6533b85bfe1ef96bd12ba12f

RESEARCH PRODUCT

CDnet 2014: An Expanded Change Detection Benchmark Dataset

Prakash IshwarFatih PorikliYannick BenezethYi WangJanusz KonradPierre-marc Jodoin

subject

[ INFO.INFO-TS ] Computer Science [cs]/Signal and Image Processingbusiness.industryComputer science[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingMotion detection[ SPI.SIGNAL ] Engineering Sciences [physics]/Signal and Image processingcomputer.software_genre[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingAnalyticsBenchmark (computing)Data miningbusinesscomputer[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processingChange detection[SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing

description

International audience; Change detection is one of the most important low-level tasks in video analytics. In 2012, we introduced the changedetection.net (CDnet) benchmark, a video dataset devoted to the evalaution of change and motion detection approaches. Here, we present the latest release of the CDnet dataset, which includes 22 additional videos (~70,000 pixel-wise annotated frames) spanning 5 new categories that incorporate challenges encountered in many surveillance settings. We describe these categories in detail and provide an overview of the results of more than a dozen methods submitted to the IEEE Change Detection Workshop 2014. We highlight strengths and weaknesses of these methods and identify remaining issues in change detection.

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01018757/document