Camera Motion and Surrounding Scene Appearance as Context for Action Recognition
نویسندگان
چکیده
This paper describes a framework for recognizing human actions in videos by incorporating a new set of visual cues that represent the context of the action. We develop a weak foreground-background segmentation approach in order to robustly extract not only foreground features that are focused on the actors, but also global camera motion and contextual scene information. Using dense point trajectories, our approach separates and describes the foreground motion from the background, represents the appearance of the extracted static background, and encodes the global camera motion that interestingly is shown to be discriminative for certain action classes. Our experiments on four challenging benchmarks (HMDB51, Hollywood2, Olympic Sports, and UCF50) show that our contextual features enable a significant performance improvement over state-of-the-art algorithms.
منابع مشابه
Surrounding Scene Appearance as Contextual Features for Action Recognition
This notebook paper describes the submission of the KAUSTUNINORTE team to the challenge THUMOS 2014. Our system extracts a new set of visual cues that represent the context of an action as described in [1]. Using dense point trajectories, our approach separates and describes the foreground motion from the background and represents the appearance of the extracted static background that interesti...
متن کاملPedestrians Tracking in a Camera Network
With the increase of the number of cameras installed across a video surveillance network, the ability of security staffs to attentively scan all the video feeds actually decreases. Therefore, the need for an intelligent system that operates as a tracking system is vital for security personnel to do their jobs well. Tracking people as they move through a camera network with non-overlapping field...
متن کاملPedestrians Tracking in a Camera Network
With the increase of the number of cameras installed across a video surveillance network, the ability of security staffs to attentively scan all the video feeds actually decreases. Therefore, the need for an intelligent system that operates as a tracking system is vital for security personnel to do their jobs well. Tracking people as they move through a camera network with non-overlapping field...
متن کاملFeature Tracking and Motion Compensation for Action Recognition
This paper discusses an approach to human action recognition via local feature tracking and robust estimation of background motion. The main contribution is a robust feature extraction algorithm based on KLT tracker and SIFT as well as a method for estimating dominant planes in the scene. Multiple interest point detectors are used to provide large number of features for every frame. The motion ...
متن کاملAction Change Detection in Video Based on HOG
Background and Objectives: Action recognition, as the processes of labeling an unknown action of a query video, is a challenging problem, due to the event complexity, variations in imaging conditions, and intra- and inter-individual action-variability. A number of solutions proposed to solve action recognition problem. Many of these frameworks suppose that each video sequence includes only one ...
متن کامل