جهت دسترسی به کاربرگه ی زیر، از این لینک استفاده کنید. http://localhost/handle/Hannan/623941
عنوان: NUS-PRO: A New Visual Tracking Challenge
پدیدآورنده: Annan Li;Min Lin;Yi Wu;Ming-Hsuan Yang;Shuicheng Yan
کلید واژه ها: performance evaluation;Object tracking;benchmark database
تاریخ انتشار: 2016
ناشر: IEEE
چکیده: Numerous approaches on object tracking have been proposed during the past decade with demonstrated success. However, most tracking algorithms are evaluated on limited video sequences and annotations. For thorough performance evaluation, we propose a large-scale database which contains 365 challenging image sequences of pedestrians and rigid objects. The database covers 12 kinds of objects, and most of the sequences are captured from moving cameras. Each sequence is annotated with target location and occlusion level for evaluation. A thorough experimental evaluation of 20 state-of-the-art tracking algorithms is presented with detailed analysis using different metrics. The database is publicly available and evaluation can be carried out online for fair assessments of visual tracking algorithms.
توضیحات : 
آدرس: http://localhost/handle/Hannan/150979
http://localhost/handle/Hannan/623941
ISSN: 0162-8828
دوره: 38
شماره: 2
مجموعه(های):2016

پیوست های این کاربرگه
فایل توضیحات اندازهفرمت  
7072555.pdf1.44 MBAdobe PDFتصویر
مشاهده فایل
عنوان: NUS-PRO: A New Visual Tracking Challenge
پدیدآورنده: Annan Li;Min Lin;Yi Wu;Ming-Hsuan Yang;Shuicheng Yan
کلید واژه ها: performance evaluation;Object tracking;benchmark database
تاریخ انتشار: 2016
ناشر: IEEE
چکیده: Numerous approaches on object tracking have been proposed during the past decade with demonstrated success. However, most tracking algorithms are evaluated on limited video sequences and annotations. For thorough performance evaluation, we propose a large-scale database which contains 365 challenging image sequences of pedestrians and rigid objects. The database covers 12 kinds of objects, and most of the sequences are captured from moving cameras. Each sequence is annotated with target location and occlusion level for evaluation. A thorough experimental evaluation of 20 state-of-the-art tracking algorithms is presented with detailed analysis using different metrics. The database is publicly available and evaluation can be carried out online for fair assessments of visual tracking algorithms.
توضیحات : 
آدرس: http://localhost/handle/Hannan/150979
http://localhost/handle/Hannan/623941
ISSN: 0162-8828
دوره: 38
شماره: 2
مجموعه(های):2016

پیوست های این کاربرگه
فایل توضیحات اندازهفرمت  
7072555.pdf1.44 MBAdobe PDFتصویر
مشاهده فایل
عنوان: NUS-PRO: A New Visual Tracking Challenge
پدیدآورنده: Annan Li;Min Lin;Yi Wu;Ming-Hsuan Yang;Shuicheng Yan
کلید واژه ها: performance evaluation;Object tracking;benchmark database
تاریخ انتشار: 2016
ناشر: IEEE
چکیده: Numerous approaches on object tracking have been proposed during the past decade with demonstrated success. However, most tracking algorithms are evaluated on limited video sequences and annotations. For thorough performance evaluation, we propose a large-scale database which contains 365 challenging image sequences of pedestrians and rigid objects. The database covers 12 kinds of objects, and most of the sequences are captured from moving cameras. Each sequence is annotated with target location and occlusion level for evaluation. A thorough experimental evaluation of 20 state-of-the-art tracking algorithms is presented with detailed analysis using different metrics. The database is publicly available and evaluation can be carried out online for fair assessments of visual tracking algorithms.
توضیحات : 
آدرس: http://localhost/handle/Hannan/150979
http://localhost/handle/Hannan/623941
ISSN: 0162-8828
دوره: 38
شماره: 2
مجموعه(های):2016

پیوست های این کاربرگه
فایل توضیحات اندازهفرمت  
7072555.pdf1.44 MBAdobe PDFتصویر
مشاهده فایل