|Title||Keypoint Density-based Region Proposal for Fine-Grained Object Detection using Regions with Convolutional Neural Network Features|
|Year of Publication||2015|
|Authors||Turner, JT, Gupta, K, Morris, B, Aha, DW|
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 on fine-grained tasks by 100% versus the existing selective search region proposal technique without compromising detection accuracy. KDRP makes the application of CNNs to real-time detection and classification feasible.
NRL Publication Release Number: