Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions
3D action recognition has broad applications in human-computer interaction and intelligent surveillance. However, recognizing similar actions remains challenging since previous literature fails to capture motion and shape cues effectively from noisy depth data. In this paper, we propose a novel two-layer Bag-of-Visual-Words (BoVW) model, which suppresses the noise disturbances and jointly encodes both motion and shape cues. First, background clutter is removed by a background modeling method that is designed for depth data. Then, motion and shape cues are jointly used to generate robust and distinctive spatial-temporal interest points (STIPs): motion-based STIPs and shape-based STIPs. In the first layer of our model, a multi-scale 3D local steering kernel (M3DLSK) descriptor is proposed to describe local appearances of cuboids around motion-based STIPs. In the second layer, a spatial-temporal vector (STV) descriptor is proposed to describe the spatial-temporal distributions of shape-based STIPs. Using the Bag-of-Visual-Words (BoVW) model, motion and shape cues are combined to form a fused action representation. Our model performs favorably compared with common STIP detection and description methods. Thorough experiments verify that our model is effective in distinguishing similar actions and robust to background clutter, partial occlusions and pepper noise.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Action RecognitionAction RecognitionTemporal Action LocalizationSimilar Papers 제목 키워드 기반
Real-time 3D human action recognition based on Hyperpoint sequence
Real-time 3D human action recognition has broad industrial applications, such as surveillance, human-computer interaction, and healthcare monitoring. By relying on complex spatio-temporal local encoding, most existing po…
3D Action RecognitionAction RecognitionTemporal Action LocalizationFeature Sampling Strategies for Action Recognition
Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scalin…
Action RecognitionTemporal Action LocalizationMultimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living
Domain shifts, such as appearance changes, are a key challenge in real-world applications of activity recognition models, which range from assistive robotics and smart homes to driver observation in intelligent vehicles.…
Activity Recognitionmultimodal generationOptical Flow EstimationHabitAction: A Video Dataset for Human Habitual Behavior Recognition
Human Action Recognition (HAR) is a very crucial task in computer vision. It helps to carry out a series of downstream tasks, like understanding human behaviors. Due to the complexity of human behaviors, many highly valu…
Action RecognitionTemporal Action LocalizationSampling Strategies for Real-Time Action Recognition
Local spatio-temporal features and bag-of-features representations have become popular for action recognition. A recent trend is to use dense sampling for better performance. While many methods claimed to use dense featu…
Action RecognitionComputational EfficiencyTemporal Action Localization