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.
@article{arxiv.1603.00502,
title = {Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features},
author = {JT Turner and Kalyan Gupta and Brendan Morris and David W. Aha},
journal= {arXiv preprint arXiv:1603.00502},
year = {2016}
}