18527490. 3D OBJECT RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORK WITH DEPTH BASED MULTI-SCALE FILTERS simplified abstract (Intel Corporation)
Contents
- 1 3D OBJECT RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORK WITH DEPTH BASED MULTI-SCALE FILTERS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 3D OBJECT RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORK WITH DEPTH BASED MULTI-SCALE FILTERS - 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
3D OBJECT RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORK WITH DEPTH BASED MULTI-SCALE FILTERS
Organization Name
Inventor(s)
3D OBJECT RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORK WITH DEPTH BASED MULTI-SCALE FILTERS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18527490 titled '3D OBJECT RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORK WITH DEPTH BASED MULTI-SCALE FILTERS
Simplified Explanation
The patent application discusses techniques for training and implementing convolutional neural networks for object recognition, specifically focusing on using 3D filters of different spatial sizes at the first convolutional layer to generate multi-scale feature maps for object recognition data.
- Applying 3D filters of different spatial sizes at the first convolutional layer
- Generating multi-scale feature maps for object recognition data
- Providing pathways to fully connected layers for each feature map
- Recognizing objects in 3D input image segments
Potential Applications
The technology can be applied in various fields such as autonomous driving, medical imaging, surveillance systems, and robotics for object recognition and classification tasks.
Problems Solved
This technology addresses the challenge of accurately recognizing and classifying objects in 3D input image segments by generating multi-scale feature maps using 3D filters.
Benefits
The benefits of this technology include improved object recognition accuracy, enhanced feature extraction capabilities, and the ability to handle complex 3D input data for various applications.
Potential Commercial Applications
The technology can be utilized in industries such as automotive, healthcare, security, and manufacturing for developing advanced object recognition systems with improved performance and accuracy.
Possible Prior Art
Prior art in the field of convolutional neural networks and object recognition may include research papers, patents, and existing commercial products that utilize similar techniques for feature extraction and object classification.
Unanswered Questions
How does this technology compare to traditional 2D convolutional neural networks for object recognition tasks?
This article does not provide a direct comparison between the proposed 3D convolutional neural network approach and traditional 2D convolutional neural networks in terms of performance, efficiency, and accuracy for object recognition tasks.
What are the computational requirements for training and implementing 3D convolutional neural networks with multi-scale feature maps?
The article does not delve into the computational resources, training time, and memory requirements needed to train and implement 3D convolutional neural networks with multi-scale feature maps for object recognition tasks.
Original Abstract Submitted
Techniques related to training and implementing convolutional neural networks for object recognition are discussed. Such techniques may include applying, at a first convolutional layer of the convolutional neural network, 3D filters of different spatial sizes to an 3D input image segment to generate multi-scale feature maps such that each feature map has a pathway to fully connected layers of the convolutional neural network, which generate object recognition data corresponding to the 3D input image segment.
