A Systematic Solution for Moving-Target Detection and Tracking While Only Using a Monocular Camera

This paper focuses on moving-target detection and tracking in a three-dimensional (3D) space, and proposes a visual target tracking system only using a two-dimensional (2D) camera. To quickly detect moving targets, an improved optical flow method with detailed modifications in the pyramid, warping, and cost volume network (PWC-Net) is applied. Meanwhile, a clustering algorithm is used to accurately extract the moving target from a noisy background. Then, the target position is estimated using a proposed geometrical pinhole imaging algorithm and cubature Kalman filter (CKF). Specifically, the camera's installation position and inner parameters are applied to calculate the azimuth, elevation angles, and depth of the target while only using 2D measurements. The proposed geometrical solution has a simple structure and fast computational speed. Different simulations and experiments verify the effectiveness of the proposed method.

Automated summary

This paper focuses on moving-target detection and tracking in a three-dimensional (3D) space, proposing a visual target tracking system that only utilizes a two-dimensional (2D) camera. An improved optical flow method, with modifications in the pyramid, warping, and cost volume network (PWC-Net), is applied for quick target detection. Additionally, a clustering algorithm accurately extracts the moving target from a noisy background. The target position is then estimated using a proposed geometrical pinhole imaging algorithm and cubature Kalman filter (CKF) based on the camera's installation position and inner parameters.