Three-dimensional convolution and Faster RCNN-based video action detection method
A three-dimensional convolution and motion detection technology, applied in the field of image processing, can solve the problems of synchronous positioning and lack of spatial annotation information, and achieve the effect of motion positioning and excellent performance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0092] Example 1:
[0093] In the present invention, NVIDIA GPU is used as the computing platform, CUDA is used as the GPU accelerator, and Caffe is selected as the CNN framework.
[0094] S1 data preparation:
[0095] The ActivityNet 1.3 data set is used in this experiment. The ActivityNet data set consists only of untrimmed videos and has 200 different types of activities, including 10024 videos in the training set, 4926 videos in the validation set, and 5044 videos in the test set. Compared with THUMOS14, this is a large data set, regardless of the number of activity categories involved or the number of videos.
[0096] Step 1.1: Download the ActivityNet 1.3 data set from http: / / activity-net.org / download.html to the local.
[0097] Step 1.2: Convert the downloaded video into images according to 25 frames per second (fps), and the images of different subsets are placed in folders according to the corresponding video names.
[0098] Step 1.3: According to the data augmentation strateg...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap