Print Email Facebook Twitter People Detection from Overhead Cameras Title People Detection from Overhead Cameras: A study of impact of occlusion on performance Author Liu, Lu (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Hung, H.S. (mentor) Cabrera Quiros, L.C. (graduation committee) Reinders, M.J.T. (graduation committee) Kooij, J.F.P. (graduation committee) Degree granting institution Delft University of Technology Programme Electrical Engineering | Embedded Systems Date 2018-08-31 Abstract During the last decades, people detection has received great attention in computer vision and pattern recognition because of its various applications. Though there are thousands of papers provide approaches for people detection, most of them focus on datasets from side view. People detection from overhead cameras, as an important situation for surveillance, is essential to research. This work based on annotated videos from MatchNMingle dataset, which are taken by overhead cameras. The videos were taken in a mingle after a speed-dating event. People are annotated by bounding boxes contain their body. In this crowded social scene, people occlusion is one of the challenge barriers for detection. In this work, we study the relation between people occlusion and detecting performance by experiments. Based on a deep network consisting of GoogLeNet and Overfeat, we analyze the performance of detectors trained with various occlusion distribution at different occlusion level. On the ground of experiment results, we attempt to promote the performance by selection of training data. Apart from this, as an attempt for promotion, we train head detectors by newly collected head annotation. The performance evaluation of these two methods indicates their potential for people detection in crowded scene. Subject People DetectionOcclusionDeep Learning To reference this document use: http://resolver.tudelft.nl/uuid:33a6b9b6-f26c-4ef1-8047-5c33d95487c6 Part of collection Student theses Document type master thesis Rights © 2018 Lu Liu Files PDF Thesis_Report_LuLiu_4.pdf 8.54 MB Close viewer /islandora/object/uuid:33a6b9b6-f26c-4ef1-8047-5c33d95487c6/datastream/OBJ/view