Adaptive Contour Feature and Color Feature Fusion for Monocular Textureless 3D Object Tracking

Contour-matching-based textureless 3-D object tracking algorithms commonly use 3-D–2-D correspondence between the 3-D object model and 2-D object contour in the image to track the 3-D object. However, this often fails in highly cluttered backgrounds or in presence of motion blur. To overcome this problem, we propose a monocular textureless 3-D object tracking method based on adaptive fusion of contour feature and color feature. First, contour matching and local color statistics are performed nearby the projection contour of 3-D model to extract contour feature and color feature. Then, the energy function is defined based on adaptively weighted contour feature and statistical color feature, and the differentials of this energy function with respect to pose parameters of the 3-D object are derived. Finally, the optimal pose is obtained via LM solver. To deal with fast motion of object and camera, a coarse-to-fine tracking strategy is applied iteratively for multi-scale video frames. Qualitative and quantitative experiments show that the proposed algorithm has a great advantage over other state-of-the-art algorithms in the case of cluttered background and motion blur, and can obtain more accurate and robust tracking results.