Samsung electronics co., ltd. (20240119709). METHOD OF TRAINING OBJECT RECOGNITION MODEL BY USING SPATIAL INFORMATION AND COMPUTING DEVICE FOR PERFORMING THE METHOD simplified abstract
Contents
- 1 METHOD OF TRAINING OBJECT RECOGNITION MODEL BY USING SPATIAL INFORMATION AND COMPUTING DEVICE FOR PERFORMING THE METHOD
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHOD OF TRAINING OBJECT RECOGNITION MODEL BY USING SPATIAL INFORMATION AND COMPUTING DEVICE FOR PERFORMING THE METHOD - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
METHOD OF TRAINING OBJECT RECOGNITION MODEL BY USING SPATIAL INFORMATION AND COMPUTING DEVICE FOR PERFORMING THE METHOD
Organization Name
Inventor(s)
Jinyoung Hwang of Suwon-si (KR)
METHOD OF TRAINING OBJECT RECOGNITION MODEL BY USING SPATIAL INFORMATION AND COMPUTING DEVICE FOR PERFORMING THE METHOD - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240119709 titled 'METHOD OF TRAINING OBJECT RECOGNITION MODEL BY USING SPATIAL INFORMATION AND COMPUTING DEVICE FOR PERFORMING THE METHOD
Simplified Explanation
The method described in the patent application involves training an object recognition model using spatial information, specifically illumination information. Here are some key points to explain the innovation:
- Obtaining spatial information, including illumination information, for multiple spots in a space.
- Selecting at least one spot from the spatial information and obtaining illumination information for that spot.
- Generating training data by combining the obtained illumination information with images captured at the selected spot.
- Training a neural network model for object recognition using the training data.
Potential Applications
This technology could be applied in various fields such as autonomous driving, surveillance systems, and robotics for improved object recognition capabilities.
Problems Solved
This method addresses the challenge of training object recognition models in varying lighting conditions by incorporating spatial information, leading to more robust and accurate recognition.
Benefits
The use of spatial information for training enhances the model's ability to recognize objects under different lighting conditions, improving overall performance and reliability.
Potential Commercial Applications
Commercial applications for this technology include enhancing security systems, optimizing industrial automation processes, and improving the accuracy of medical imaging systems.
Possible Prior Art
One possible prior art in this field is the use of convolutional neural networks for object recognition, but the specific incorporation of spatial information, such as illumination data, may be a novel aspect of this innovation.
Unanswered Questions
How does this method compare to existing techniques for object recognition models trained on spatial information?
This article does not provide a direct comparison with existing techniques, leaving the reader to wonder about the specific advantages or limitations of this method compared to others in the field.
What are the potential limitations or challenges of implementing this technology in real-world applications?
The article does not address the practical challenges or limitations that may arise when implementing this technology in real-world scenarios, leaving room for speculation on potential obstacles or constraints.
Original Abstract Submitted
a method of training an object recognition model by using spatial information is provided. the method includes obtaining spatial information including illumination information corresponding to a plurality of spots in a space, obtaining illumination information corresponding to at least one spot of the plurality of spots from the spatial information, obtaining training data by using the obtained illumination information and an image obtained by capturing the at least one spot, and training a neural network model for object recognition by using the training data.
