An Object Detection Method Using Invariant Feature Based on Local Hue Histogram in Divided Areas of an Object

In recent years, the decreasing birthrate and aging population are developing, and there is concern about the lack of labor power such as household chores and nursing care at home. Therefore, application of robot technology to the living field is expected. In the living field, Robots that support the lives of people are collectively referred to as life support robots. This robot is required to perform various tasks to support humans. Especially, the object detection task is important when people request the robot to transport and rearrange objects. However, when detecting an object from the camera mounted on the robot, detection becomes difficult because the detection environment is unspecified. Scale Invariant Feature Transform (SIFT) and Color Indexing are widely known as object detection methods using two-dimensional information. However, these methods do not have robustness against all environmental changes. In this research, we focus on the invariant feature of the hue histogram in divided areas of an object and propose a highly accurate object detection method.