Detection of Nearby Obstacles with Monocular Vision for Earthmoving Operations

Abstract

The equipment used in earthmoving operations poses a significant threat to the safety of the equipment operator and construction workers due to the operator's inherently poor visibility of the surrounding environment. This study proposes a method of automated detection of nearby obstacles with monocular vision, with the goal of protecting the equipment operator and construction workers from potentially dangerous situations, such as collisions between earthmoving equipment and obstacles within a certain proximity. The proposed method consists of three steps: 1) correction of lens distortion prior to further processing, 2) shadow removal, and 3) detection of nearby obstacles with a predefined height level via perspective transformations. The proposed method was tested on video streams acquired from a camera installed on the side of the equipment body while an excavator executed excavating and moving tasks. The experimental results showed that the proposed method can provide the equipment operator with information about nearby obstacles during the excavator's manipulation and transportation. It is expected that the proposed method can be implemented in rearview monitoring systems and surrounding view monitoring systems for operator assistance and to achieve active safety.