DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click HERE
to register or log in.
Keypoint Density-Based Region Proposal for Fine-Grained Object Detection and Classification Using Regions with Convolutional Neural Network Features
KNEXUS RESEARCH CORP NATIONAL HARBOR MD NATIONAL HARBOR
Pagination or Media Count:
Although recent advances in regional Convolutional Neural Networks CNNs enable them to outperform conventional techniques on standard object detection and classification tasks, their response time is still slow for real-time performance. To address this issue, we propose a method for region proposal as an alternative to selective search, which is used in current state-of-the art object detection algorithms. We evaluate our Keypoint Density-based Region Proposal KDRP approach and show that it speeds up detection and classification on fine-grained tasks by 100 versus the existing selective search region proposal technique without compromising classification accuracy. KDRP makes the application of CNNs to real-time detection and classification feasible.
APPROVED FOR PUBLIC RELEASE