Human motion analysis from UAV video. Issue 2 (16th April 2018)

• Record Type: Journal Article
• Authors: Perera, Asanka G.; Law, Yee Wei; Al-Naji, Ali; Chahl, Javaan
• Is Part Of: International journal of intelligent unmanned systems. Volume 6:Issue 2(2018)
• Page Start: 69
• Page End: 92
• Publication Date: 2018-04-16
• Subjects: UAV -- Pose estimation -- Dynamic classifier selection -- Gait estimation -- Trajectory estimation; Vehicles, Remotely piloted -- Periodicals; Robots -- Control systems -- Periodicals; Mechanical engineering -- Robots -- Periodicals; Robotics -- Periodicals; Submersibles -- Periodicals; Space vehicles -- Command control systems -- Periodicals; 629.046
• DOI: 10.1108/IJIUS-10-2017-0012
• Languages: English
• ISSNs: 2049-6427

Abstract

Abstract : Purpose: The purpose of this paper is to present a preliminary solution to address the problem of estimating human pose and trajectory by an aerial robot with a monocular camera in near real time. Design/methodology/approach: The distinguishing feature of the solution is a dynamic classifier selection architecture. Each video frame is corrected for perspective using projective transformation. Then, a silhouette is extracted as a Histogram of Oriented Gradients (HOG). The HOG is then classified using a dynamic classifier. A class is defined as a pose-viewpoint pair, and a total of 64 classes are defined to represent a forward walking and turning gait sequence. The dynamic classifier consists of a Support Vector Machine (SVM) classifier C64 that recognizes all 64 classes, and 64 SVM classifiers that recognize four classes each – these four classes are chosen based on the temporal relationship between them, dictated by the gait sequence. Findings: The solution provides three main advantages: first, classification is efficient due to dynamic selection (4-class vs 64-class classification). Second, classification errors are confined to neighbors of the true viewpoints. This means a wrongly estimated viewpoint is at most an adjacent viewpoint of the true viewpoint, enabling fast recovery from incorrect estimations. Third, the robust temporal relationship between poses is used to resolve the left-right ambiguities of human silhouettes. Originality/value: Experiments conducted on both fronto-parallel videos and aerial videos confirm that the solution can achieve accurate pose and trajectory estimation for these different kinds of videos. For example, the "walking on an 8-shaped path" data set (1, 652 frames) can achieve the following estimation accuracies: 85 percent for viewpoints and 98.14 percent for poses.