Vision-Based System for 3D Tower Crane Monitoring

Cranes play an important role in the industry sectors worldwide, such as construction, transport, shipping and cargo industry. For the safety of loading and unloading materials there are definitely ongoing improvements in the crane industry. However, there still remains issues related to the crane operation and control measures given by the pendulum swing while the crane is moving. To solve this problem a vision-based movement control of a 3 degrees of freedom (3 DOF) crane system, using both an analytical and experimental models based on displacements and adaptive optimization algorithms was proposed. The framework consists of three steps, more precise recognition, detection and tracking a set of targets within the image to compute the payload displacement. A prepossessing process was applied in order to enhance the image improving both the color information and the edge extraction task. Then, a set of targets within the image were detected to estimate the displacement. Then to solve the problem given by the displacement, a tracking task was implemented using a second order filter. This paper introduces a new strategy to determine the relationship between the movement of the spin in the jib and position of the markers within the image. Regression analysis was carried out to take into account the motion of the cart and the payload. In Results Section is shown a set of real-time experiment, obtaining euclidean errors of 1.41 pixel, 2 pixels and 3.16 pixels for Cart, Jib and Hoist, respectively.