;
- and
- determine a plurality of characters associated with the license plate by performing the following steps for each character in the plurality of characters:
- determine a location of a character in the plurality of characters;
- based on the location of the character in the plurality of characters, determine corresponding characters in each frame in the plurality of frames containing the license plate;
- determine a most frequent character occurring among the character and the corresponding characters;
- and
- determine the most frequent character to be a part of the plurality of characters associated with the license plate.
19 more elements
Dependencies are inferred from the claim text.