This is accomplished by a periodic loss function based on an extension of a common regression loss. In addition to predicting the center and size of a bounding box, RAPiD also predicts its angle. The network architecture diagram is shown below. It extends the model proposed in YOLO, one of the most successful object detection algorithms for standard images. Technical Approach: RAPiD is a single-stage fully-convolutional neural network that predicts arbitrarily-rotated bounding boxes of people in a fisheye image. Our fully- convolutional neural network directly regresses the angle of each bounding box using a periodic loss function, which accounts for angle periodicities. We show that our simple, yet effective method outperforms state-of-the-art results on three datasets: Mirror Worlds, HABBOF, and CEPDOF. In this work, we propose a faster and accurate approach by designing an end-to-end neural network, which extends YOLO v3 to precisely handle human-body orientation in overhead fisheye images. The main reason for this is the fact that the algorithm applies YOLO (version 3) to each fisheye image up to 24 times. produced accurate results at very high computational complexity even on a relatively small HABBOF dataset it required tens of GPU-hours during inference. Summary: Our previous people-detection algorithm for fisheye images by Li et al. In this work, we develop a fast people-detection algorithm for overhead fisheye images. Ozan Tezcan, Hayato Nakamura, Prakash Ishwar, Janusz Konradįunding : Advanced Research Projects Agency – Energy (ARPA-E)īackground : Occupancy sensing is an enabling technology for smart buildings of the future knowing where and how many people are in a building is key for saving energy, space management and security (e.g., fire, active shooter). RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |