Realtime Access Map
A direct approach for object detection with catadioptric omnidirectional cameras
MetadataShow full item record
In this paper, we present an omnidirectional vision-based method for object detection. We first adopt the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras. Main steps are modification of gradient magnitudes using Riemannian metric and conversion of gradient orientations to form an omnidirectional sliding window. In this way, we perform object detection directly on the omnidirectional images without converting them to panoramic or perspective images. Our experiments, with synthetic and real images, compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the proposed approach should be preferred.
Showing items related by title, author, creator and subject.
Tamur Kaya, Gamze (Izmir Institute of Technology, 2019-07)Measuring and monitoring body temperature has importance for disease diagnosis. It could also help following the course of the disease. Extensive number of body temperature monitoring applications are designed and developed. ...
Sarıgil, Öykü (Izmir Institute of Technology, 2019-07)Adipocytes are the major energy depots which primarily compose adipose tissue in the body. They are mainly responsible for energy balance and also play a crucial role as endocrine and paracrine cells. Hypertrophy (cell ...
Detection and localization of motorway overhead directional signs by convolutional neural networks trained with synthetic images Hekimgil, Hakan (Izmir Institute of Technology, 2019-07)Image classification, object detection and recognition have gone a long way in the last decade. The competitions, starting with ImageNet, have shown that various improving implementations of Artificial Neural Networks ...