18078311. METHOD AND APPARATUS WITH OBJECT DETECTION simplified abstract (Samsung Electronics Co., Ltd.)
Contents
METHOD AND APPARATUS WITH OBJECT DETECTION
Organization Name
Inventor(s)
METHOD AND APPARATUS WITH OBJECT DETECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18078311 titled 'METHOD AND APPARATUS WITH OBJECT DETECTION
Simplified Explanation
The patent application describes an electronic device that can perform object detection and classification in input images. It uses a feature map generated from the input image to identify and classify objects. The device also determines object regions and regions of interest (ROI) within the objects based on the feature map.
- The device can detect and classify multiple objects in an input image.
- It generates a feature map to identify and locate objects within the image.
- The device determines ROI within the objects and classifies them separately.
- It displays indicators on the input image to identify object regions and feature points.
- The device performs post-processing differently based on whether an ROI is determined in an object.
Potential applications of this technology:
- Object detection and classification in surveillance systems.
- Autonomous vehicles for identifying and tracking objects on the road.
- Image recognition and analysis in medical imaging for identifying specific features or anomalies.
- Robotics and automation for object detection and manipulation.
Problems solved by this technology:
- Efficient and accurate object detection and classification in images.
- Identification and tracking of specific regions of interest within objects.
- Improved post-processing based on the presence or absence of ROI.
Benefits of this technology:
- Enhanced object detection and classification capabilities.
- Improved accuracy and efficiency in identifying and tracking objects.
- Customized post-processing based on the presence or absence of ROI.
- Potential for applications in various industries such as surveillance, healthcare, and robotics.
Original Abstract Submitted
An electronic device generates a feature map from an input image to perform object detection, classifies one or more objects included in the input image and determines one or more object regions including the one or more objects based on the feature map, classifies an ROI included in at least a portion of the objects and determines the ROI included in the input image based on the feature map, displays on the input image an indicator identifying a first object region of a first object where the ROI is determined and a feature point of a first ROI of the first object, and displays on the input image an indicator identifying a second object region of a second object where the ROI is not determined and a feature point of the second object region, to perform post-processing differently according to whether an ROI is determined in an object.
