Multi-scale Conditional Random Fields for first-person activity recognition on elders and disabled patients

Robust multi-dimensional motion features for first-person vision activity recognition

“…Therefore, motion in FPV of an ambulatory activity is generally dominated by a global motion on which discriminant features are extracted. Existing motion-features use either raw grid optical flow [8,11] or limited directional and/or magnitude information [12][13][14] . Motion patterns of activities can vary in their magnitude, direction and frequency characteristics [14] .…”

“…For example, on the one hand, Walk and Run have similar direction but different magnitudes and frequency patterns, on the other hand, Sit-down and Stand-up possess similar motion magnitudes but in opposite directions. Generally, existing works employ either interest point-based [12,13] or optical flow-based [8][9][10][11]14] methods in order to estimate motion and then extract features.…”

“…1 ) include life-logging and video summarization [3][4][5][6][7] , activity recognition [8][9][10][11][12][13][14][15][16][17][18][19][20][21] , and eye-tracking and gaze detection [22][23][24][25] . Human activities can be categorized as ambulatory (e.g., walk) [8][9][10][11][12][13][14][15] ; person-to-object interactions (e.g., cook) [16][17][18][19] ; and person-to-person interactions (e.g., handshake) [20,21] . In particular, the recognition of ambulatory activities [26] involving a fullbody motion ( Fig.…”

“…3 ). Wearable cameras are often employed jointly with other sensors, more commonly with inertial sensors [8][9][10] , in order to leverage the merits of the latter. However, using multiple wearable sensors results in obtrusiveness of the system, complexity of the preprocessing stage (e.g., need for synchronization), and higher computational cost for feature extraction.…”

An Activity Recognition-Assistance Algorithm Based on Hybrid Semantic Model in Smart Home

“…The most prominent one is the living assistance system. Implementing assistance services based on the wireless SH infrastructure can dramatically improve the living quality of people who cannot take care of themselves and handle their common lives [7][8][9][10][11]. For example, the emergency of people suffering Alzheimer's disease can be recognized and assistance is provided.…”