A method of image target detection based on dc-spp-yolo
A technology of DC-SPP-YOLO and target detection, which is applied in the direction of instrumentation, computing, character and pattern recognition, etc., can solve problems such as gradient disappearance, local area characteristics ignored, and information flow hindered
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0067] The embodiment uses the public and widely used PASCALVOC (2007+2012) standard data set for image recognition and target detection algorithm performance evaluation to carry out the training and testing of the DC-SPP-YOLO model; wherein the VOC 2007+2012 data set contains image samples 32,487 images, 8,218 images in the training dataset, 8,333 images in the verification dataset, 4,952 images in the VOC 2007 test dataset, and 10,990 images in the VOC 2012 test dataset.
[0068] The computer configuration of embodiment is Intel (R) Xeon (R) E5-2643 3.3GHz CPU, 32.00GB memory, 1 Navida GTX 1080Ti GPU that memory is 11.00GB. The embodiment is carried out on the Windows 10 system Visual Studio 2017 platform, and the deep learning framework used is Darknet, which is realized by programming in C / C++ language.
[0069] Apply the present invention to the above-mentioned PASCAL VOC data set image target detection, the specific steps are as follows:
[0070] Step 1: Use geometric t...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com