RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images
This addresses the challenge of accurately detecting people in fisheye images for applications like surveillance, though it is incremental as it builds on existing detection methods with a rotation-aware approach.
The paper tackles the problem of people detection in overhead fisheye images by developing RAPiD, an end-to-end rotation-aware method that uses arbitrarily-oriented bounding boxes, and it outperforms state-of-the-art results on three datasets.
Recent methods for people detection in overhead, fisheye images either use radially-aligned bounding boxes to represent people, assuming people always appear along image radius or require significant pre-/post-processing which radically increases computational complexity. In this work, we develop an end-to-end rotation-aware people detection method, named RAPiD, that detects people using arbitrarily-oriented bounding boxes. Our fully-convolutional neural network directly regresses the angle of each bounding box using a periodic loss function, which accounts for angle periodicities. We have also created a new dataset with spatio-temporal annotations of rotated bounding boxes, for people detection as well as other vision tasks in overhead fisheye videos. We show that our simple, yet effective method outperforms state-of-the-art results on three fisheye-image datasets. Code and dataset are available at http://vip.bu.edu/rapid .