US Patent Application 18232215. INFORMATION PROCESSING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY STORAGE MEDIUM simplified abstract
INFORMATION PROCESSING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY STORAGE MEDIUM
Organization Name
Inventor(s)
INFORMATION PROCESSING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY STORAGE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18232215 titled 'INFORMATION PROCESSING APPARATUS, CONTROL METHOD, AND NON-TRANSITORY STORAGE MEDIUM
Simplified Explanation
The patent application describes an information processing apparatus that includes a recognizer.
- The apparatus can analyze an input image and identify a crowd within it.
- The recognizer outputs a label describing the type of the crowd and structure information describing the arrangement of objects within the crowd.
- The structure information includes details about the location and direction of objects in the crowd.
- The apparatus acquires training data, including images, labels, and structure information, to train the recognizer.
- The recognizer is trained using the input image, label, and structure information from the training data.
- The goal is to improve the accuracy and efficiency of crowd analysis and identification.
Original Abstract Submitted
An information processing apparatus () includes a recognizer (). An image () is input to the recognizer (). The recognizer () outputs, for a crowd included in the input image (), a label () describing a type of the crowd and structure information () describing a structure of the crowd. The structure information () indicates a location and a direction of an object included in the crowd. The information processing apparatus () acquires training data () which includes a training image (), a training label (), and training structure information (). The information processing apparatus () performs training of the recognizer () using the label () and the structure information (), which are acquired by inputting the training image () with respect to the recognizer (, and the training label () and the training structure information ().