Salient Bundle Adjustment for Visual SLAM
This work aims to improve the accuracy of visual SLAM for robotics applications by incorporating visual saliency, offering an incremental improvement to existing bundle adjustment techniques.
This paper proposes a Salient Bundle Adjustment method for Visual SLAM that uses a saliency prediction model to assign higher importance to salient feature points during optimization. Experiments on KITTI and EuRoc datasets show that the proposed algorithm outperforms existing state-of-the-art algorithms in both indoor and outdoor environments.
Recently, the philosophy of visual saliency and attention has started to gain popularity in the robotics community. Therefore, this paper aims to mimic this mechanism in SLAM framework by using saliency prediction model. Comparing with traditional SLAM that treated all feature points as equal important in optimization process, we think that the salient feature points should play more important role in optimization process. Therefore, we proposed a saliency model to predict the saliency map, which can capture both scene semantic and geometric information. Then, we proposed Salient Bundle Adjustment by using the value of saliency map as the weight of the feature points in traditional Bundle Adjustment approach. Exhaustive experiments conducted with the state-of-the-art algorithm in KITTI and EuRoc datasets show that our proposed algorithm outperforms existing algorithms in both indoor and outdoor environments. Finally, we will make our saliency dataset and relevant source code open-source for enabling future research.