Simultaneous segmentation and classification of human actions in video streams using deeply optimized Hough transform

Abstract

Most researches on human activity recognition do not take into account the temporal localization of actions. In this paper, a new method is designed to model both actions and their temporal domains. This method is based on a new Hough method which outperforms previous published ones on honeybee dataset thanks to a deeper optimization of the Hough variables. Experiments are performed to select skeleton features adapted to this method and relevant to capture human actions. With these features, our pipeline improves stateof-the-art performances on TUM dataset and outperforms baselines on several public datasets.

Customer Analysis via Video Analytics: Customer Detection with Multiple Cues

“…Customer behavior analysis via video analytics employs and integrates techniques from various related fields, e.g., motion detection [6] [7], pedestrian detection [8] [9], object detection and recognition [10][11] [12], object tracking [14] [15], and activity recognition [16][17] [18].…”

An Anti-Collision Method of Slip Barrel for Automatic Ship Loading in Bulk Terminal

“…In the theory of line fitting of Hough transform, each pixel of binary image can be represented by in with polar coordinates of the Equation 8 [23][24][25]. is the angle between point and the x-axis and is the distance between point with coordinate origin.…”

Application of Assistive Computer Vision Methods to Oyama Karate Techniques Recognition

“…Most researches on human activity recognition do not take into account the temporal localization of actions. In paper [21], a new method is designed to model both actions and their temporal domains. This method is based on a new Hough method.…”