Intelligent 3D Cognitive Semantic Map Exploration and Integration Service Robotic System for Assisted Elder Care Applications(II)

We implemented the object recognition architecture with the state-of-the-art robtic tool – ROS and use it recognize some commonly seen objects in our daily lives.

Object recognition research is not good enough, because of there are too many kinds of objects in the world so that object recognition problem is not easy to deal with. Because human can easily recognize objects with simple shape, but dealing with complex objects, human tends to divide this complex object into the combinations of simple objects.

The main contributions of our research are listed below:

First, we categorize all objects into simple objects consisting of features such as shape and complex objects consisting of simple objects.

Second, we propose a concept using the object’s functions to define the features of object. These features are called human-adopted features.

Third, we use human-adopted features to simplify object recognition problem into three sub-problems.

Fourth, we assume if the first two sub-problems are perfectly solved, we can solve the third sub-problem by the algorithm combining the concept similar to inverted files and intersection to achieve 100% recognition rate.

Fifth, we prove the algorithm used to solve the third sub-problem is totally correct.

Sixth, we’ll present the claim in the experiment – “Assume the first two sub-problems are solves, we can achieve 100% recognition rate”.