Accurate Human Localization for Automatic Labelling of Human from Fisheye Images
- Authors
- Van Pha Than; Thanh Binh Nguyen; 정선태
- Issue Date
- May-2017
- Publisher
- 한국멀티미디어학회
- Keywords
- Human Localization; Fisheye Camera; CNN (Convolutional Neural Networks); GoogLeNet; Long Short Term Memory; Saliency Detection
- Citation
- 멀티미디어학회논문지, v.20, no.5, pp.769 - 781
- Journal Title
- 멀티미디어학회논문지
- Volume
- 20
- Number
- 5
- Start Page
- 769
- End Page
- 781
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/6717
- DOI
- 10.9717/kmms.2017.20.5.769
- ISSN
- 1229-7771
- Abstract
- Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground- Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.
- Files in This Item
-
Go to Link
- Appears in
Collections - College of Information Technology > Department of Smart Systems Software > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/6717)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.