کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
535550 870353 2013 12 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Common-sense reasoning for human action recognition
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
پیش نمایش صفحه اول مقاله
Common-sense reasoning for human action recognition
چکیده انگلیسی

This paper presents a novel method that leverages reasoning capabilities in a computer vision system dedicated to human action recognition. The proposed methodology is decomposed into two stages. First, a machine learning based algorithm – known as bag of words – gives a first estimate of action classification from video sequences, by performing an image feature analysis. Those results are afterward passed to a common-sense reasoning system, which analyses, selects and corrects the initial estimation yielded by the machine learning algorithm. This second stage resorts to the knowledge implicit in the rationality that motivates human behaviour. Experiments are performed in realistic conditions, where poor recognition rates by the machine learning techniques are significantly improved by the second stage in which common-sense knowledge and reasoning capabilities have been leveraged. This demonstrates the value of integrating common-sense capabilities into a computer vision pipeline.

Figure optionsDownload high-quality image (80 K)Download as PowerPoint slideHighlights
► Action recognition approach which combines statistical & knowledge based reasoning.
► First fully context & scenario independent framework combing computer vision and AI.
► Inclusion of artificial intelligence strategies, based on common sense reasoning.
► Results outperform state-of-art in computer vision under real-life conditions.
► Computer vision authors should not focus only on machine learning but also on AI.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition Letters - Volume 34, Issue 15, 1 November 2013, Pages 1849–1860
نویسندگان
, , ,