# Unstructured Human Activity Detection from RGBD Images Source: [Unstructured Human Activity Detection from RGBD Images]() Collection index: [llms.txt]() Data updated: 2025-10-25T19:58:36.387Z Authors: Jaeyong Sung, Colin Ponce, Bart Selman, Ashutosh Saxena Published: 2011-07-01T09:41:12.000Z ## Abstract Being able to detect and recognize human activities is essential for several applications, including personal assistive robotics. In this paper, we perform detection and recognition of unstructured human activity in unstructured environments. We use a RGBD sensor (Microsoft Kinect) as the input sensor, and compute a set of features based on human pose and motion, as well as based on image and pointcloud information. Our algorithm is based on a hierarchical maximum entropy Markov model (MEMM), which considers a person's activity as composed of a set of sub-activities. We infer the two-layered graph structure using a dynamic programming approach. We test our algorithm on detecting and recognizing twelve different activities performed by four people in different environments, such as a kitchen, a living room, an office, etc., and achieve good performance even when the person was not seen before in the training set. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Activity Recognition on Cornell Activity Dataset CAD-60 (New Person)](): Activity Recognition; Cornell Activity Dataset CAD-60 (New Person); Precision (Bathroom): 72.7. - [High-level Activity Labeling on CAD-120](): High-level Activity Labeling; CAD-120; Micro P/R: 26.4. ## Original sources and implementation [Original paper]() [PDF]()