Object detection with convolutional context features
Year: 2017
Type: conference-paper
Abstract: A novel extension to Hızlı B-ESA object detection algorithm is proposed in order to learn convolutional context features for determining boundaries of objects better. For input images, the hypothesis windows and their context around those windows are learned through convolutional layers as two parallel networks. The resulting object and context feature maps are combined in such a way that they preserve their spatial relationship. The proposed algorithm is trained and evaluated on PASCAL VOC 2007 detection benchmark dataset and yielded improvements in performance over state-of-the-art, for almost all classes, especially the ones with distinctive context.
Authors: Emre Can Kaya, A. Aydin Alatan
Institution: Middle East Technical University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2725693418