IEEE Winter Conference on Applications of Computer Vision · 2014 · 127 citations · 11 references
ComputingComputer ScienceComputer VisionMachine LearningRobot VisionAction RecognitionDepth EstimationMotion AnalysisMotion CaptureMotion EstimationRepresentation LearningActivity RecognitionImportance MeasuresMotion Representation LearningOnline Action RecognitionRandom Forest ClassificationRandom ForestsSkeleton-based Action RecognitionSpatiotemporal Feature Learning
We propose an algorithm which combines the discriminative information from depth images as well as from 3D joint positions to achieve high action recognition accuracy. To avoid the suppression of subtle discriminative information and also to handle local occlusions, we compute a vector of many independent local features. Each feature encodes spatiotemporal variations of depth and depth gradients at a specific space-time location in the action volume. Moreover, we encode the dominant skeleton movements by computing a local 3D joint position difference histogram. For each joint, we compute a 3D space-time motion volume which we use as an importance indicator and incorporate in the feature vector for improved action discrimination. To retain only the discriminant features, we train a random decision forest (RDF). The proposed algorithm is evaluated on three standard datasets and compared with nine state-of-the-art algorithms. Experimental results show that, on the average, the proposed algorithm outperform all other algorithms in accuracy and have a processing speed of over 112 frames/second.
11
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
J. R. Quinlan · Machine Learning · 1986 · 14.8K citations · Full text
J. R. Quinlan · Machine Learning · 1986 · 12.4K citations · Full text
Real-time human pose recognition in parts from single depth images
Jamie Shotton, Andrew Fitzgibbon, Mat Cook et al. · 2011 · 3.5K citations
A Spatio-Temporal Descriptor Based on 3D-Gradients
Alexander Klaeser, C. Schmid · 2008 · 1.9K citations · Full text