Real-time Object Recognition in Sparse Range Images Using Error Surface Embedding

A novel object recognition algorithm is introduced to identify objects and recover their pose from sparse range data. The method is based upon comparing the 7-D error surfaces of objects in various poses, which result from the registration error function between two convolved surfaces. The objects and their pose values are encoded by a small set of feature vectors extracted from the minima of the error surfaces. The problem of object recognition is thus reduced to comparing these feature vectors to find the corresponding error surfaces between the runtime data and a preprocessed database. The algorithm, called Potential Well Space Embedding (PWSE) has been implemented and tested on both simulated and real data. The experimental results show the technique to be both effective and efficient, executing at 122 frames per second on standard hardware and with recognition rates exceeding 97% for a database of 60 objects. The performance of PWSE on the large size database was also evaluated on the Princeton Shape Benchmark containing 1,814 objects. In addition, it functions well with very sparse data, possibly comprising only hundreds of points per image, and is shown to be robust to measurement error and outliers. With some small modifications, we applied PWSE to the problem of object class recognition. In experiments with the Princeton Shape Benchmark, PWSE is able to provides better classification rates than the previous methods in terms of nearest neighbour classification.