Skip to Main Content
Visual object recognition is a useful skill for robots to possess. However, present approaches to the problem do not scale to large numbers of objects (few manage more than 10) and require too much computation for real-time tasks on a robot. This paper presents a hybrid decision tree/support vector machine approach to recognition which is fast, with recognition times under one second. A new test dataset is also presented, consisting of over 100,000 images of Lego bricks, acquired by repeatedly dropping the bricks. The proposed method achieves 96% accuracy on the set of 89 different types of Lego bricks, demonstrating its applicability for large-scale real-time visual object recognition.