CDnet 2014: An Expanded Change Detection Benchmark Dataset

TLDR

Change detection is a key low‑level task in video analytics, and the CDnet benchmark, introduced in 2012, provides a dataset for evaluating change and motion detection methods. The authors present the latest CDnet release, adding 22 videos with 70,000 pixel‑wise annotated frames across five new categories reflecting surveillance challenges. The dataset expansion includes detailed category descriptions and an overview of results from over a dozen methods submitted to the 2014 IEEE Change Detection Workshop. The study highlights the strengths and weaknesses of the evaluated methods and identifies remaining challenges in change detection.

Abstract

Change detection is one of the most important lowlevel 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 DetectionWorkshop 2014. We highlight strengths and weaknesses of these methods and identify remaining issues in change detection.