کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6937471 | 1449738 | 2017 | 22 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
SMC faster R-CNN: Toward a scene-specialized multi-object detector
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
چشم انداز کامپیوتر و تشخیص الگو
پیش نمایش صفحه اول مقاله

چکیده انگلیسی
Generally, the performance of a generic detector decreases significantly when it is tested on a specific scene due to the large variation between the source training dataset and the samples from the target scene. To solve this problem, we propose a new formalism of transfer learning based on the theory of a Sequential Monte Carlo (SMC) filter to automatically specialize a scene-specific Faster R-CNN detector. The suggested framework uses different strategies based on the SMC filter steps to approximate iteratively the target distribution as a set of samples in order to specialize the Faster R-CNN detector towards a target scene. Moreover, we put forward a likelihood function that combines spatio-temporal information extracted from the target video sequence and the confidence-score given by the output layer of the Faster R-CNN, to favor the selection of target samples associated with the right label. The effectiveness of the suggested framework is demonstrated through experiments on several public traffic datasets. Compared with the state-of-the-art specialization frameworks, the proposed framework presents encouraging results for both single and multi-traffic object detections.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computer Vision and Image Understanding - Volume 164, November 2017, Pages 3-15
Journal: Computer Vision and Image Understanding - Volume 164, November 2017, Pages 3-15
نویسندگان
Ala Mhalla, Thierry Chateau, Houda Maâmatou, Sami Gazzah, Najoua Essoukri Ben Amara,